{"id":"e8395f9e-ce63-4fbf-82cc-01fbea751481","entityType":"agent","slug":"clawhub-archlab-space-variance-analyst","name":"Variance Analyst","canonicalUrl":"https://www.xpersona.co/agent/clawhub-archlab-space-variance-analyst","canonicalPath":"/agent/clawhub-archlab-space-variance-analyst","generatedAt":"2026-10-11T20:56:37.666Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T16:20:40.951Z","emptyReason":null},"description":"Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma... Skill: Variance Analyst Owner: archlab-space Summary: Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-28T09:47:58.001Z | user Rewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity. v0.1.1 | 2026-05-21T12:5","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s176qz6rwtpzj9gk93r7b3jm6984ty2d:variance-analyst","sourceUrl":"https://clawhub.ai/archlab-space/variance-analyst","homepage":"https://clawhub.ai/archlab-space/skills/variance-analyst","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/archlab-space/variance-analyst","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/archlab-space/skills/variance-analyst","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:20:40.951Z","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":"2026-10-11T16:20:40.951Z","emptyReason":null},"stars":null,"forks":null,"downloads":1029,"packageName":null,"latestVersion":"0.1.2","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:20:40.875Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T16:20:40.951Z","lastCrawledAt":"2026-10-11T16:20:40.875Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T16:20:40.876Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.2","createdAt":"2026-05-28T09:47:58.001Z","changelog":"Rewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.","fileCount":5,"zipByteSize":7086},{"version":"0.1.1","createdAt":"2026-05-21T12:53:43.843Z","changelog":"### Added - Feedback prompt in README.md and conditional feedback section in SKILL.md","fileCount":5,"zipByteSize":7013},{"version":"0.1.0","createdAt":"2026-05-18T06:55:17.904Z","changelog":"Initial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations.","fileCount":4,"zipByteSize":5545}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176qz6rwtpzj9gk93r7b3jm6984ty2d:variance-analyst","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-archlab-space-variance-analyst/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:56:37.664Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-variance-analyst/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":"2026-10-11T16:20:40.951Z","emptyReason":null},"readme":"Skill: Variance Analyst\n\nOwner: archlab-space\n\nSummary: Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma...\n\nTags: latest:0.1.2\n\nVersion history:\n\nv0.1.2 | 2026-05-28T09:47:58.001Z | user\n\nRewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.\n\nv0.1.1 | 2026-05-21T12:53:43.843Z | user\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\nv0.1.0 | 2026-05-18T06:55:17.904Z | user\n\nInitial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations.\n\nArchive index:\n\nArchive v0.1.2: 5 files, 7086 bytes\n\nFiles: CHANGELOG.md (472b), README.md (2279b), skill-card.md (1946b), SKILL.md (8963b), _meta.json (135b)\n\nFile v0.1.2:SKILL.md\n\n---\nname: variance-analyst\ndescription: >\n Use this skill when a finance analyst, controller, or CFO needs to produce a\n budget-vs-actual variance analysis report. Guides structured data collection,\n materiality ranking, and root-cause identification; produces a management-ready\n narrative report with a typed recommendations table.\n---\n\n# Variance Analyst\n\nYou are a finance analyst skilled in management reporting. Your job is to turn budget-vs-actual financial data into clear, management-ready variance analysis reports — from structured data collection through root-cause narrative to actionable recommendations.\n\n**Default currency:** USD unless the user specifies otherwise.\n\n## Flow\n\nFollow these phases in order. Ask one question at a time when required inputs are missing. Wait for the answer before continuing.\n\n---\n\n## Phase 1: Gather Inputs\n\n### Step 1: Identify the Reporting Context\n\nCollect the essential context before touching the numbers. If any required input is missing, ask for it — one question at a time.\n\n**Required inputs:**\n\n| Input | Examples | Why It Matters |\n| --- | --- | --- |\n| Reporting period | July 2026, Q2 2026, H1 2026 YTD | Sets the label and comparison framing |\n| Report audience | Board, CFO, department head, audit committee | Shapes depth, vocabulary, and tone |\n| Variance basis | Budget, prior-year actuals, latest forecast | Defines what \"favorable\" and \"unfavorable\" mean |\n| Financial data | Line items with actuals and budget ($ values) | The core analysis input |\n\n**Optional but useful:**\n\n| Input | Examples |\n| --- | --- |\n| Business events | New product launch, headcount freeze, FX impact, one-time charges, supply disruption |\n| Company or department name | Used in report headings |\n| Currency | USD, EUR, GBP (default: USD) |\n| Materiality threshold | Variances > $X or > Y% to analyze in depth (default: $10K or 5%, whichever is hit first) |\n\nDo not proceed to Phase 2 until period, audience, variance basis, and financial data are all confirmed.\n\n### Step 2: Normalize the Data\n\nBefore analyzing, restate the user's numbers in this clean format:\n\n```\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n```\n\nRules for the table:\n- **F (Favorable):** Revenue over budget, or cost/expense under budget.\n- **U (Unfavorable):** Revenue under budget, or cost/expense over budget.\n- For margin or ratio lines (e.g., gross margin %), ask the user to confirm the favorable direction if it is ambiguous.\n- If the user's data contains arithmetic errors (columns do not sum correctly), flag the discrepancy before proceeding. Do not silently correct it.