{"id":"a0b076b8-96ce-404f-8fca-2c3eaf0e1b4c","entityType":"agent","slug":"clawhub-terrycarter1985-earnings-call-processor","name":"Earnings Call Processor","canonicalUrl":"https://www.xpersona.co/agent/clawhub-terrycarter1985-earnings-call-processor","canonicalPath":"/agent/clawhub-terrycarter1985-earnings-call-processor","generatedAt":"2026-10-12T04:41:46.411Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T01:32:55.565Z","emptyReason":null},"description":"Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Skill: Earnings Call Processor Owner: terrycarter1985 Summary: Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Tags: latest:3.0.0 Version history: v1.1.0-alpha.1 | 2026-05-12T00:14:48.331Z | user v1.1.0-alpha.1: Local whisper fallback, structured analysis pipeline, Feishu draft integration, stock data via yfinance v3.0.0 | 2","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 961 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s17brwfrqyjhbjgadkvar20h8x8492g8:earnings-call-processor","sourceUrl":"https://clawhub.ai/terrycarter1985/earnings-call-processor","homepage":"https://clawhub.ai/terrycarter1985/skills/earnings-call-processor","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/terrycarter1985/earnings-call-processor","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/terrycarter1985/skills/earnings-call-processor","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Skill: Earnings Ca"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:32:55.565Z","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":"2026-10-12T01:32:55.565Z","emptyReason":null},"stars":null,"forks":null,"downloads":961,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.1.0-alpha.1","tractionLabel":"961 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:32:55.552Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T01:32:55.565Z","lastCrawledAt":"2026-10-12T01:32:55.552Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T01:32:55.552Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0-alpha.1","createdAt":"2026-05-12T00:14:48.331Z","changelog":"v1.1.0-alpha.1: Local whisper fallback, structured analysis pipeline, Feishu draft integration, stock data via yfinance","fileCount":7,"zipByteSize":9575},{"version":"3.0.0","createdAt":"2026-05-12T00:14:20.859Z","changelog":"Complete process_earnings_call.py: Feishu doc generation, Whisper transcription, stock analysis","fileCount":4,"zipByteSize":6133},{"version":"1.3.0","createdAt":"2026-05-11T23:57:34.760Z","changelog":"v1.3.0: Peer comparison, QoQ analysis, retry logic, output-to-file, custom templates, enhanced 9-section analysis framework","fileCount":5,"zipByteSize":9925},{"version":"2.2.0","createdAt":"2026-05-11T23:56:24.802Z","changelog":"v2.2.0: Fixed datetime deprecation, full pipeline validation, improved _meta.json and docs","fileCount":5,"zipByteSize":7566},{"version":"2.1.0","createdAt":"2026-05-07T09:33:55.915Z","changelog":"v2.1.0: Full automated pipeline - process_call.py auto-fetches stock data via yfinance, structured JSON output with analysis instructions, graceful fallbacks, auto-notify after Feishu draft creation, enhanced SKILL.md workflow docs","fileCount":5,"zipByteSize":7455},{"version":"2.0.0","createdAt":"2026-05-06T20:09:28.536Z","changelog":"v2.0.0: end-to-end pipeline script, auto-notify, investment takeaways, improved analysis framework","fileCount":5,"zipByteSize":6010},{"version":"1.0.0","createdAt":"2026-05-06T20:05:09.226Z","changelog":"Initial release: audio transcription, structured analysis framework, Feishu draft output","fileCount":5,"zipByteSize":5556},{"version":"1.2.1","createdAt":"2026-05-06T19:57:00.279Z","changelog":"v1.2.1 — Complete Feishu document generation: fixed incomplete build_feishu_document(), added Whisper CLI/Python fallback, stock analysis metrics (MA, Bollinger, volatility, volume), Key Takeaways derivation, draft/publish split, and --skip-transcribe for testing.","fileCount":4,"zipByteSize":6409}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17brwfrqyjhbjgadkvar20h8x8492g8:earnings-call-processor","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-terrycarter1985-earnings-call-processor/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T04:41:46.409Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-terrycarter1985-earnings-call-processor/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":"2026-10-12T01:32:55.565Z","emptyReason":null},"readme":"Skill: Earnings Call Processor\n\nOwner: terrycarter1985\n\nSummary: Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results.\n\nTags: latest:3.0.0\n\nVersion history:\n\nv1.1.0-alpha.1 | 2026-05-12T00:14:48.331Z | user\n\nv1.1.0-alpha.1: Local whisper fallback, structured analysis pipeline, Feishu draft integration, stock data via yfinance\n\nv3.0.0 | 2026-05-12T00:14:20.859Z | user\n\nComplete process_earnings_call.py: Feishu doc generation, Whisper transcription, stock analysis\n\nv1.3.0 | 2026-05-11T23:57:34.760Z | user\n\nv1.3.0: Peer comparison, QoQ analysis, retry logic, output-to-file, custom templates, enhanced 9-section analysis framework\n\nv2.2.0 | 2026-05-11T23:56:24.802Z | user\n\nv2.2.0: Fixed datetime deprecation, full pipeline validation, improved _meta.json and docs\n\nv2.1.0 | 2026-05-07T09:33:55.915Z | user\n\nv2.1.0: Full automated pipeline - process_call.py auto-fetches stock data via yfinance, structured JSON output with analysis instructions, graceful fallbacks, auto-notify after Feishu draft creation, enhanced SKILL.md workflow docs\n\nv2.0.0 | 2026-05-06T20:09:28.536Z | user\n\nv2.0.0: end-to-end pipeline script, auto-notify, investment takeaways, improved analysis framework\n\nv1.0.0 | 2026-05-06T20:05:09.226Z | user\n\nInitial release: audio transcription, structured analysis framework, Feishu draft output\n\nv1.2.1 | 2026-05-06T19:57:00.279Z | user\n\nv1.2.1 — Complete Feishu document generation: fixed incomplete build_feishu_document(), added Whisper CLI/Python fallback, stock analysis metrics (MA, Bollinger, volatility, volume), Key Takeaways derivation, draft/publish split, and --skip-transcribe for testing.\n\nv1.1.1 | 2026-05-06T19:54:39.988Z | user\n\nComplete Feishu document generation with Whisper transcription and financial metrics structuring\n\nv1.2.0 | 2026-05-06T19:46:18.433Z | user\n\nv1.2.0: Full automated workflow - process_call.sh one-command runner, OpenAI Whisper API transcription, standalone stock data fetcher, enhanced analysis assembly with speaker extraction & Q&A segmentation, richer financial fields, SKILL.md as agent execution guide.\n\nv1.1.0 | 2026-05-04T04:28:24.140Z | user\n\nv1.1.0: Automated earnings call workflow - audio transcription, financial data fetch, structured analysis, Feishu draft publishing\n\nArchive index:\n\nArchive v1.1.0-alpha.1: 7 files, 9575 bytes\n\nFiles: references/output_format.md (1145b), scripts/create_feishu_draft.py (2149b), scripts/fetch_stock.py (2733b), scripts/process_earnings_call.py (7900b), scripts/transcribe.py (3628b), SKILL.md (3854b), _meta.json (150b)\n\nFile v1.1.0-alpha.1:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call processing workflow. Transcribe earnings call audio (OpenAI Whisper API or local whisper), fetch stock/financial data, generate structured analysis, and publish as Feishu draft. Use when processing earnings call recordings, quarterly earnings audio, investor call transcripts, or when asked to analyze an earnings call. Triggers on phrases like \"process earnings call\", \"analyze this earnings call\", \"transcribe earnings call\", \"财报电话会\", \"处理财报\", \"earnings call analysis\".