{"id":"3f7f0627-0926-4ce0-9c50-f44f3b5ab4db","entityType":"agent","slug":"clawhub-aaron-he-zhu-performance-analyzer","name":"Performance Analyzer","canonicalUrl":"https://www.xpersona.co/agent/clawhub-aaron-he-zhu-performance-analyzer","canonicalPath":"/agent/clawhub-aaron-he-zhu-performance-analyzer","generatedAt":"2026-10-11T04:34:52.910Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":null},"description":"Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ... Skill: Performance Analyzer Owner: aaron-he-zhu Summary: Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T14:58:51.029Z | auto - Summary: Introduces compatibility and metadata updates, minor documentation revision, and reorganizes skill manifest file","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:performance-analyzer","sourceUrl":"https://clawhub.ai/aaron-he-zhu/performance-analyzer","homepage":"https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/aaron-he-zhu/performance-analyzer","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":null},"stars":null,"forks":null,"downloads":1194,"packageName":null,"latestVersion":"19.0.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:09:35.383Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T02:09:35.399Z","lastCrawledAt":"2026-10-11T02:09:35.383Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T02:09:35.383Z","lastVerifiedAt":null,"highlights":[{"version":"19.0.0","createdAt":"2026-07-24T14:58:51.029Z","changelog":"- Summary: Introduces compatibility and metadata updates, minor documentation revision, and reorganizes skill manifest files. - Updated version, metadata, and compatibility fields in SKILL.md - Added a new distribution-manifest.json file for packaging or distribution - Removed deprecated skill-card.md file - Slightly revised summary/description wording in SKILL.md (added “达人营销效果分析/投放复盘”)","fileCount":5,"zipByteSize":10467},{"version":"18.0.0","createdAt":"2026-07-13T06:25:23.620Z","changelog":"Version 18.0.0 - Updated metadata: discipline changed to \"influencer\", phase set to \"report\", geo-relevance marked \"low\"; tags/category updated to \"report\". - Analysis methodology now references STAR (Suitability/Trust/Appeal/Return) analysis instead of C3 analysis for scoring. - Clarified that the skill now provides measured Return (R) inputs for STAR, but SQS scoring is handled by the creator-content-auditor. - Removed the file: skill-card.md.","fileCount":4,"zipByteSize":9782},{"version":"17.0.0","createdAt":"2026-07-11T16:36:13.588Z","changelog":"- Version 17.0.0 removes the dedicated skill-card.md and fully transitions skill metadata into SKILL.md. - Updates version metadata to 17.0.0 and synchronizes author/version blocks. - No changes to features, analysis workflow, or instructions. - Housekeeping release: improves maintainability, no impact to usage or outputs.","fileCount":4,"zipByteSize":9789},{"version":"16.0.1","createdAt":"2026-07-08T13:01:18.924Z","changelog":"- Version bumped from 16.0.0 to 16.0.1 in metadata and related fields - No functional, structural, or instructional changes to the skill—documentation only update - All logic and contract details remain unchanged; file updated for version consistency","fileCount":4,"zipByteSize":9904},{"version":"16.0.0","createdAt":"2026-07-06T03:02:49.010Z","changelog":"- Version update to 16.0.0. - Updated metadata version references from 14.0.0 to 16.0.0. - No functional or instruction changes detected; documentation and contract remain consistent.","fileCount":4,"zipByteSize":9795},{"version":"14.0.0","createdAt":"2026-07-05T08:45:35.443Z","changelog":"- Version bump to 14.0.0. - Updated metadata \"version\" from 13.0.0 to 14.0.0. - No functional or instructional changes outside of version number.","fileCount":4,"zipByteSize":9717},{"version":"13.0.0","createdAt":"2026-07-05T02:33:53.503Z","changelog":"**Performance Analyzer v13.0.0 — Changelog** - Major documentation update: New, comprehensive SKILL.md with clear use cases, instructions, and data source details. - Adds detailed guidance for step-by-step influencer campaign analysis, including platform and creator ranking, sentiment, and attribution. - Explicitly clarifies this skill does not perform dollar-level return math (direct users to roi-calculator for that). - Includes “Quick Start” examples and an example output for easier onboarding. - Better outlines skill contracts, data requirements, and output expectations for both influencer and cross-channel paid ads use.","fileCount":4,"zipByteSize":9700}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:performance-analyzer","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T04:34:52.908Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-performance-analyzer/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":null},"readme":"Skill: Performance Analyzer\n\nOwner: aaron-he-zhu\n\nSummary: Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ...\n\nTags: latest:19.0.0\n\nVersion history:\n\nv19.0.0 | 2026-07-24T14:58:51.029Z | auto\n\n- Summary: Introduces compatibility and metadata updates, minor documentation revision, and reorganizes skill manifest files.\n- Updated version, metadata, and compatibility fields in SKILL.md\n- Added a new distribution-manifest.json file for packaging or distribution\n- Removed deprecated skill-card.md file\n- Slightly revised summary/description wording in SKILL.md (added “达人营销效果分析/投放复盘”)\n\nv18.0.0 | 2026-07-13T06:25:23.620Z | auto\n\nVersion 18.0.0\n\n- Updated metadata: discipline changed to \"influencer\", phase set to \"report\", geo-relevance marked \"low\"; tags/category updated to \"report\".\n- Analysis methodology now references STAR (Suitability/Trust/Appeal/Return) analysis instead of C3 analysis for scoring.\n- Clarified that the skill now provides measured Return (R) inputs for STAR, but SQS scoring is handled by the creator-content-auditor.\n- Removed the file: skill-card.md.\n\nv17.0.0 | 2026-07-11T16:36:13.588Z | auto\n\n- Version 17.0.0 removes the dedicated skill-card.md and fully transitions skill metadata into SKILL.md.\n- Updates version metadata to 17.0.0 and synchronizes author/version blocks.\n- No changes to features, analysis workflow, or instructions.\n- Housekeeping release: improves maintainability, no impact to usage or outputs.\n\nv16.0.1 | 2026-07-08T13:01:18.924Z | auto\n\n- Version bumped from 16.0.0 to 16.0.1 in metadata and related fields\n- No functional, structural, or instructional changes to the skill—documentation only update\n- All logic and contract details remain unchanged; file updated for version consistency\n\nv16.0.0 | 2026-07-06T03:02:49.010Z | auto\n\n- Version update to 16.0.0.