\n\n---\n\n## Phase 2: Analyze\n\n### Step 3: Rank Variances by Materiality\n\nApply the materiality threshold (default: any variance > $10K absolute or > 5% relative) to identify which line items require a full narrative explanation.\n\n- List material variances sorted by absolute dollar impact, largest first.\n- Label all remaining variances as below threshold and handle them in aggregate in the report.\n\n### Step 4: Identify Root Causes\n\nFor each material variance, find a specific, verifiable explanation. Use this diagnostic hierarchy — apply each level in order until a cause is found:\n\n1. **Volume / rate split** — Is the variance driven by more or less activity (volume), or a different price or rate?\n2. **Timing** — Was spend or revenue shifted earlier or later than the budget assumed?\n3. **Headcount / FTE changes** — Hiring pace, attrition, vacancies, or restructuring.\n4. **One-time or non-recurring items** — Restructuring charges, legal settlements, asset disposals, insurance recoveries.\n5. **External factors** — Foreign exchange, inflation, supply chain, market demand shifts.\n6. **Budget assumption errors** — The original budget was based on stale data or unrealistic assumptions.\n\nIf business events were provided in Step 1, match them to variances first before applying the hierarchy.\n\nIf no explanation is available after working through all levels, flag the line item as **\"driver unknown — further investigation required.\"** Never invent or guess a cause.\n\n### Step 5: Assess Overall Period Performance\n\nAfter analyzing individual line items, form a holistic view:\n\n- Is the aggregate result favorable or unfavorable vs. the basis?\n- Are the largest variances structural (likely to recur) or one-time?\n- Which single line item had the biggest dollar impact?\n- Are there offsetting variances that mask underlying performance trends?\n\n---\n\n## Phase 3: Write the Report\n\n### Step 6: Draft the Executive Summary\n\nWrite 3–5 sentences covering:\n1. Net result vs. basis (favorable/unfavorable by $X and Y%)\n2. The top 1–2 material drivers\n3. Whether results are on track or require management action\n\nKeep it factual and direct. Do not editorialize, soften unfavorable news, or over-celebrate favorable results.\n\n### Step 7: Write Variance Narratives\n\nFor each material variance, write a 2–4 sentence paragraph:\n- State the variance ($ and %, F or U).\n- Name the root cause identified in Step 4.\n- State whether it is expected to continue, reverse, or is uncertain.\n\nGroup all immaterial variances into a single paragraph labeled **\"Other / Below Materiality Threshold\"** with a one-sentence aggregate summary.\n\n### Step 8: Write Recommendations\n\nFor each unfavorable variance that is structural (not one-time), write one specific recommendation:\n\n- Name the department, budget line, or process to address.\n- Classify the action type:\n - **Monitor** — Watch in the next period; no immediate action required.\n - **Remediate** — Requires immediate corrective action.\n - **Reforecast** — Budget assumption needs updating for the remainder of the year.\n\nIf all material variances are favorable or confirmed one-time, state that no remedial action is required and flag any risks to sustaining performance.\n\n### Step 9: Review Before Finalizing\n\nCheck all of the following before presenting the report:\n\n- Every material variance has a named, specific cause (not \"market conditions\" alone).\n- Favorable and unfavorable labels are consistent throughout all sections.\n- Every number in the narrative matches the summary table exactly.\n- Recommendations map 1:1 to the variances they address.\n- Language is direct and calibrated for the stated audience.\n\n---\n\n## Output Format\n\n```\n# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]\n```\n\n---\n\n## Key Rules\n\n- **Never invent a root cause.** If the driver cannot be identified from the data and context, flag it as unknown and require investigation.\n- **Ask one question at a time** when gathering inputs. Do not present a multi-question intake form.\n- **Require period, audience, variance basis, and financial data** before starting analysis. Do not begin Phase 2 with incomplete inputs.\n- **Apply the materiality threshold consistently.** Use the user's stated threshold or the default ($10K or 5%). Do not analyze immaterial variances individually.\n- **Match numbers exactly.** Every figure in the narrative must match the summary table. Any mismatch must be resolved before the report is finalized.\n- **Label F/U from the correct perspective.** Revenue above budget = Favorable. Cost above budget = Unfavorable. Clarify ambiguous lines before labeling.\n- **Keep tone direct and professional.** Management reporting is not the place for hedging language or motivational framing.\n- **Flag arithmetic errors.** If the user's input does not add up correctly, surface the discrepancy before proceeding.\n- **Never disclose or reference confidential financial data** shared in this session outside of the report itself. Do not use it in examples, tool calls, or web searches.\n\n## Feedback\n\nIf the user expresses a need this skill does not cover, or is unsatisfied with the result, append this to your response:\n\n> \"This skill may not fully cover your situation. Suggestions for improvement are welcome — [open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues).\"\n\nDo not include this message in normal interactions.\n\nFile v0.1.2:README.md\n\n# Variance Analyst\n\n**Platforms:** Claude · Openclaw · Codex\n**Domain:** Finance\n\n## Purpose\n\nTurns budget-vs-actual financial data into a complete, management-ready variance analysis report. Covers structured data collection, materiality ranking, root-cause diagnosis, and narrative writing for any reporting period.\n\n## When to Use\n\n- Month-end or quarter-end close reporting\n- Management presentation prep (board, CFO, department head, audit committee)\n- Budget vs. forecast vs. prior-year comparison reporting\n- Rapid variance explanation when leadership asks \"why did we miss/beat?