\n---\n\n# Earnings Call Processor\n\nEnd-to-end pipeline: audio → transcript + stock data → structured analysis → Feishu draft.\n\n## Prerequisites\n\n- **OpenAI API key** (for Whisper API transcription) — set `OPENAI_API_KEY`; or use `--local` for offline transcription\n- **openai-whisper** — `pip install openai-whisper` (required for `--local` mode; auto-fallback if API unavailable)\n- **yfinance** — `pip install yfinance`\n- **ffmpeg** — required by whisper for audio processing\n- **Feishu** (optional, for draft creation) — requires feishu-doc skill configured\n\n## Quick Start\n\n```bash\n# Full pipeline: transcribe + stock data + analysis + Feishu draft\npython3 scripts/process_earnings_call.py ./call.wav AAPL\n\n# Use local whisper (no API key needed)\npython3 scripts/process_earnings_call.py ./call.wav AAPL --local\n\n# Skip Feishu (local output only)\npython3 scripts/process_earnings_call.py ./call.wav MSFT --no-feishu\n\n# Custom output dir, language, and local model size\npython3 scripts/process_earnings_call.py ./call.mp3 TSLA --output-dir ./results --language en --local --model small\n```\n\n## Pipeline Steps\n\n1. **Transcribe** (`scripts/transcribe.py`) — Sends audio to OpenAI Whisper API (or local whisper with `--local`), returns transcript + segments\n2. **Fetch Stock** (`scripts/fetch_stock.py`) — Pulls price history, company info, financials via yfinance\n3. **Analyze** (`scripts/process_earnings_call.py` → `build_analysis()`) — Combines transcript + stock data into structured markdown\n4. **Publish** (`scripts/create_feishu_draft.py`) — Creates Feishu document with the analysis\n\n## Individual Scripts\n\n### Transcribe only\n\n```bash\n# API mode (requires OPENAI_API_KEY)\npython3 scripts/transcribe.py ./call.wav --output transcript.json\n\n# Local mode (no API key needed)\npython3 scripts/transcribe.py ./call.wav --local --model base --output transcript.json\n```\n\n### Stock data only\n\n```bash\npython3 scripts/fetch_stock.py AAPL --period 3mo --output stock.json\n```\n\n### Feishu draft from existing content\n\n```bash\npython3 scripts/create_feishu_draft.py --title \"AAPL Q4 Analysis\" --content-file analysis.md\n```\n\n## Output\n\nAll outputs go to `--output-dir` (default: `./output`):\n\n| File | Description |\n|------|-------------|\n| `transcript.json` | Full transcript with segments and timestamps |\n| `stock_data.json` | Price history, company info, financials |\n| `analysis.md` | Structured analysis document (also sent to Feishu) |\n\n## Agent Workflow\n\nWhen invoked by an agent:\n\n1. Run `process_earnings_call.py` with audio path and ticker\n2. Read the generated `analysis.md`\n3. Use LLM reasoning to fill in \"Key Themes & Sentiment\" section:\n   - Analyze full transcript for management tone\n   - Extract forward guidance statements\n   - Identify risk factors\n   - Note any changes vs. prior quarter language\n4. Update the Feishu draft with enriched analysis (use `feishu-doc` skill's `append` or `replace`)\n\nSee [references/output_format.md](references/output_format.md) for the document structure specification.