\n- Updated metadata version references from 14.0.0 to 16.0.0.\n- No functional or instruction changes detected; documentation and contract remain consistent.\n\nv14.0.0 | 2026-07-05T08:45:35.443Z | auto\n\n- Version bump to 14.0.0.\n- Updated metadata \"version\" from 13.0.0 to 14.0.0.\n- No functional or instructional changes outside of version number.\n\nv13.0.0 | 2026-07-05T02:33:53.503Z | auto\n\n**Performance Analyzer v13.0.0 — Changelog**\n\n- Major documentation update: New, comprehensive SKILL.md with clear use cases, instructions, and data source details.\n- Adds detailed guidance for step-by-step influencer campaign analysis, including platform and creator ranking, sentiment, and attribution.\n- Explicitly clarifies this skill does not perform dollar-level return math (direct users to roi-calculator for that).\n- Includes “Quick Start” examples and an example output for easier onboarding.\n- Better outlines skill contracts, data requirements, and output expectations for both influencer and cross-channel paid ads use.\n\nArchive index:\n\nArchive v19.0.0: 5 files, 10467 bytes\n\nFiles: distribution-manifest.json (1183b), references/analysis-templates.md (10937b), skill-card.md (2201b), SKILL.md (10526b), _meta.json (140b)\n\nFile v19.0.0:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator. 达人营销效果分析/投放复盘'\nversion: \"19.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"influencer\", \"phase\": \"report\", \"geo-relevance\": \"low\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"report\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension STAR analysis (Suitability/Trust/Appeal/Return dimension reads) from [star-benchmark.md](../../../references/star-benchmark.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the measured Return (R) evidence — this skill contributes the inputs but does not compute the SQS (the creator-content-auditor gate does).\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — preregistered readback windows, outcome unit, alpha, practical-effect boundary, multiplicity/sequential policy, guardrails, and decision owner. Report statistical and practical flags separately; use `experiment.py` for deterministic `Calculated` evidence, and never substitute a universal p-value/lift rule or attribute a business action to the helper.\n- The STAR benchmark at [references/star-benchmark.md](../../../references/star-benchmark.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../scout/fit-scorer/SKILL.md), [campaign-planner](../../target/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Report family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../scout/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v19.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"19.0.0\",\n \"publishedAt\": 1784905131029\n}\n\nFile v19.0.0:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Do more of this |\n| [Element 2] | [metric] | Expand this approach |\n\n### What Didn't Work\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Adjust or eliminate |\n| [Element 2] | [metric] | Test alternatives |\n\n### Optimization Opportunities\n\n| Opportunity | Expected Impact | Effort | Priority |\n|-------------|-----------------|--------|----------|\n| [Opportunity 1] | [impact] | [effort] | High |\n| [Opportunity 2] | [impact] | [effort] | Medium |\n| [Opportunity 3] | [impact] | [effort] | Low |\n\n### Influencer Roster Recommendations\n\n| Influencer | Recommendation | Rationale |\n|------------|----------------|-----------|\n| @[handle1] | Renew/Ambassador | Top performer |\n| @[handle2] | Renew at same level | Solid results |\n| @[handle3] | Don't renew | Below expectations |\n| @[handle4] | Increase investment | High potential |\n\n### Future Campaign Recommendations\n\n1. **Platform Mix**: [recommendation]\n2. **Influencer Tier**: [recommendation]\n3. **Content Format**: [recommendation]\n4. **Messaging**: [recommendation]\n5. **Budget Allocation**: [recommendation]\n```\n\n---\n\n## Worked Example (full)\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output**:\n\n```markdown\n# Summer Skincare Campaign Performance Analysis\n\n## Executive Summary\n\n**Campaign Performance**: Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n## Top 3 Performers\n\n1. **@skincaresarah** - ROI 4.2:1, highest conversions\n2. **@glowwithgrace** - Best engagement (6.8%)\n3. **@beautyreview** - Highest reach per dollar\n\n## Key Learning\n\nTikTok outperformed Instagram significantly (3.5:1 ROI vs 2.1:1). Recommend shifting 20% of Instagram budget to TikTok for future campaigns.\n\n## Recommendation\n\nRenew partnerships with top 5 performers. Replace bottom 2 with TikTok-native creators.\n```\n\nFile v19.0.0:skill-card.md\n\n## Description:\n\nAnalyzes influencer campaign performance by comparing results against targets and benchmarks, ranking platforms, creators, and content, reading engagement quality and sentiment, and summarizing conversion attribution and learnings.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nMarketing teams, analysts, and campaign operators use this skill during or after influencer campaigns to evaluate results, compare creators and platforms, identify effective content patterns, and prepare recommendations for future planning.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Campaign analytics and business metrics may be summarized into memory notes.\n\nMitigation: Review the campaign data before use and avoid providing sensitive analytics unless persistent workspace notes are permitted.\n\nRisk: ROI, revenue, CPA, and budget recommendations may be misleading if treated as final financial decisions.\n\nMitigation: Treat outputs as draft business analysis and validate dollar-level conclusions with a dedicated ROI calculator or finance workflow before acting.\n\n## Reference(s):\n\n- [Performance Analyzer on ClawHub](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)\n- [Source homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)\n- [Analysis templates](references/analysis-templates.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown analysis report with metric tables, rankings, attribution summaries, and recommendations]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include memory write paths for campaign analysis and durable findings when supported by the host environment.]