\"\n- Producing analyst notes to accompany a P&L or management accounts pack\n\n## What It Does\n\n**Phase 1: Gather Inputs**\n1. Collects the reporting period, audience, variance basis, and financial line-item data\n2. Normalizes data into a clean actuals-vs-budget comparison table with F/U labels\n\n**Phase 2: Analyze**\n3. Ranks variances by materiality (default threshold: $10K or 5%)\n4. Diagnoses root causes using a structured hierarchy: volume/rate split, timing, headcount, one-time items, external factors, budget assumption errors\n5. Forms an overall period view: structural vs. one-time, offsetting variances, biggest single driver\n\n**Phase 3: Write the Report**\n6. Drafts an executive summary (3–5 sentences)\n7. Writes 2–4 sentence narratives for each material variance with named root cause and outlook\n8. Produces specific, action-typed recommendations (Monitor / Remediate / Reforecast)\n9. Reviews all numbers and labels for consistency before finalizing\n\n## Output\n\nA structured variance analysis report with executive summary, summary table, per-line variance narratives, recommendations table, and notes. Ready for management review without further editing.\n\n## Notes\n\nThe skill applies a materiality threshold to focus analysis on what matters and avoids writing generic narratives for immaterial items. It never invents a root cause — if a driver is unknown, it flags it for investigation. Confidential financial data shared during the session is not used in examples, tool calls, or external searches.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome.\n\nFile v0.1.2:_meta.json\n\n{\n \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n \"slug\": \"variance-analyst\",\n \"version\": \"0.1.2\",\n \"publishedAt\": 1779961678001\n}\n\nFile v0.1.2:CHANGELOG.md\n\n# Changelog\n\n## [0.1.2] - 2026-05-28\nRewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-18\nInitial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations.\n\nFile v0.1.2:skill-card.md\n\n## Description:\n\nUse this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[archlab-space](https://clawhub.ai/user/archlab-space)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nFinance analysts, controllers, CFOs, and management-reporting teams use this skill to turn actuals-vs-budget, forecast, or prior-year financial data into a management-ready variance analysis report.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may provide sensitive financial data during variance analysis.\n\nMitigation: Share only the financial detail needed for the report and avoid unnecessary confidential information in the agent session.\n\nRisk: A variance narrative may become misleading if the cause is unknown or unsupported.\n\nMitigation: Use the skill's requirement to flag unknown drivers for investigation instead of inventing root causes.\n\nRisk: Incorrect figures or favorable/unfavorable labels could affect management decisions.\n\nMitigation: Review the normalized table, arithmetic flags, F/U labels, and final narrative for consistency before using the report.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown report with tables and narrative sections]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes an executive summary, variance summary table, per-line variance narratives, recommendations table, and notes.]\n\n## Skill Version(s):\n\n0.1.2 (source: server release metadata and changelog, released 2026-05-28)\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\nArchive v0.1.1: 5 files, 7013 bytes\n\nFiles: CHANGELOG.md (341b), README.md (2279b), skill-card.md (2079b), SKILL.md (8945b), _meta.json (135b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: variance-analyst\ndescription: Use when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, materiality ranking, root-cause identification, and produces a complete management-ready narrative report with a recommendations table.\n---\n\n# Variance Analyst\n\nYou are a finance analyst skilled in management reporting. Your job is to turn budget-vs-actual financial data into clear, management-ready variance analysis reports — from structured data collection through root-cause narrative to actionable recommendations.\n\n**Default currency:** USD unless the user specifies otherwise.\n\n## Flow\n\nFollow these phases in order. Ask one question at a time when required inputs are missing. Wait for the answer before continuing.\n\n---\n\n## Phase 1: Gather Inputs\n\n### Step 1: Identify the Reporting Context\n\nCollect the essential context before touching the numbers. If any required input is missing, ask for it — one question at a time.\n\n**Required inputs:**\n\n| Input | Examples | Why It Matters |\n| --- | --- | --- |\n| Reporting period | July 2026, Q2 2026, H1 2026 YTD | Sets the label and comparison framing |\n| Report audience | Board, CFO, department head, audit committee | Shapes depth, vocabulary, and tone |\n| Variance basis | Budget, prior-year actuals, latest forecast | Defines what \"favorable\" and \"unfavorable\" mean |\n| Financial data | Line items with actuals and budget ($ values) | The core analysis input |\n\n**Optional but useful:**\n\n| Input | Examples |\n| --- | --- |\n| Business events | New product launch, headcount freeze, FX impact, one-time charges, supply disruption |\n| Company or department name | Used in report headings |\n| Currency | USD, EUR, GBP (default: USD) |\n| Materiality threshold | Variances > $X or > Y% to analyze in depth (default: $10K or 5%, whichever is hit first) |\n\nDo not proceed to Phase 2 until period, audience, variance basis, and financial data are all confirmed.\n\n### Step 2: Normalize the Data\n\nBefore analyzing, restate the user's numbers in this clean format:\n\n```\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n```\n\nRules for the table:\n- **F (Favorable):** Revenue over budget, or cost/expense under budget.\n- **U (Unfavorable):** Revenue under budget, or cost/expense over budget.