\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `OPENAI_API_KEY` | For API mode | Whisper API transcription; not needed with `--local` |\n| `OPENAI_BASE_URL` | No | Custom OpenAI API endpoint |\n\nFile v1.1.0-alpha.1:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.1.0-alpha.1\",\n  \"publishedAt\": 1778544888331\n}\n\nFile v1.1.0-alpha.1:references/output_format.md\n\n# Earnings Call Output Format\n\n## Document Structure\n\nThe Feishu draft follows this structure:\n\n1. **Header** — Company name, ticker, generation timestamp, call duration\n2. **Quick Metrics** — Current price, market cap, P/E, EPS, growth rates, price trend\n3. **Transcript Summary** — First 500 chars of transcript as preview; full transcript in raw JSON\n4. **Key Themes & Sentiment** — Template for analyst/LLM to fill: tone, key topics, guidance, risks\n5. **Financial Context** — Table: sector, industry, 52-week range, forward P/E\n6. **Price Action** — Recent 10 trading days table\n7. **Action Items** — Checklist for follow-up analysis\n\n## LLM Post-Processing (Optional)\n\nAfter generating the draft, an LLM can enrich \"Key Themes & Sentiment\" by:\n- Analyzing the full transcript for management tone (bullish/bearish/neutral)\n- Extracting specific forward guidance statements\n- Identifying risk factors mentioned\n- Comparing language vs. previous quarter's call\n\nThe `process_earnings_call.py` script produces the structural scaffold. The agent invoking it should follow up with LLM-based analysis to fill the template sections.\n\nArchive v3.0.0: 4 files, 6133 bytes\n\nFiles: _meta.json (142b), skill-card.md (1853b), SKILL.md (1490b), src/process_earnings_call.py (11126b)\n\nFile v3.0.0:SKILL.md\n\n---\nname: earnings-call-processor\nversion: 3.0.0\ndescription: Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results.\ntags: ['earnings', 'transcription', 'whisper', 'feishu', 'finance']\n---\n\n# Earnings Call Processor\n\nEnd-to-end pipeline: audio → transcript → stock analysis → Feishu document.\n\n## Workflow\n\n1. **Transcribe** — Run Whisper on earnings call audio (WAV/MP3/M4A)\n2. **Analyze** — Load CSV stock history, compute key financial indicators\n3. **Generate** — Build a structured Feishu document with transcript + financials\n4. **Publish** — Create as draft first, then promote to shared doc after review\n\n## Usage\n\n```bash\npython3 src/process_earnings_call.py \\\n  --audio audio_transcripts/earnings_call_sample.wav \\\n  --stock-csv financial_reports/aapl_stock_history.csv \\\n  --symbol AAPL \\\n  --output-dir /tmp/earnings_output\n```\n\n### Feishu document creation\n\nAfter the local output is ready, use the feishu-doc skill to publish:\n\n```bash\npython3 /path/to/feishu-doc/scripts/doc_ctl.py create \"AAPL Earnings Call Summary\" --content \"$(cat /tmp/earnings_output/feishu_content.md)\"\n```\n\n## Requirements\n\n- `whisper` (OpenAI Whisper CLI)\n- `pandas`\n- Python 3.10+\n\n## Output\n\n- `{output_dir}/transcript.txt` — Raw Whisper transcript\n- `{output_dir}/financial_indicators.json` — Computed indicators\n- `{output_dir}/feishu_content.md` — Structured content ready for Feishu doc\n\nFile v3.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"3.0.0\",\n  \"publishedAt\": 1778544860859\n}\n\nFile v3.0.0:skill-card.md\n\n## Description:\n\nTranscribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[terrycarter1985](https://clawhub.ai/user/terrycarter1985)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and finance teams use this skill to turn earnings-call audio and stock history CSV data into local transcripts, financial indicators, and Feishu-ready Markdown for review and publication.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The default shared temporary output folder can retain or expose full earnings-call transcripts, summaries, and Feishu-ready content, and may be vulnerable to local tampering.