\n\n## Skill Version(s):\n\n19.0.0 (source: server release metadata and frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v19.0.0:distribution-manifest.json\n\n{\n \"capabilities\": [\n \"inline-delivery\",\n \"canonical-state-read\"\n ],\n \"capability_ceiling\": \"lite\",\n \"catalog_sha256\": \"6f0256cf52710f2916ecebaea0f3110c9313099ec4a69a11cac72ba9b2f3b940\",\n \"files\": [\n {\n \"bytes\": 10526,\n \"mode\": \"0644\",\n \"path\": \"SKILL.md\",\n \"sha256\": \"e7cebbd726167dd7e7ef7958b6e377d1c2503a39a9cef3c377a181f7e751cc3e\"\n },\n {\n \"bytes\": 10937,\n \"mode\": \"0644\",\n \"path\": \"references/analysis-templates.md\",\n \"sha256\": \"684a96b4e1250b392c15084cec140dfcc5f227e6a069cbb17f437b744c5fa384\"\n }\n ],\n \"files_sha256\": \"5c7a93e8c24a84b48a0e45e81a4ed050e3c07defc5e8c82d68149c9f7bb9964a\",\n \"hash_algorithm\": \"sha256\",\n \"kind\": \"standalone-skill\",\n \"manifest_excludes\": [\n \"distribution-manifest.json\"\n ],\n \"manifest_path\": \"distribution-manifest.json\",\n \"package_ceiling\": {\n \"max_bytes\": 1000000,\n \"max_files\": 64\n },\n \"profile\": \"lite\",\n \"profile_definition_sha256\": \"4598e1f7bba667ef928ea2a60a6252ad9348086e9eecab29437db442df2a568e\",\n \"schema_version\": \"1.1\",\n \"source\": {\n \"commit\": \"f552620c278afddcb25d09637a0cfcc1ce48faf4\",\n \"repository\": \"aaron-he-zhu/aaron-marketing-skills\"\n }\n}\n\nArchive v18.0.0: 4 files, 9782 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2575b), SKILL.md (10488b), _meta.json (140b)\n\nFile v18.0.0:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.'\nversion: \"18.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"18.0.0\", \"discipline\": \"influencer\", \"phase\": \"report\", \"geo-relevance\": \"low\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"report\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension STAR analysis (Suitability/Trust/Appeal/Return dimension reads) from [star-benchmark.md](../../../references/star-benchmark.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the measured Return (R) evidence — this skill contributes the inputs but does not compute the SQS (the creator-content-auditor gate does).\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — preregistered readback windows, outcome unit, alpha, practical-effect boundary, multiplicity/sequential policy, guardrails, and decision owner. Report statistical and practical flags separately; use `experiment.py` for deterministic `Calculated` evidence, and never substitute a universal p-value/lift rule or attribute a business action to the helper.\n- The STAR benchmark at [references/star-benchmark.md](../../../references/star-benchmark.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../scout/fit-scorer/SKILL.md), [campaign-planner](../../target/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Report family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../scout/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v18.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"18.0.0\",\n \"publishedAt\": 1783923923620\n}\n\nFile v18.0.0:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Do more of this |\n| [Element 2] | [metric] | Expand this approach |\n\n### What Didn't Work\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Adjust or eliminate |\n| [Element 2] | [metric] | Test alternatives |\n\n### Optimization Opportunities\n\n| Opportunity | Expected Impact | Effort | Priority |\n|-------------|-----------------|--------|----------|\n| [Opportunity 1] | [impact] | [effort] | High |\n| [Opportunity 2] | [impact] | [effort] | Medium |\n| [Opportunity 3] | [impact] | [effort] | Low |\n\n### Influencer Roster Recommendations\n\n| Influencer | Recommendation | Rationale |\n|------------|----------------|-----------|\n| @[handle1] | Renew/Ambassador | Top performer |\n| @[handle2] | Renew at same level | Solid results |\n| @[handle3] | Don't renew | Below expectations |\n| @[handle4] | Increase investment | High potential |\n\n### Future Campaign Recommendations\n\n1. **Platform Mix**: [recommendation]\n2. **Influencer Tier**: [recommendation]\n3. **Content Format**: [recommendation]\n4. **Messaging**: [recommendation]\n5. **Budget Allocation**: [recommendation]\n```\n\n---\n\n## Worked Example (full)\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output**:\n\n```markdown\n# Summer Skincare Campaign Performance Analysis\n\n## Executive Summary\n\n**Campaign Performance**: Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n## Top 3 Performers\n\n1. **@skincaresarah** - ROI 4.2:1, highest conversions\n2. **@glowwithgrace** - Best engagement (6.8%)\n3. **@beautyreview** - Highest reach per dollar\n\n## Key Learning\n\nTikTok outperformed Instagram significantly (3.5:1 ROI vs 2.1:1). Recommend shifting 20% of Instagram budget to TikTok for future campaigns.\n\n## Recommendation\n\nRenew partnerships with top 5 performers. Replace bottom 2 with TikTok-native creators.\n```\n\nFile v18.0.0:skill-card.md\n\n## Description:
\nAnalyzes influencer campaign performance against targets and benchmarks, ranks platforms, creators, and content, reviews engagement quality and sentiment, attributes conversions, and produces ranked learnings.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams, growth teams, and campaign analysts use this skill after or during influencer campaigns to turn campaign analytics, creator reports, web analytics, sales data, and promo-code results into a structured performance readout. It helps compare creators and platforms, identify content patterns that worked, and prepare recommendations for future campaigns.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Campaign analytics, sales data, promo-code results, and conversion data may be sensitive commercial information.
\nMitigation: Install and run the skill only where the agent is permitted to process those inputs, and review what is saved to shared memory before reusing it.
\nRisk: ROI, CPA, revenue, and attribution conclusions can be misleading when source data is incomplete or attribution methods are mixed.
\nMitigation: Treat financial conclusions as draft analysis, label measured, user-provided, and estimated inputs clearly, and confirm dollar-level return with a dedicated ROI workflow.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)
\n- [Publisher homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [Analysis templates](artifact/references/analysis-templates.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance]
\n**Output Format:** [Markdown performance analysis with scorecards, ranking tables, attribution breakdowns, and recommendations]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May include memory-save guidance for campaign analysis and hot-cache facts when the host environment supports shared memory.]