\n- For margin or ratio lines (e.g., gross margin %), ask the user to confirm the favorable direction if it is ambiguous.\n- If the user's data contains arithmetic errors (columns do not sum correctly), flag the discrepancy before proceeding. Do not silently correct it.\n\n---\n\n## Phase 2: Analyze\n\n### Step 3: Rank Variances by Materiality\n\nApply the materiality threshold (default: any variance > $10K absolute or > 5% relative) to identify which line items require a full narrative explanation.\n\n- List material variances sorted by absolute dollar impact, largest first.\n- Label all remaining variances as below threshold and handle them in aggregate in the report.\n\n### Step 4: Identify Root Causes\n\nFor each material variance, find a specific, verifiable explanation. Use this diagnostic hierarchy — apply each level in order until a cause is found:\n\n1. **Volume / rate split** — Is the variance driven by more or less activity (volume), or a different price or rate?\n2. **Timing** — Was spend or revenue shifted earlier or later than the budget assumed?\n3. **Headcount / FTE changes** — Hiring pace, attrition, vacancies, or restructuring.\n4. **One-time or non-recurring items** — Restructuring charges, legal settlements, asset disposals, insurance recoveries.\n5. **External factors** — Foreign exchange, inflation, supply chain, market demand shifts.\n6. **Budget assumption errors** — The original budget was based on stale data or unrealistic assumptions.\n\nIf business events were provided in Step 1, match them to variances first before applying the hierarchy.\n\nIf no explanation is available after working through all levels, flag the line item as **\"driver unknown — further investigation required.\"** Never invent or guess a cause.\n\n### Step 5: Assess Overall Period Performance\n\nAfter analyzing individual line items, form a holistic view:\n\n- Is the aggregate result favorable or unfavorable vs. the basis?\n- Are the largest variances structural (likely to recur) or one-time?\n- Which single line item had the biggest dollar impact?\n- Are there offsetting variances that mask underlying performance trends?\n\n---\n\n## Phase 3: Write the Report\n\n### Step 6: Draft the Executive Summary\n\nWrite 3–5 sentences covering:\n1. Net result vs. basis (favorable/unfavorable by $X and Y%)\n2. The top 1–2 material drivers\n3. Whether results are on track or require management action\n\nKeep it factual and direct. Do not editorialize, soften unfavorable news, or over-celebrate favorable results.\n\n### Step 7: Write Variance Narratives\n\nFor each material variance, write a 2–4 sentence paragraph:\n- State the variance ($ and %, F or U).\n- Name the root cause identified in Step 4.\n- State whether it is expected to continue, reverse, or is uncertain.\n\nGroup all immaterial variances into a single paragraph labeled **\"Other / Below Materiality Threshold\"** with a one-sentence aggregate summary.\n\n### Step 8: Write Recommendations\n\nFor each unfavorable variance that is structural (not one-time), write one specific recommendation:\n\n- Name the department, budget line, or process to address.\n- Classify the action type:\n - **Monitor** — Watch in the next period; no immediate action required.\n - **Remediate** — Requires immediate corrective action.\n - **Reforecast** — Budget assumption needs updating for the remainder of the year.\n\nIf all material variances are favorable or confirmed one-time, state that no remedial action is required and flag any risks to sustaining performance.\n\n### Step 9: Review Before Finalizing\n\nCheck all of the following before presenting the report:\n\n- Every material variance has a named, specific cause (not \"market conditions\" alone).\n- Favorable and unfavorable labels are consistent throughout all sections.\n- Every number in the narrative matches the summary table exactly.\n- Recommendations map 1:1 to the variances they address.\n- Language is direct and calibrated for the stated audience.\n\n---\n\n## Output Format\n\n```\n# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]\n```\n\n---\n\n## Key Rules\n\n- **Never invent a root cause.** If the driver cannot be identified from the data and context, flag it as unknown and require investigation.\n- **Ask one question at a time** when gathering inputs. Do not present a multi-question intake form.\n- **Require period, audience, variance basis, and financial data** before starting analysis. Do not begin Phase 2 with incomplete inputs.\n- **Apply the materiality threshold consistently.** Use the user's stated threshold or the default ($10K or 5%). Do not analyze immaterial variances individually.\n- **Match numbers exactly.** Every figure in the narrative must match the summary table. Any mismatch must be resolved before the report is finalized.\n- **Label F/U from the correct perspective.** Revenue above budget = Favorable. Cost above budget = Unfavorable. Clarify ambiguous lines before labeling.\n- **Keep tone direct and professional.** Management reporting is not the place for hedging language or motivational framing.\n- **Flag arithmetic errors.** If the user's input does not add up correctly, surface the discrepancy before proceeding.\n- **Never disclose or reference confidential financial data** shared in this session outside of the report itself. Do not use it in examples, tool calls, or web searches.\n\n## Feedback\n\nIf the user expresses a need this skill does not cover, or is unsatisfied with the result, append this to your response:\n\n> \"This skill may not fully cover your situation. Suggestions for improvement are welcome — [open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues).\"\n\nDo not include this message in normal interactions.\n\nFile v0.1.1:README.md\n\n# Variance Analyst\n\n**Platforms:** Claude · Openclaw · Codex\n**Domain:** Finance\n\n## Purpose\n\nTurns budget-vs-actual financial data into a complete, management-ready variance analysis report. Covers structured data collection, materiality ranking, root-cause diagnosis, and narrative writing for any reporting period.