\n\nMitigation: Use a private, user-owned output directory, inspect generated Feishu content before publishing, and delete transcripts and summaries when no longer needed.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/terrycarter1985/skills/earnings-call-processor)\n- [ClawHub publisher profile](https://clawhub.ai/user/terrycarter1985)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, json, shell commands]\n\n**Output Format:** [Local text transcript, JSON indicators, and Feishu-ready Markdown files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Writes transcript.txt, financial_indicators.json, and feishu_content.md under the selected output directory.]\n\n## Skill Version(s):\n\n3.0.0 (source: frontmatter, server release evidence, _meta.json)\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 v1.3.0: 5 files, 9925 bytes\n\nFiles: references/analysis_framework.md (3327b), scripts/process_call.py (10049b), scripts/transcribe.py (3020b), SKILL.md (5517b), _meta.json (142b)\n\nFile v1.3.0:SKILL.md\n\n---\nname: earnings-call-processor\nversion: 1.2.0\ndescription: Automated earnings call processing workflow — transcribe audio, fetch stock & peer data, generate structured analysis with QoQ comparison, and publish to Feishu as draft.\ntags: ['earnings', 'transcript', 'finance', 'feishu', 'workflow', 'peer-comparison']\nmetadata:\n  openclaw:\n    requires:\n      skills: ['finance', 'feishu-doc']\n---\n\n# Earnings Call Processor v1.2.0\n\nFully automated pipeline: audio → transcript → stock data + peer comparison → structured analysis → Feishu draft.\n\n## When to Use\n\n- User provides an earnings call audio file or recording URL\n- User asks to analyze a company's earnings call\n- User mentions \"财报电话会\", \"earnings call\", \"transcript analysis\", \"财报分析\"\n- Scheduled/automated earnings season processing\n\n## Quick Start\n\n```\nUser: \"处理这份AAPL Q1 2025财报电话会 audio.mp3\"\nUser: \"分析这份MSFT Q4 2024财报\" (with transcript file)\n```\n\nAgent executes the full pipeline automatically—no manual step-by-step.\n\n## Automated Workflow\n\n### 1. Run Pipeline Script\n\n```bash\n# From audio\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --audio {path}\n\n# From transcript\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --transcript {path}\n\n# With custom peers\npython3 scripts/process_call.py --ticker AAPL --quarter \"Q1 2025\" --transcript call.txt --peers MSFT GOOGL AMZN\n\n# Save output to file\npython3 scripts/process_call.py --ticker AAPL --quarter \"Q1 2025\" --audio call.mp3 --output earnings/AAPL_Q1_2025.json\n\n# Custom analysis template\npython3 scripts/process_call.py --ticker AAPL --quarter \"Q1 2025\" --transcript call.txt --template references/custom_framework.md\n```\n\nScript outputs JSON with transcript, stock data, peer data, and next-step instructions.\n\nIf `--audio` is given, `scripts/transcribe.py` runs automatically (requires faster-whisper).\nStock data is fetched via yfinance with retry logic (3 retries, exponential backoff).\nPeer comparison data is auto-detected for major tickers or specified via `--peers`.\n\n### 2. Apply Analysis Framework\n\nRead `references/analysis_framework.md` and apply it to the transcript + stock data + peer data from step 1.\n\nGenerate structured markdown with all 9 required sections:\n1. 执行摘要 (beat/miss/meet, headline numbers, market reaction)\n2. 核心财务指标 (revenue, EPS, margins with YoY, QoQ, and vs-consensus)\n3. 管理层基调 (sentiment: 🟢/🟡/🔴 with quoted evidence + tone trajectory)\n4. 