\n\n## Skill Version(s):
\n18.0.0 (source: evidence.release.version and SKILL.md frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v17.0.0: 4 files, 9789 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2582b), SKILL.md (10469b), _meta.json (140b)\n\nFile v17.0.0:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.'\nversion: \"17.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension C3 analysis (ACE/ART scope scores) from [c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the ROI score and CVI rollup — this skill contributes the inputs but does not compute the rollup.\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — preregistered readback windows, outcome unit, alpha, practical-effect boundary, multiplicity/sequential policy, guardrails, and decision owner. Report statistical and practical flags separately; use `experiment.py` for deterministic `Calculated` evidence, and never substitute a universal p-value/lift rule or attribute a business action to the helper.\n- The C3 benchmark at [references/c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../discover/fit-scorer/SKILL.md), [campaign-planner](../../plan/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Measure family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../discover/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v17.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"17.0.0\",\n \"publishedAt\": 1783787773588\n}\n\nFile v17.0.0:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Do more of this |\n| [Element 2] | [metric] | Expand this approach |\n\n### What Didn't Work\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Adjust or eliminate |\n| [Element 2] | [metric] | Test alternatives |\n\n### Optimization Opportunities\n\n| Opportunity | Expected Impact | Effort | Priority |\n|-------------|-----------------|--------|----------|\n| [Opportunity 1] | [impact] | [effort] | High |\n| [Opportunity 2] | [impact] | [effort] | Medium |\n| [Opportunity 3] | [impact] | [effort] | Low |\n\n### Influencer Roster Recommendations\n\n| Influencer | Recommendation | Rationale |\n|------------|----------------|-----------|\n| @[handle1] | Renew/Ambassador | Top performer |\n| @[handle2] | Renew at same level | Solid results |\n| @[handle3] | Don't renew | Below expectations |\n| @[handle4] | Increase investment | High potential |\n\n### Future Campaign Recommendations\n\n1. **Platform Mix**: [recommendation]\n2. **Influencer Tier**: [recommendation]\n3. **Content Format**: [recommendation]\n4. **Messaging**: [recommendation]\n5. **Budget Allocation**: [recommendation]\n```\n\n---\n\n## Worked Example (full)\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output**:\n\n```markdown\n# Summer Skincare Campaign Performance Analysis\n\n## Executive Summary\n\n**Campaign Performance**: Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n## Top 3 Performers\n\n1. **@skincaresarah** - ROI 4.2:1, highest conversions\n2. **@glowwithgrace** - Best engagement (6.8%)\n3. **@beautyreview** - Highest reach per dollar\n\n## Key Learning\n\nTikTok outperformed Instagram significantly (3.5:1 ROI vs 2.1:1). Recommend shifting 20% of Instagram budget to TikTok for future campaigns.\n\n## Recommendation\n\nRenew partnerships with top 5 performers. Replace bottom 2 with TikTok-native creators.\n```\n\nFile v17.0.0:skill-card.md\n\n## Description:
\nPerformance Analyzer helps agents evaluate influencer campaign results by comparing metrics against targets and benchmarks, ranking platforms, creators, and content, reading engagement quality and sentiment, and summarizing conversion attribution and learnings.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams, influencer program operators, and agents use this skill mid-flight or after a campaign to assess performance, compare creators and platforms, identify winning content patterns, and prepare recommendations for future planning.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: ROI, cost-per-result, revenue, or budget-allocation outputs may exceed the skill's stated boundary.
\nMitigation: Route dollar-level return math and budget-shift decisions to a dedicated ROI skill or human review before acting on them.
\nRisk: Campaign analytics, sales or revenue data, and durable memory entries may contain sensitive business information.
\nMitigation: Provide only necessary campaign data, review memory writes, and avoid persisting confidential details unless the workspace policy allows it.
\nRisk: API keys or connector credentials may be exposed if pasted into prompts.
\nMitigation: Provide credentials only through environment variables or approved secret-management mechanisms.
\n\n\n## Reference(s):
\n- [Analysis templates](references/analysis-templates.md)
\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance, shell commands]
\n**Output Format:** [Markdown analysis with tables, ranked recommendations, and optional inline shell commands]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May write campaign analyses to memory paths and promote durable findings when the host supports memory.]
\n\n## Skill Version(s):
\n17.0.0 (source: server release metadata and SKILL.md frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v16.0.1: 4 files, 9904 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2919b), SKILL.md (10534b), _meta.json (140b)\n\nFile v16.0.1:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.'\nversion: \"16.0.1\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"16.0.1\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension C3 analysis (ACE/ART scope scores) from [c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the ROI score and CVI rollup — this skill contributes the inputs but does not compute the rollup.\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — readback windows and promote/keep-testing/rollback rule. Call a creator/format/platform a real winner only when it clears the documented significance bar: Mann-Whitney U at p < 0.05 **and** ≥ 15% relative lift over control, with a bootstrap confidence interval on the lift that excludes zero. Below the sample floor, stay Keep-testing. Method only — compute by hand or in a notebook, no scipy or stats dependency.\n- The C3 benchmark at [references/c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../discover/fit-scorer/SKILL.md), [campaign-planner](../../plan/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Measure family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../discover/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v16.0.1:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"16.0.1\",\n \"publishedAt\": 1783515678924\n}\n\nFile v16.0.1:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Do more of this |\n| [Element 2] | [metric] | Expand this approach |\n\n### What Didn't Work\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Adjust or eliminate |\n| [Element 2] | [metric] | Test alternatives |\n\n### Optimization Opportunities\n\n| Opportunity | Expected Impact | Effort | Priority |\n|-------------|-----------------|--------|----------|\n| [Opportunity 1] | [impact] | [effort] | High |\n| [Opportunity 2] | [impact] | [effort] | Medium |\n| [Opportunity 3] | [impact] | [effort] | Low |\n\n### Influencer Roster Recommendations\n\n| Influencer | Recommendation | Rationale |\n|------------|----------------|-----------|\n| @[handle1] | Renew/Ambassador | Top performer |\n| @[handle2] | Renew at same level | Solid results |\n| @[handle3] | Don't renew | Below expectations |\n| @[handle4] | Increase investment | High potential |\n\n### Future Campaign Recommendations\n\n1. **Platform Mix**: [recommendation]\n2. **Influencer Tier**: [recommendation]\n3. **Content Format**: [recommendation]\n4. **Messaging**: [recommendation]\n5. **Budget Allocation**: [recommendation]\n```\n\n---\n\n## Worked Example (full)\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output**:\n\n```markdown\n# Summer Skincare Campaign Performance Analysis\n\n## Executive Summary\n\n**Campaign Performance**: Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n## Top 3 Performers\n\n1. **@skincaresarah** - ROI 4.2:1, highest conversions\n2. **@glowwithgrace** - Best engagement (6.8%)\n3. **@beautyreview** - Highest reach per dollar\n\n## Key Learning\n\nTikTok outperformed Instagram significantly (3.5:1 ROI vs 2.1:1). Recommend shifting 20% of Instagram budget to TikTok for future campaigns.\n\n## Recommendation\n\nRenew partnerships with top 5 performers. Replace bottom 2 with TikTok-native creators.\n```\n\nFile v16.0.1:skill-card.md\n\n## Description:
\nAnalyzes influencer campaign performance by scoring metrics against targets and benchmarks, ranking platforms, creators, and content, reading engagement quality and sentiment, attributing conversions, and producing ranked learnings.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams, creator partnerships managers, and analysts use this skill during or after influencer campaigns to compare results against goals, identify winning creators and content patterns, and prepare optimization recommendations. It is intended for performance readouts and planning support, with dollar-level ROI math routed for review or to a dedicated ROI calculator.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill can analyze and save campaign, creator, sales, revenue, and ROI-related data in workspace memory.
\nMitigation: Use it only in workspaces where retention and sharing rules are acceptable, and avoid providing sensitive client data unless the workspace is approved for that data.
\nRisk: The security summary notes that the skill blurs its non-financial boundary by directing ROI, CPA, and revenue analysis.
\nMitigation: Treat ROI, CPA, and revenue conclusions as review-required, or route dollar-level return math to a dedicated ROI calculator.