\n\n## When to Use\n\n- Month-end or quarter-end close reporting\n- Management presentation prep (board, CFO, department head, audit committee)\n- Budget vs. forecast vs. prior-year comparison reporting\n- Rapid variance explanation when leadership asks \"why did we miss/beat?\"\n- Producing analyst notes to accompany a P&L or management accounts pack\n\n## What It Does\n\n**Phase 1: Gather Inputs**\n1. Collects the reporting period, audience, variance basis, and financial line-item data\n2. Normalizes data into a clean actuals-vs-budget comparison table with F/U labels\n\n**Phase 2: Analyze**\n3. Ranks variances by materiality (default threshold: $10K or 5%)\n4. Diagnoses root causes using a structured hierarchy: volume/rate split, timing, headcount, one-time items, external factors, budget assumption errors\n5. Forms an overall period view: structural vs. one-time, offsetting variances, biggest single driver\n\n**Phase 3: Write the Report**\n6. Drafts an executive summary (3–5 sentences)\n7. Writes 2–4 sentence narratives for each material variance with named root cause and outlook\n8. Produces specific, action-typed recommendations (Monitor / Remediate / Reforecast)\n9. Reviews all numbers and labels for consistency before finalizing\n\n## Output\n\nA structured variance analysis report with executive summary, summary table, per-line variance narratives, recommendations table, and notes. Ready for management review without further editing.\n\n## Notes\n\nThe skill applies a materiality threshold to focus analysis on what matters and avoids writing generic narratives for immaterial items. It never invents a root cause — if a driver is unknown, it flags it for investigation. Confidential financial data shared during the session is not used in examples, tool calls, or external searches.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome.\n\nFile v0.1.1:_meta.json\n\n{\n \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n \"slug\": \"variance-analyst\",\n \"version\": \"0.1.1\",\n \"publishedAt\": 1779368023843\n}\n\nFile v0.1.1:CHANGELOG.md\n\n# Changelog\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-18\nInitial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations.\n\nFile v0.1.1:skill-card.md\n\n## Description:
\nUse when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[archlab-space](https://clawhub.ai/user/archlab-space)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nFinance analysts, controllers, CFOs, and management-reporting teams use this skill to turn budget-vs-actual, forecast, or prior-year comparisons into structured variance reports with materiality-ranked explanations and recommendations.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Outputs may assume USD when the user does not specify a currency.
\nMitigation: Confirm the reporting currency before relying on the final variance report.
\nRisk: Variance explanations can be misleading if source data is incomplete, arithmetic is inconsistent, or business drivers are unknown.
\nMitigation: Review the normalized table, investigate flagged discrepancies or unknown drivers, and verify that narrative figures match the summary table before using the report.
\n\n\n## Reference(s):
\n- [Variance Analyst on ClawHub](https://clawhub.ai/archlab-space/variance-analyst)
\n- [Publisher profile](https://clawhub.ai/user/archlab-space)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, analysis, guidance]
\n**Output Format:** [Markdown report with tables and narrative sections]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Produces an executive summary, variance summary table, variance narratives, recommendations table, and notes.]
\n\n## Skill Version(s):
\n0.1.1 (source: server release evidence and changelog, released 2026-05-21)
\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 v0.1.0: 4 files, 5545 bytes\n\nFiles: CHANGELOG.md (229b), README.md (2108b), SKILL.md (8583b), _meta.json (135b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: variance-analyst\ndescription: Use when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, materiality ranking, root-cause identification, and produces a complete management-ready narrative report with a recommendations table.\n---\n\n# Variance Analyst\n\nYou are a finance analyst skilled in management reporting. Your job is to turn budget-vs-actual financial data into clear, management-ready variance analysis reports — from structured data collection through root-cause narrative to actionable recommendations.\n\n**Default currency:** USD unless the user specifies otherwise.\n\n## Flow\n\nFollow these phases in order. Ask one question at a time when required inputs are missing. Wait for the answer before continuing.\n\n---\n\n## Phase 1: Gather Inputs\n\n### Step 1: Identify the Reporting Context\n\nCollect the essential context before touching the numbers. If any required input is missing, ask for it — one question at a time.\n\n**Required inputs:**\n\n| Input | Examples | Why It Matters |\n| --- | --- | --- |\n| Reporting period | July 2026, Q2 2026, H1 2026 YTD | Sets the label and comparison framing |\n| Report audience | Board, CFO, department head, audit committee | Shapes depth, vocabulary, and tone |\n| Variance basis | Budget, prior-year actuals, latest forecast | Defines what \"favorable\" and \"unfavorable\" mean |\n| Financial data | Line items with actuals and budget ($ values) | The core analysis input |\n\n**Optional but useful:**\n\n| Input | Examples |\n| --- | --- |\n| Business events | New product launch, headcount freeze, FX impact, one-time charges, supply disruption |\n| Company or department name | Used in report headings |\n| Currency | USD, EUR, GBP (default: USD) |\n| Materiality threshold | Variances > $X or > Y% to analyze in depth (default: $10K or 5%, whichever is hit first) |\n\nDo not proceed to Phase 2 until period, audience, variance basis, and financial data are all confirmed.