战略亮点 (M&A, products, expansion, capital allocation, AI/tech)\n5. Q&A 重点 (top 3-5 analyst questions + responses, new vs recurring themes)\n6. 前瞻指引 (raised/lowered/maintained guidance)\n7. 同行对比 (peer comparison table with valuation metrics)\n8. 股价关联 (after-hours reaction, volume, sector comparison, options)\n9. 投资要点 (bull/bear/risk/watch + vs last quarter changes)\n\n### 3. Create Feishu Draft\n\n```bash\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"财报分析: {COMPANY} {QUARTER}\" --content \"<markdown>\"\n```\n\nTitle format: `财报分析: {公司名} {YEAR} Q{N}`\n\n### 4. Notify User\n\nAfter draft creation, send the user a brief summary with the Feishu doc link:\n- Company + quarter\n- Beat/miss verdict\n- Key metric highlights (including QoQ)\n- Sentiment classification\n- Peer comparison highlight\n- Doc link\n\n## Transcription (Audio Input)\n\n```bash\npython3 scripts/transcribe.py <audio_file> [--model base] [--language en] [--output out.txt]\n```\n\nUses faster-whisper (CPU, int8). Models: tiny/base/small/medium/large.\n\n## Stock Data Enrichment\n\nThe pipeline script auto-fetches via yfinance (with retry):\n- Current price, previous close, market cap, PE ratios, 52-week range\n- 5-day price history (earnings window)\n- Company name, sector, industry\n- **Quarterly financials** (for QoQ comparison)\n\nFallback: use `finance` skill tools (`yfinance_get_stock_price`, `yfinance_get_historical_data`, `yfinance_get_stock_info`) if inline yfinance fails.\n\n## Peer Comparison\n\nAuto-detected peers for major tickers (see `DEFAULT_PEERS` in `scripts/process_call.py`).\n\nOverride with `--peers` flag or disable with `--no-peers`.\n\n## Configuration\n\n| Env Var | Default | Description |\n|---------|---------|-------------|\n| `WHISPER_MODEL` | `base` | faster-whisper model size |\n| `WHISPER_DEVICE` | `cpu` | cpu or cuda |\n\n## Output Structure\n\n```\nworkspace/earnings/\n├── transcripts/\n│   └── AAPL_2025Q1.txt\n├── data/\n│   └── AAPL_2025Q1.json\n└── reports/\n    └── AAPL_2025Q1.md\n```\n\n## Changelog\n\n### v1.2.0\n- Peer comparison: auto-detect or specify peer tickers for relative valuation\n- QoQ analysis: quarterly financials fetched for sequential comparison\n- Retry logic: 3 retries with exponential backoff for stock data fetches\n- Output to file: `--output` flag saves JSON pipeline output\n- Custom templates: `--template` flag for alternative analysis frameworks\n- Enhanced analysis framework: 9 sections (added peer comparison, QoQ, tone trajectory, AI/tech highlights)\n- New vs recurring Q&A themes tracking\n\n### v1.1.0\n- End-to-end pipeline: `process_call.py` now fetches stock data automatically\n- Auto-notify user after Feishu draft creation\n- Structured JSON output with analysis instructions\n- Graceful fallback when yfinance unavailable\n- Version field in frontmatter\n- Improved analysis framework with investment takeaways\n\n### v1.0.0\n- Initial release: basic transcript analysis\n\nFile v1.3.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.3.0\",\n  \"publishedAt\": 1778543854760\n}\n\nFile v1.3.0:references/analysis_framework.md\n\n# Earnings Call Analysis Framework v1.2.0\n\nUse this template to structure analysis output.\n\n## Document Title Format\n\n`财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n## Sections\n\n### 一、执行摘要 (Executive Summary)\n\n3-5 sentences covering:\n- Overall earnings result (beat/miss/meet)\n- Key headline number (revenue, EPS)\n- Market reaction (up/down/flat post-earnings)\n- One-line forward outlook\n\n### 二、核心财务指标 (Key Financial Metrics)\n\n| 指标 | 本期 | 上期 | 同比变化 | 环比变化 | 一致预期 | vs预期 |\n|------|------|------|----------|----------|----------|--------|\n| 营收 | | | | | | |\n| EPS | | | | | | |\n| 毛利率 | | | | | | |\n| 运营利润率 | | | | | | |\n| 自由现金流 | | | | | | |\n\nFor Feishu: use bullet list format (tables unsupported in some channels):\n- **营收**: $X (同比 +Y%, 环比 +Z%, 预期 $W, beat/miss by V%)\n- **EPS**: $X (同比 +Y%, 环比 +Z%)\n\n**环比分析** (QoQ Analysis): Compare with immediately preceding quarter. Highlight seasonal patterns and one-time items that affect QoQ comparability.