\nRisk: Campaign reports may mix measured API data with creator-supplied exports or screenshots that can differ by timing and rounding.
\nMitigation: Label source types clearly and review material discrepancies before using the analysis for budget or roster decisions.
\n\n\n## Reference(s):
\n- [Performance Analyzer on ClawHub](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)
\n- [Project homepage from metadata](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [Analysis Templates](references/analysis-templates.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, shell commands, guidance]
\n**Output Format:** [Markdown analysis with tables, scorecards, rankings, attribution summaries, and recommendations; may include an inline shell command for optional YouTube metric collection.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May save campaign, creator, revenue, ROI, and recommendation summaries to workspace memory files.]
\n\n## Skill Version(s):
\n16.0.1 (source: server evidence release version and SKILL.md frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v16.0.0: 4 files, 9795 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2785b), SKILL.md (10532b), _meta.json (140b)\n\nFile v16.0.0:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.'\nversion: \"16.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"16.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension C3 analysis (ACE/ART scope scores) from [c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the ROI score and CVI rollup — this skill contributes the inputs but does not compute the rollup.\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — readback windows and promote/keep-testing/rollback rule. Call a creator/format/platform a real winner only when it clears the documented significance bar: Mann-Whitney U at p < 0.05 **and** ≥ 15% relative lift over control, with a bootstrap confidence interval on the lift that excludes zero. Below the sample floor, stay Keep-testing. Method only — compute by hand or in a notebook, no scipy or stats dependency.\n- The C3 benchmark at [references/c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../discover/fit-scorer/SKILL.md), [campaign-planner](../../plan/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Track family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../discover/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v16.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"16.0.0\",\n \"publishedAt\": 1783306969010\n}\n\nFile v16.0.0:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Do more of this |\n| [Element 2] | [metric] | Expand this approach |\n\n### What Didn't Work\n\n| Element | Performance | Recommendation |\n|---------|-------------|----------------|\n| [Element 1] | [metric] | Adjust or eliminate |\n| [Element 2] | [metric] | Test alternatives |\n\n### Optimization Opportunities\n\n| Opportunity | Expected Impact | Effort | Priority |\n|-------------|-----------------|--------|----------|\n| [Opportunity 1] | [impact] | [effort] | High |\n| [Opportunity 2] | [impact] | [effort] | Medium |\n| [Opportunity 3] | [impact] | [effort] | Low |\n\n### Influencer Roster Recommendations\n\n| Influencer | Recommendation | Rationale |\n|------------|----------------|-----------|\n| @[handle1] | Renew/Ambassador | Top performer |\n| @[handle2] | Renew at same level | Solid results |\n| @[handle3] | Don't renew | Below expectations |\n| @[handle4] | Increase investment | High potential |\n\n### Future Campaign Recommendations\n\n1. **Platform Mix**: [recommendation]\n2. **Influencer Tier**: [recommendation]\n3. **Content Format**: [recommendation]\n4. **Messaging**: [recommendation]\n5. **Budget Allocation**: [recommendation]\n```\n\n---\n\n## Worked Example (full)\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output**:\n\n```markdown\n# Summer Skincare Campaign Performance Analysis\n\n## Executive Summary\n\n**Campaign Performance**: Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n## Top 3 Performers\n\n1. **@skincaresarah** - ROI 4.2:1, highest conversions\n2. **@glowwithgrace** - Best engagement (6.8%)\n3. **@beautyreview** - Highest reach per dollar\n\n## Key Learning\n\nTikTok outperformed Instagram significantly (3.5:1 ROI vs 2.1:1). Recommend shifting 20% of Instagram budget to TikTok for future campaigns.\n\n## Recommendation\n\nRenew partnerships with top 5 performers. Replace bottom 2 with TikTok-native creators.\n```\n\nFile v16.0.0:skill-card.md\n\n## Description:
\nUse when the user asks to analyze influencer campaign performance, compare influencers, or find what content worked; produces metric scorecards against targets and benchmarks, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings; not for dollar-level return math.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams, analysts, and campaign operators use this skill during or after influencer campaigns to compare results against targets and benchmarks, rank platforms, creators, and content, evaluate engagement quality and sentiment, attribute conversions, and turn findings into ranked learnings.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill may produce ROI, CPA, revenue-attribution, budget-allocation, or renew/drop recommendations that users could treat as final business decisions.
\nMitigation: Review dollar-level calculations and route ROI, CPA, revenue attribution, budget shifts, and partnership renewal decisions to a dedicated ROI calculator or human reviewer before acting.
\nRisk: The skill can handle sensitive campaign analytics, sales metrics, and creator performance data, and may write conclusions into memory.
\nMitigation: Provide only the campaign and sales metrics needed for the analysis, review generated memory entries before retaining or sharing them, and avoid unnecessary personal or confidential data.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)
\n- [Publisher profile](https://clawhub.ai/user/aaron-he-zhu)
\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [analysis-templates.md](references/analysis-templates.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, shell commands, guidance]
\n**Output Format:** [Markdown performance analysis with tables, ranked recommendations, and optional inline shell commands]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May write campaign analysis and durable conclusions to memory paths when used by a compatible host.]