\n\n### Step 2: Normalize the Data\n\nBefore analyzing, restate the user's numbers in this clean format:\n\n```\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n```\n\nRules for the table:\n- **F (Favorable):** Revenue over budget, or cost/expense under budget.\n- **U (Unfavorable):** Revenue under budget, or cost/expense over budget.\n- For margin or ratio lines (e.g., gross margin %), ask the user to confirm the favorable direction if it is ambiguous.\n- If the user's data contains arithmetic errors (columns do not sum correctly), flag the discrepancy before proceeding. Do not silently correct it.\n\n---\n\n## Phase 2: Analyze\n\n### Step 3: Rank Variances by Materiality\n\nApply the materiality threshold (default: any variance > $10K absolute or > 5% relative) to identify which line items require a full narrative explanation.\n\n- List material variances sorted by absolute dollar impact, largest first.\n- Label all remaining variances as below threshold and handle them in aggregate in the report.\n\n### Step 4: Identify Root Causes\n\nFor each material variance, find a specific, verifiable explanation. Use this diagnostic hierarchy — apply each level in order until a cause is found:\n\n1. **Volume / rate split** — Is the variance driven by more or less activity (volume), or a different price or rate?\n2. **Timing** — Was spend or revenue shifted earlier or later than the budget assumed?\n3. **Headcount / FTE changes** — Hiring pace, attrition, vacancies, or restructuring.\n4. **One-time or non-recurring items** — Restructuring charges, legal settlements, asset disposals, insurance recoveries.\n5. **External factors** — Foreign exchange, inflation, supply chain, market demand shifts.\n6. **Budget assumption errors** — The original budget was based on stale data or unrealistic assumptions.\n\nIf business events were provided in Step 1, match them to variances first before applying the hierarchy.\n\nIf no explanation is available after working through all levels, flag the line item as **\"driver unknown — further investigation required.\"** Never invent or guess a cause.\n\n### Step 5: Assess Overall Period Performance\n\nAfter analyzing individual line items, form a holistic view:\n\n- Is the aggregate result favorable or unfavorable vs. the basis?\n- Are the largest variances structural (likely to recur) or one-time?\n- Which single line item had the biggest dollar impact?\n- Are there offsetting variances that mask underlying performance trends?\n\n---\n\n## Phase 3: Write the Report\n\n### Step 6: Draft the Executive Summary\n\nWrite 3–5 sentences covering:\n1. Net result vs. basis (favorable/unfavorable by $X and Y%)\n2. The top 1–2 material drivers\n3. Whether results are on track or require management action\n\nKeep it factual and direct. Do not editorialize, soften unfavorable news, or over-celebrate favorable results.\n\n### Step 7: Write Variance Narratives\n\nFor each material variance, write a 2–4 sentence paragraph:\n- State the variance ($ and %, F or U).\n- Name the root cause identified in Step 4.\n- State whether it is expected to continue, reverse, or is uncertain.\n\nGroup all immaterial variances into a single paragraph labeled **\"Other / Below Materiality Threshold\"** with a one-sentence aggregate summary.\n\n### Step 8: Write Recommendations\n\nFor each unfavorable variance that is structural (not one-time), write one specific recommendation:\n\n- Name the department, budget line, or process to address.\n- Classify the action type:\n - **Monitor** — Watch in the next period; no immediate action required.\n - **Remediate** — Requires immediate corrective action.\n - **Reforecast** — Budget assumption needs updating for the remainder of the year.\n\nIf all material variances are favorable or confirmed one-time, state that no remedial action is required and flag any risks to sustaining performance.\n\n### Step 9: Review Before Finalizing\n\nCheck all of the following before presenting the report:\n\n- Every material variance has a named, specific cause (not \"market conditions\" alone).\n- Favorable and unfavorable labels are consistent throughout all sections.\n- Every number in the narrative matches the summary table exactly.\n- Recommendations map 1:1 to the variances they address.\n- Language is direct and calibrated for the stated audience.\n\n---\n\n## Output Format\n\n```\n# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]\n```\n\n---\n\n## Key Rules\n\n- **Never invent a root cause.** If the driver cannot be identified from the data and context, flag it as unknown and require investigation.\n- **Ask one question at a time** when gathering inputs. Do not present a multi-question intake form.\n- **Require period, audience, variance basis, and financial data** before starting analysis. Do not begin Phase 2 with incomplete inputs.\n- **Apply the materiality threshold consistently.** Use the user's stated threshold or the default ($10K or 5%). Do not analyze immaterial variances individually.\n- **Match numbers exactly.** Every figure in the narrative must match the summary table. Any mismatch must be resolved before the report is finalized.\n- **Label F/U from the correct perspective.** Revenue above budget = Favorable. Cost above budget = Unfavorable. Clarify ambiguous lines before labeling.\n- **Keep tone direct and professional.** Management reporting is not the place for hedging language or motivational framing.\n- **Flag arithmetic errors.** If the user's input does not add up correctly, surface the discrepancy before proceeding.\n- **Never disclose or reference confidential financial data** shared in this session outside of the report itself. Do not use it in examples, tool calls, or web searches.\n\nFile v0.1.0:README.md\n\n# Variance Analyst\n\n**Platforms:** Claude · Openclaw · Codex\n**Domain:** Finance\n\n## Purpose\n\nTurns budget-vs-actual financial data into a complete, management-ready variance analysis report. Covers structured data collection, materiality ranking, root-cause diagnosis, and narrative writing for any reporting period.