\n\n### 三、管理层基调分析 (Management Sentiment)\n\nCategorize as: 🟢 信心充足 / 🟡 谨慎乐观 / 🔴 偏谨慎\n\nEvidence from transcript:\n- CEO key phrases → quote 2-3 notable statements\n- CFO tone on margin/expense → quote 1-2 statements\n- Language shifts vs prior call (new cautious phrases, removed optimistic phrases)\n- **Tone trajectory**: Is sentiment improving, stable, or deteriorating vs last quarter?\n\n### 四、战略亮点 (Strategic Highlights)\n\n- **M&A / Partnerships**: Any announced or completed deals\n- **Product Launches**: New products, features, or services\n- **Market Expansion**: Geographic or segment expansion\n- **Cost Initiatives**: Restructuring, efficiency programs\n- **Capital Allocation**: Buyback, dividend changes\n- **AI/Technology**: AI-related investments, capabilities, or mentions (highlight if significant)\n\n### 五、Q&A 重点 (Q&A Highlights)\n\nTop 3-5 analyst questions with management response summary:\n1. **[Analyst Firm]**: [Question topic] → Management: [Key response point]\n2. ...\n\nNote which questions were asked for the first time vs recurring themes.\n\n### 六、前瞻指引 (Forward Guidance)\n\n| 指标 | 公司指引 | 一致预期 | 含义 |\n|------|----------|----------|------|\n| 下季营收 | | | 上调/下调/维持 |\n| 全年EPS | | | 上调/下调/维持 |\n| CapEx | | | |\n\nAlso note: raised guidance, lowered guidance, or maintained.\n\n### 七、同行对比 (Peer Comparison)\n\n| 指标 | {TICKER} | {PEER1} | {PEER2} | {PEER3} |\n|------|----------|---------|---------|---------|\n| 股价 | | | | |\n| 市值 | | | | |\n| P/E (TTM) | | | | |\n| P/E (Fwd) | | | | |\n| 52周高点距离 | | | | |\n\nCommentary on relative valuation and positioning vs peers.\n\n### 八、股价数据关联 (Stock Data Correlation)\n\n- **盘后/盘前反应**: +X% / -X%\n- **成交量**: vs 20日平均\n- **行业对比**: 同期同行业公司表现\n- **技术位**: 关键支撑/阻力\n- **期权市场**: 如果有相关数据，隐含波动率变化\n\n### 九、投资要点 (Investment Takeaways)\n\n3-5 bullet takeaways:\n- 📈 Bull case: ...\n- 📉 Bear case: ...\n- ⚠️ Risk factors: ...\n- 🔄 vs 上季变化: What changed this quarter vs last\n- 🎯 Key watch items for next quarter: ...\n\nArchive v2.2.0: 5 files, 7566 bytes\n\nFiles: _meta.json (142b), references/analysis_framework.md (2413b), scripts/process_call.py (6883b), scripts/transcribe.py (2102b), SKILL.md (4009b)\n\nFile v2.2.0:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call transcript processing and analysis. Use when the user provides an earnings call audio file or transcript and wants structured analysis including key metrics, management sentiment, forward guidance, and stock data correlation. Triggers on phrases like \"process earnings call\", \"analyze earnings call\", \"财报电话会\", \"财报分析\", \"处理财报\", or when an audio/transcript file related to quarterly earnings is provided. Outputs structured analysis as a Feishu draft document. Fully automated pipeline: audio → transcript → stock data → structured analysis → Feishu draft.\nversion: 2.2.0\n---\n\n# Earnings Call Processor v2.2.0\n\nFully automated pipeline: audio → transcript → stock data → structured analysis → Feishu draft.\n\n## Quick Start\n\nProvide an audio file or transcript with ticker and quarter:\n\n```\nUser: \"处理这份AAPL Q1 2025财报电话会 audio.mp3\"\nUser: \"分析这份MSFT Q4 2024财报\" (with transcript file)\n```\n\nAgent executes the full pipeline automatically—no manual step-by-step.