\n\n## Skill Version(s):
\n16.0.0 (source: server release metadata and artifact frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v14.0.0: 4 files, 9717 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2504b), SKILL.md (10532b), _meta.json (140b)\n\nFile v14.0.0:SKILL.md\n\n---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.'\nversion: \"14.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"14.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to `memory/hot-cache.md`.\n- **Done when**:\n - Core metrics are scored against target and benchmark with a performance verdict.\n - Top and bottom performers are ranked with reasons, and content patterns that worked are named.\n - Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.\n- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) — turn measured performance into dollar-level return.\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.\n\nWhere a connector could speed the work, the skill marks it with a `~~` placeholder:\n\n- `~~social platform analytics` — native reach/engagement/video metrics per post.\n- `~~web analytics` — site traffic, click-through, and on-site conversion data.\n\n**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py\" videos @creator --limit 20` pulls the actual per-video views/likes/comments for the campaign window — **Measured** platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free `YOUTUBE_API_KEY`. See [scripts/connectors/README.md](../../../scripts/connectors/README.md).\n- `~~ecommerce / sales platform` — revenue, orders, AOV, promo-code redemptions.\n- `~~influencer database` — historical creator benchmarks for comparison.\n\nNo placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free/keyless data recipe per category.\n\n## Instructions\n\nWork the steps in order. Each fill-in template lives in [references/analysis-templates.md](references/analysis-templates.md) — copy the matching block and populate it.\n\n1. **Gather performance data** — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.\n2. **Analyze core metrics** — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.\n3. **Analyze by platform** — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.\n4. **Analyze by influencer** — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.\n5. **Content performance analysis** — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.\n6. **Engagement quality analysis** — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.\n7. **Conversion & attribution analysis** — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.\n8. **Generate insights & recommendations** — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.\n\nBefore naming any creator/format/platform a real winner, clear the significance bar in [measurement-protocol.md](../../../references/measurement-protocol.md) — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension C3 analysis (ACE/ART scope scores) from [c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md), and hand the measured inputs to [roi-calculator](../roi-calculator/SKILL.md) for the ROI score and CVI rollup — this skill contributes the inputs but does not compute the rollup.\n\n## Example\n\n**User**: \"Analyze performance of our summer skincare campaign with 10 influencers\"\n\n**Output** (abridged — full version in [references/analysis-templates.md](references/analysis-templates.md)):\n\n```markdown\n# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators.\n```\n\n## Reference Materials\n\n- [references/analysis-templates.md](references/analysis-templates.md) — the eight fill-in step templates plus the full worked example.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and handoff format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — verified free/keyless data recipes per connector category.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — readback windows and promote/keep-testing/rollback rule. Call a creator/format/platform a real winner only when it clears the documented significance bar: Mann-Whitney U at p < 0.05 **and** ≥ 15% relative lift over control, with a bootstrap confidence interval on the lift that excludes zero. Below the sample floor, stay Keep-testing. Method only — compute by hand or in a notebook, no scipy or stats dependency.\n- The C3 benchmark at [references/c3/scoring-architecture.md](../../../references/c3/scoring-architecture.md) — scoring architecture when a structured score is needed.\n- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generator/SKILL.md), [fit-scorer](../../discover/fit-scorer/SKILL.md), [campaign-planner](../../plan/campaign-planner/SKILL.md).\n\n## Next Best Skill\n\n**Primary**: [roi-calculator](../roi-calculator/SKILL.md) — convert measured performance into dollar-level ROI, cost-per-result, and payback math.\n\n**Alternates** (same Track family):\n\n- [report-generator](../report-generator/SKILL.md) — package the analysis into a formal stakeholder report.\n- [fit-scorer](../../discover/fit-scorer/SKILL.md) — feed proven performers back into creator scoring for the next round.\n\n**Termination note**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.\n\nFile v14.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"14.0.0\",\n \"publishedAt\": 1783241135443\n}\n\nFile v14.0.0:references/analysis-templates.md\n\n# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |\n```\n\n---\n\n## Step 4 — Analyze by Influencer\n\n```markdown\n## Influencer Performance\n\n### Influencer Ranking\n\n| Rank | Influencer | Reach | ER | Conversions | ROI | Score |\n|------|------------|-------|-------|-------------|-----|-------|\n| 1 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐⭐ |\n| 2 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 3 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐⭐ |\n| 4 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐⭐ |\n| 5 | @[handle] | [X] | [%] | [X] | [X]:1 | ⭐⭐ |\n\n### Top Performers Deep Dive\n\n#### #1: @[handle]\n\n| Metric | Result | vs. Campaign Avg |\n|--------|--------|------------------|\n| Reach | [X] | [+/-X%] |\n| Engagement Rate | [%] | [+/-X%] |\n| Video Completion | [%] | [+/-X%] |\n| Click-through Rate | [%] | [+/-X%] |\n| Conversion Rate | [%] | [+/-X%] |\n| Cost per Conversion | $[X] | [+/-X%] |\n\n**Why They Performed Well**:\n- [Reason 1]\n- [Reason 2]\n- [Reason 3]\n\n**Content Analysis**:\n- Format: [what they posted]\n- Hook: [how they opened]\n- Message: [how they communicated]\n- CTA: [what they asked viewers to do]\n\n**Recommendation**: [Renew/Expand/Ambassador potential]\n\n### Underperformers Analysis\n\n#### @[handle]\n\n**Results**: [summary]\n**Why Underperformed**: [analysis]\n**Learning**: [what to do differently]\n```\n\n---\n\n## Step 5 — Content Performance Analysis\n\n```markdown\n## Content Performance\n\n### Top Performing Content\n\n| Rank | Creator | Platform | Format | Reach | ER | Key Feature |\n|------|---------|----------|--------|-------|-------|-------------|\n| 1 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 2 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n| 3 | @[handle] | [platform] | [format] | [X] | [%] | [why