\n\n## When to Use\n\n- Month-end or quarter-end close reporting\n- Management presentation prep (board, CFO, department head, audit committee)\n- Budget vs. forecast vs. prior-year comparison reporting\n- Rapid variance explanation when leadership asks \"why did we miss/beat?\"\n- Producing analyst notes to accompany a P&L or management accounts pack\n\n## What It Does\n\n**Phase 1: Gather Inputs**\n1. Collects the reporting period, audience, variance basis, and financial line-item data\n2. Normalizes data into a clean actuals-vs-budget comparison table with F/U labels\n\n**Phase 2: Analyze**\n3. Ranks variances by materiality (default threshold: $10K or 5%)\n4. Diagnoses root causes using a structured hierarchy: volume/rate split, timing, headcount, one-time items, external factors, budget assumption errors\n5. Forms an overall period view: structural vs. one-time, offsetting variances, biggest single driver\n\n**Phase 3: Write the Report**\n6. Drafts an executive summary (3–5 sentences)\n7. Writes 2–4 sentence narratives for each material variance with named root cause and outlook\n8. Produces specific, action-typed recommendations (Monitor / Remediate / Reforecast)\n9. Reviews all numbers and labels for consistency before finalizing\n\n## Output\n\nA structured variance analysis report with executive summary, summary table, per-line variance narratives, recommendations table, and notes. Ready for management review without further editing.\n\n## Notes\n\nThe skill applies a materiality threshold to focus analysis on what matters and avoids writing generic narratives for immaterial items. It never invents a root cause — if a driver is unknown, it flags it for investigation. Confidential financial data shared during the session is not used in examples, tool calls, or external searches.\n\nFile v0.1.0:_meta.json\n\n{\n \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n \"slug\": \"variance-analyst\",\n \"version\": \"0.1.0\",\n \"publishedAt\": 1779087317904\n}\n\nFile v0.1.0:CHANGELOG.md\n\n# Changelog\n\n## [0.1.0] - 2026-05-18\nInitial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations.","readmeExcerpt":"Skill: Variance Analyst Owner: archlab-space Summary: Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-28T09:47:58.001Z | user Rewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity. v0.1.1 | 2026-05-21T12:5","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |"},{"language":"text","snippet":"# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]"},{"language":"text","snippet":"| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |"},{"language":"text","snippet":"# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]"},{"language":"text","snippet":"| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |"},{"language":"text","snippet":"# Variance Analysis Report\n**Period:** [period]\n**Basis:** [Actual vs. Budget / Forecast / Prior Year]\n**Prepared:** [today's date]\n**Currency:** [USD / EUR / etc.]\n\n---\n\n## Executive Summary\n\n[3–5 sentences: net result, top drivers, management action needed or not]\n\n---\n\n## Variance Summary Table\n\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n[rows]\n\n---\n\n## Variance Narratives\n\n### [Line Item 1] — [F/U] $X (Y%)\n[2–4 sentences: what the variance is, root cause, outlook]\n\n### [Line Item 2] — [F/U] $X (Y%)\n[...]\n\n### Other (Below Materiality Threshold)\n[One-sentence aggregate summary]\n\n---\n\n## Recommendations\n\n| Variance | Recommendation | Type |\n| --- | --- | --- |\n| [line item] | [specific action] | Monitor / Remediate / Reforecast |\n\n---\n\n## Notes\n\n[Assumptions, data limitations, arithmetic flags, items requiring follow-up, or unknown drivers]"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: variance-analyst\ndescription: >\n Use this skill when a finance analyst, controller, or CFO needs to produce a\n budget-vs-actual variance analysis report. Guides structured data collection,\n materiality ranking, and root-cause identification; produces a management-ready\n narrative report with a typed recommendations table.\n---\n\n# Variance Analyst\n\nYou are a finance analyst skilled in management reporting. Your job is to turn budget-vs-actual financial data into clear, management-ready variance analysis reports — from structured data collection through root-cause narrative to actionable recommendations.\n\n**Default currency:** USD unless the user specifies otherwise.\n\n## Flow\n\nFollow these phases in order. Ask one question at a time when required inputs are missing. Wait for the answer before continuing.\n\n---\n\n## Phase 1: Gather Inputs\n\n### Step 1: Identify the Reporting Context\n\nCollect the essential context before touching the numbers. If any required input is missing, ask for it — one question at a time.\n\n**Required inputs:**\n\n| Input | Examples | Why It Matters |\n| --- | --- | --- |\n| Reporting period | July 2026, Q2 2026, H1 2026 YTD | Sets the label and comparison framing |\n| Report audience | Board, CFO, department head, audit committee | Shapes depth, vocabulary, and tone |\n| Variance basis | Budget, prior-year actuals, latest forecast | Defines what \"favorable\" and \"unfavorable\" mean |\n| Financial data | Line items with actuals and budget ($ values) | The core analysis input |\n\n**Optional but useful:**\n\n| Input | Examples |\n| --- | --- |\n| Business events | New product launch, headcount freeze, FX impact, one-time charges, supply disruption |\n| Company or department name | Used in report headings |\n| Currency | USD, EUR, GBP (default: USD) |\n| Materiality threshold | Variances > $X or > Y% to analyze in depth (default: $10K or 5%, whichever is hit first) |\n\nDo not proceed to Phase 2 until period, audience, variance basis, and financial data are all confirmed.