it worked] |\n\n### Content Format Analysis\n\n| Format | Pieces | Avg Reach | Avg ER | Best Performer |\n|--------|--------|-----------|--------|----------------|\n| Video (Reels/TikTok) | [#] | [X] | [%] | @[handle] |\n| Static Images | [#] | [X] | [%] | @[handle] |\n| Carousels | [#] | [X] | [%] | @[handle] |\n| Stories | [#] | [X] | [%] | @[handle] |\n| YouTube Videos | [#] | [X] | [%] | @[handle] |\n\n### Content Theme Analysis\n\n| Theme | Pieces | Avg ER | Conversion Rate | Notes |\n|-------|--------|--------|-----------------|-------|\n| Product demo | [#] | [%] | [%] | [notes] |\n| Lifestyle | [#] | [%] | [%] | [notes] |\n| Tutorial | [#] | [%] | [%] | [notes] |\n| Review | [#] | [%] | [%] | [notes] |\n| Unboxing | [#] | [%] | [%] | [notes] |\n\n### Winning Content Patterns\n\n**Hook Patterns That Worked**:\n- [Pattern 1]: [examples]\n- [Pattern 2]: [examples]\n\n**Messaging That Resonated**:\n- [Message type 1]: [why it worked]\n- [Message type 2]: [why it worked]\n\n**Visual Elements That Performed**:\n- [Element 1]\n- [Element 2]\n```\n\n---\n\n## Step 6 — Engagement Quality Analysis\n\n```markdown\n## Engagement Quality\n\n### Engagement Breakdown\n\n| Type | Volume | % of Total | Quality Assessment |\n|------|--------|------------|-------------------|\n| Likes | [X] | [%] | Passive |\n| Comments | [X] | [%] | [quality] |\n| Saves | [X] | [%] | High intent |\n| Shares | [X] | [%] | High value |\n| Link clicks | [X] | [%] | Direct action |\n\n### Comment Sentiment Analysis\n\n| Sentiment | % | Examples |\n|-----------|---|----------|\n| Positive | [%] | \"[example]\", \"[example]\" |\n| Neutral/Questions | [%] | \"[example]\", \"[example]\" |\n| Negative | [%] | \"[example]\", \"[example]\" |\n\n**Key Themes in Comments**:\n- [Theme 1]: [frequency] mentions\n- [Theme 2]: [frequency] mentions\n- [Theme 3]: [frequency] mentions\n\n### Purchase Intent Signals\n\n| Signal | Count | Examples |\n|--------|-------|----------|\n| \"Where to buy\" questions | [#] | |\n| Price questions | [#] | |\n| Code requests | [#] | |\n| \"Just ordered\" | [#] | |\n| Tagged friends | [#] | |\n\n### Engagement Quality Score: [X/10]\n```\n\n---\n\n## Step 7 — Conversion & Attribution Analysis\n\n```markdown\n## Conversion Analysis\n\n### Conversion Funnel\n\n```\nReach [XXXXXXXXXX] 1,000,000 (100%)\n ↓\nEngagements [XXXXXXX ] 150,000 (15%)\n ↓\nLink Clicks [XXX ] 25,000 (2.5%)\n ↓\nSite Visits [XX ] 20,000 (2%)\n ↓\nAdd to Cart [X ] 5,000 (0.5%)\n ↓\nPurchases [X ] 2,000 (0.2%)\n```\n\n### Conversion Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| Click-through Rate | [%] | [%] | ✅/❌ |\n| Landing Page CVR | [%] | [%] | ✅/❌ |\n| Overall CVR | [%] | [%] | ✅/❌ |\n| Cost per Click | $[X] | $[X] | ✅/❌ |\n| Cost per Conversion | $[X] | $[X] | ✅/❌ |\n\n### Attribution by Method\n\n| Method | Conversions | Revenue | % of Total |\n|--------|-------------|---------|------------|\n| Promo codes | [X] | $[X] | [%] |\n| UTM tracking | [X] | $[X] | [%] |\n| Direct attribution | [X] | $[X] | [%] |\n| Estimated influence | [X] | $[X] | [%] |\n\n### Promo Code Performance\n\n| Code | Influencer | Uses | Revenue | AOV |\n|------|------------|------|---------|-----|\n| [CODE1] | @[handle] | [X] | $[X] | $[X] |\n| [CODE2] | @[handle] | [X] | $[X] | $[X] |\n| [CODE3] | @[handle] | [X] | $[X] | $[X] |\n```\n\n---\n\n## Step 8 — Generate Insights & Recommendations\n\n```markdown\n## Insights & Recommendations\n\n### Top 5 Learnings\n\n1. **[Learning 1]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n2. **[Learning 2]**\n - What we observed: [data]\n - Why it matters: [significance]\n - Future application: [how to use this]\n\n[Continue for top 5]\n\n### What Worked\n\n| E\n\nArchive v13.0.0: 4 files, 9700 bytes\n\nFiles: references/analysis-templates.md (10937b), skill-card.md (2486b), SKILL.md (10557b), _meta.json (140b)","readmeExcerpt":"Skill: Performance Analyzer Owner: aaron-he-zhu Summary: Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T14:58:51.029Z | auto - Summary: Introduces compatibility and metadata updates, minor documentation revision, and reorganizes skill manifest file","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"Analyze performance of [campaign name] influencer campaign"},{"language":"text","snippet":"Compare performance of these influencers from [campaign]: @handle1, @handle2, @handle3"},{"language":"markdown","snippet":"# Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)\n\n| Metric | Result | Target | Status |\n|--------|--------|--------|--------|\n| Total Reach | 2.4M | 2M | ✅ +20% |\n| Engagement Rate | 4.2% | 3.5% | ✅ +20% |\n| Conversions | 1,847 | 2,000 | ⚠️ -8% |\n| Revenue | $142,500 | $150,000 | ⚠️ -5% |\n| ROI | 2.8:1 | 3:1 | ⚠️ -7% |\n\n**Top 3**: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$).\n**Key learning**: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok.\n**Recommendation**: Renew top 5; replace bottom 2 with TikTok-native creators."},{"language":"markdown","snippet":"### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |"},{"language":"markdown","snippet":"## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]"},{"language":"markdown","snippet":"## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | [X] | |\n| Shares | [X] | |\n| Average Watch Time | [X]s | |\n| Completion Rate | [%] | |"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: performance-analyzer\nslug: performance-analyzer\ndisplayName: \"Performance Analyzer · 效果分析\"\nsummary: \"活动效果分析:达成 vs 目标、平台与创作者维度拆解、优化建议\"\ndescription: 'Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator. 达人营销效果分析/投放复盘'\nversion: \"19.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use mid-flight or post-campaign when a user wants to evaluate influencer results, compare creators against each other, find top-performing content or formats, judge engagement quality and comment sentiment, connect influencer activity to conversions, or build performance benchmarks for future planning.\"\nargument-hint: \" [platform or influencer handles]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"influencer\", \"phase\": \"report\", \"geo-relevance\": \"low\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"report\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# Performance Analyzer\n\nAnalyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.\n\n> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed [ad-test-designer](../../../ad/orchestrate/ad-test-designer/SKILL.md) (what to test) and [paid-measurement-loop](../../../ad/scale/paid-measurement-loop/SKILL.md) (what to read back). Save paid runs under `memory/ad/performance-analyzer/`.\n\n## Quick Start\n\n```\nAnalyze performance of [campaign name] influencer campaign\n```\n\nCompare creators within one campaign:\n\n```\nCompare performance of these influencers from [campaign]: @handle1, @handle2, @handle3\n```\n\n## Skill Contract\n\n- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from `memory/creators/.md` ([creator-registry](../../../protocol/creator-registry/SKILL.md) roster records) when present.\n- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-.md` covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.\n- **Promo"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"performance-analyzer\",\n \"version\": \"19.0.0\",\n \"publishedAt\": 1784905131029\n}"},{"path":"references/analysis-templates.md","content":"# Performance Analyzer — Analysis Templates\n\nFill-in templates for each step of the influencer performance analysis. Each maps to a numbered step in [../SKILL.md](../SKILL.md) Instructions.\n\nRepo-root links from this file use `../../../`.\n\n- [skill-contract.md](../../../../references/skill-contract.md)\n- [state-model.md](../../../../references/state-model.md)\n- [CONNECTORS.md](../../../../CONNECTORS.md)\n\n---\n\n## Step 1 — Gather Performance Data\n\n```markdown\n### Performance Data Collection\n\n**Campaign**: [name]\n**Period**: [start] - [end]\n**Influencers**: [count]\n**Platforms**: [platforms]\n\n### Data Sources\n\n| Source | Metrics Available | Collection Method |\n|--------|-------------------|-------------------|\n| Native analytics | Reach, views, engagement | Platform export |\n| Influencer reports | Screenshots/exports | From creators |\n| Website analytics | Traffic, conversions | GA/tracking |\n| Sales data | Revenue, orders | E-commerce platform |\n| Promo code data | Redemptions | Sales system |\n```\n\n---\n\n## Step 2 — Analyze Core Metrics\n\n```markdown\n## Campaign Performance Overview\n\n### Summary Metrics\n\n| Metric | Result | Target | vs. Target | vs. Benchmark |\n|--------|--------|--------|------------|---------------|\n| Total Reach | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Impressions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Total Engagements | [X] | [X] | [+/-X%] | [+/-X%] |\n| Engagement Rate | [X%] | [X%] | [+/-X%] | [+/-X%] |\n| Total Video Views | [X] | [X] | [+/-X%] | [+/-X%] |\n| Link Clicks | [X] | [X] | [+/-X%] | [+/-X%] |\n| Promo Code Uses | [X] | [X] | [+/-X%] | N/A |\n| Conversions | [X] | [X] | [+/-X%] | [+/-X%] |\n| Revenue | $[X] | $[X] | [+/-X%] | N/A |\n\n### Performance Score: [X/10]\n\n**Assessment**: [Excellent/Good/Average/Below Average/Poor]\n\n### Key Highlights\n\n✅ **What Exceeded Expectations**:\n- [Highlight 1]\n- [Highlight 2]\n\n⚠️ **What Underperformed**:\n- [Issue 1]\n- [Issue 2]\n```\n\n---\n\n## Step 3 — Analyze by Platform\n\n```markdown\n## Platform Performance\n\n### Platform Comparison\n\n| Platform | Reach | Engagements | ER | Clicks | Conversions | CPA |\n|----------|-------|-------------|-------|--------|-------------|-----|\n| Instagram | [X] | [X] | [%] | [X] | [X] | $[X] |\n| TikTok | [X] | [X] | [%] | [X] | [X] | $[X] |\n| YouTube | [X] | [X] | [%] | [X] | [X] | $[X] |\n| **Total** | **[X]** | **[X]** | **[%]** | **[X]** | **[X]** | **$[X]** |\n\n### Platform Insights\n\n**Best Performing Platform**: [Platform]\n- Why: [analysis]\n- Key content: [what worked]\n\n**Underperforming Platform**: [Platform]\n- Why: [analysis]\n- Improvement opportunity: [suggestion]\n\n### Platform-Specific Metrics\n\n#### Instagram\n\n| Metric | Feed Posts | Reels | Stories |\n|--------|------------|-------|---------|\n| Reach | [X] | [X] | [X] |\n| Engagements | [X] | [X] | [X] |\n| ER | [%] | [%] | [%] |\n| Saves | [X] | [X] | N/A |\n| Shares | [X] | [X] | [X] |\n\n#### TikTok\n\n| Metric | Result | Benchmark |\n|--------|--------|-----------|\n| Views | [X] | |\n| Likes | [X] | |\n| Comments | "},{"path":"skill-card.md","content":"## Description:\n\nAnalyzes influencer campaign performance by comparing results against targets and benchmarks, ranking platforms, creators, and content, reading engagement quality and sentiment, and summarizing conversion attribution and learnings.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nMarketing teams, analysts, and campaign operators use this skill during or after influencer campaigns to evaluate results, compare creators and platforms, identify effective content patterns, and prepare recommendations for future planning.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Campaign analytics and business metrics may be summarized into memory notes.\n\nMitigation: Review the campaign data before use and avoid providing sensitive analytics unless persistent workspace notes are permitted.\n\nRisk: ROI, revenue, CPA, and budget recommendations may be misleading if treated as final financial decisions.\n\nMitigation: Treat outputs as draft business analysis and validate dollar-level conclusions with a dedicated ROI calculator or finance workflow before acting.\n\n## Reference(s):\n\n- [Performance Analyzer on ClawHub](https://clawhub.ai/aaron-he-zhu/skills/performance-analyzer)\n- [Source homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)\n- [Analysis templates](references/analysis-templates.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown analysis report with metric tables, rankings, attribution summaries, and recommendations]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include memory write paths for campaign analysis and durable findings when supported by the host environment.]\n\n## Skill Version(s):\n\n19.0.0 (source: server release metadata and frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"distribution-manifest.json","content":"{\n \"capabilities\": [\n \"inline-delivery\",\n \"canonical-state-read\"\n ],\n \"capability_ceiling\": \"lite\",\n \"catalog_sha256\": \"6f0256cf52710f2916ecebaea0f3110c9313099ec4a69a11cac72ba9b2f3b940\",\n \"files\": [\n {\n \"bytes\": 10526,\n \"mode\": \"0644\",\n \"path\": \"SKILL.md\",\n \"sha256\": \"e7cebbd726167dd7e7ef7958b6e377d1c2503a39a9cef3c377a181f7e751cc3e\"\n },\n {\n \"bytes\": 10937,\n \"mode\": \"0644\",\n \"path\": \"references/analysis-templates.md\",\n \"sha256\": \"684a96b4e1250b392c15084cec140dfcc5f227e6a069cbb17f437b744c5fa384\"\n }\n ],\n \"files_sha256\": \"5c7a93e8c24a84b48a0e45e81a4ed050e3c07defc5e8c82d68149c9f7bb9964a\",\n \"hash_algorithm\": \"sha256\",\n \"kind\": \"standalone-skill\",\n \"manifest_excludes\": [\n \"distribution-manifest.json\"\n ],\n \"manifest_path\": \"distribution-manifest.json\",\n \"package_ceiling\": {\n \"max_bytes\": 1000000,\n \"max_files\": 64\n },\n \"profile\": \"lite\",\n \"profile_definition_sha256\": \"4598e1f7bba667ef928ea2a60a6252ad9348086e9eecab29437db442df2a568e\",\n \"schema_version\": \"1.1\",\n \"source\": {\n \"commit\": \"f552620c278afddcb25d09637a0cfcc1ce48faf4\",\n \"repository\": \"aaron-he-zhu/aaron-marketing-skills\"\n }\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ... Skill: Performance Analyzer Owner: aaron-he-zhu Summary: Use when the user asks to \"analyze influencer campaign performance\", \"compare influencers\", or \"find what content worked\"; produces metric scorecards vs targ... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T14:58:51.029Z | auto - Summary: Introduces compatibility and metadata updates, minor documentation revision, and reorganizes skill manifest file","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1501,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T02:09:35.399Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:34:52.910Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}