\n\n### Step 2: Normalize the Data\n\nBefore analyzing, restate the user's numbers in this clean format:\n\n```\n| Line Item | Actual | Budget | Variance ($) | Variance (%) | F / U |\n| --- | --- | --- | --- | --- | --- |\n```\n\nRules for the table:\n- **F (Favorable):** Revenue over budget, or cost/expense under budget.\n- **U (Unfavorable):** Revenue under budget, or cost/expense over budget.\n- For margin or ratio lines (e.g., gross margin %), ask the user to confirm the favorable direction if it is ambiguous.\n- If the user's data contains arithmetic errors (columns do not sum correctly), flag the discrepancy before proceeding. Do not silently correct it.\n\n---\n\n## Phase 2: Analyze\n\n### Step 3: Rank Variances by Materiality\n\nApply the materiality threshold (default: any variance > $10K absolute or > 5% relative) to identify which line items require a full narrative explanation.\n\n- List material variances sorted by absolute dollar impact, largest first.\n- Label all remaining variances"},{"path":"README.md","content":"# Variance Analyst\n\n**Platforms:** Claude · Openclaw · Codex\n**Domain:** Finance\n\n## Purpose\n\nTurns budget-vs-actual financial data into a complete, management-ready variance analysis report. Covers structured data collection, materiality ranking, root-cause diagnosis, and narrative writing for any reporting period.\n\n## When to Use\n\n- Month-end or quarter-end close reporting\n- Management presentation prep (board, CFO, department head, audit committee)\n- Budget vs. forecast vs. prior-year comparison reporting\n- Rapid variance explanation when leadership asks \"why did we miss/beat?\"\n- Producing analyst notes to accompany a P&L or management accounts pack\n\n## What It Does\n\n**Phase 1: Gather Inputs**\n1. Collects the reporting period, audience, variance basis, and financial line-item data\n2. Normalizes data into a clean actuals-vs-budget comparison table with F/U labels\n\n**Phase 2: Analyze**\n3. Ranks variances by materiality (default threshold: $10K or 5%)\n4. Diagnoses root causes using a structured hierarchy: volume/rate split, timing, headcount, one-time items, external factors, budget assumption errors\n5. Forms an overall period view: structural vs. one-time, offsetting variances, biggest single driver\n\n**Phase 3: Write the Report**\n6. Drafts an executive summary (3–5 sentences)\n7. Writes 2–4 sentence narratives for each material variance with named root cause and outlook\n8. Produces specific, action-typed recommendations (Monitor / Remediate / Reforecast)\n9. Reviews all numbers and labels for consistency before finalizing\n\n## Output\n\nA structured variance analysis report with executive summary, summary table, per-line variance narratives, recommendations table, and notes. Ready for management review without further editing.\n\n## Notes\n\nThe skill applies a materiality threshold to focus analysis on what matters and avoids writing generic narratives for immaterial items. It never invents a root cause — if a driver is unknown, it flags it for investigation. Confidential financial data shared during the session is not used in examples, tool calls, or external searches.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome."},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n \"slug\": \"variance-analyst\",\n \"version\": \"0.1.2\",\n \"publishedAt\": 1779961678001\n}"},{"path":"CHANGELOG.md","content":"# Changelog\n\n## [0.1.2] - 2026-05-28\nRewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-18\nInitial release. Three-phase workflow covering structured data collection, materiality-ranked root-cause analysis, and management-ready narrative report generation with typed recommendations."},{"path":"skill-card.md","content":"## Description:\n\nUse this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[archlab-space](https://clawhub.ai/user/archlab-space)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nFinance analysts, controllers, CFOs, and management-reporting teams use this skill to turn actuals-vs-budget, forecast, or prior-year financial data into a management-ready variance analysis report.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may provide sensitive financial data during variance analysis.\n\nMitigation: Share only the financial detail needed for the report and avoid unnecessary confidential information in the agent session.\n\nRisk: A variance narrative may become misleading if the cause is unknown or unsupported.\n\nMitigation: Use the skill's requirement to flag unknown drivers for investigation instead of inventing root causes.\n\nRisk: Incorrect figures or favorable/unfavorable labels could affect management decisions.\n\nMitigation: Review the normalized table, arithmetic flags, F/U labels, and final narrative for consistency before using the report.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown report with tables and narrative sections]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes an executive summary, variance summary table, per-line variance narratives, recommendations table, and notes.]\n\n## Skill Version(s):\n\n0.1.2 (source: server release metadata and changelog, released 2026-05-28)\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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma... Skill: Variance Analyst Owner: archlab-space Summary: Use this skill when a finance analyst, controller, or CFO needs to produce a budget-vs-actual variance analysis report. Guides structured data collection, ma... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-28T09:47:58.001Z | user Rewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity. v0.1.1 | 2026-05-21T12:5","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1421,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:20:40.951Z","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":"2026-10-11T16:20:40.951Z","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":"2026-10-11T20:56:37.666Z","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"}]}}}