\n\n## Automated Workflow\n\n### 1. Run Pipeline Script\n\n```bash\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --audio {path}\n# or\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --transcript {path}\n```\n\nScript outputs JSON with transcript, stock data, and next-step instructions.\n\nIf `--audio` is given, `scripts/transcribe.py` runs automatically (requires faster-whisper).\nStock data is fetched via yfinance (price, 5d history, company info).\n\n### 2. Apply Analysis Framework\n\nRead `references/analysis_framework.md` and apply it to the transcript + stock data from step 1.\n\nGenerate structured markdown with all 8 required sections:\n1. 执行摘要 (beat/miss/meet, headline numbers, market reaction)\n2. 核心财务指标 (revenue, EPS, margins with YoY and vs-consensus)\n3. 管理层基调 (sentiment: 🟢/🟡/🔴 with quoted evidence)\n4. 战略亮点 (M&A, products, expansion, capital allocation)\n5. Q&A 重点 (top 3-5 analyst questions + responses)\n6. 前瞻指引 (raised/lowered/maintained guidance)\n7. 股价关联 (after-hours reaction, volume, sector comparison)\n8. 投资要点 (bull/bear/risk/watch)\n\n### 3. Create Feishu Draft\n\n```bash\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"财报分析: {COMPANY} {QUARTER}\" --content \"<markdown>\"\n```\n\nTitle format: `财报分析: {公司名} {YEAR} Q{N}`\n\n### 4. Notify User\n\nAfter draft creation, send the user a brief summary with the Feishu doc link:\n- Company + quarter\n- Beat/miss verdict\n- Key metric highlights\n- Sentiment classification\n- Doc link\n\n## Transcription (Audio Input)\n\n```bash\npython3 scripts/transcribe.py <audio_file> [--model base] [--language en] [--output out.txt]\n```\n\nUses faster-whisper (CPU, int8). Models: tiny/base/small/medium/large.\n\n## Stock Data Enrichment\n\nThe pipeline script auto-fetches via yfinance:\n- Current price, previous close, market cap, PE ratios, 52-week range\n- 5-day price history (earnings window)\n- Company name, sector, industry\n\nFallback: use `finance` skill tools (`yfinance_get_stock_price`, `yfinance_get_historical_data`, `yfinance_get_stock_info`) if inline yfinance fails.\n\n## Configuration\n\n| Env Var | Default | Description |\n|---------|---------|-------------|\n| `WHISPER_MODEL` | `base` | faster-whisper model size |\n| `WHISPER_DEVICE` | `cpu` | cpu or cuda |\n\n## v2.2.0 Changelog\n\n- Fixed datetime deprecation warning (utcnow → timezone-aware)\n- Updated _meta.json with version tracking and changelog\n- Full pipeline validation with sample audio\n- Republished with improved documentation\n\n## v1.1.0 Changelog\n\n- End-to-end pipeline: `process_call.py` now fetches stock data automatically\n- Auto-notify user after Feishu draft creation\n- Structured JSON output with analysis instructions\n- Graceful fallback when yfinance unavailable\n- Version field in frontmatter\n- Improved analysis framework with investment takeaways\n\nFile v2.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"2.2.0\",\n  \"publishedAt\": 1778543784802\n}\n\nFile v2.2.0:references/analysis_framework.md\n\n# Earnings Call Analysis Framework\n\nUse this template to structure analysis output.\n\n## Document Title Format\n\n`财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n## Sections\n\n### 一、执行摘要 (Executive Summary)\n\n3-5 sentences covering:\n- Overall earnings result (beat/miss/meet)\n- Key headline number (revenue, EPS)\n- Market reaction (up/down/flat post-earnings)\n- One-line forward outlook\n\n### 二、核心财务指标 (Key Financial Metrics)\n\n| 指标 | 本期 | 上期 | 同比变化 | 一致预期 | vs预期 |\n|------|------|------|----------|----------|--------|\n| 营收 | | | | | |\n| EPS | | | | | |\n| 毛利率 | | | | | |\n| 运营利润率 | | | | | |\n| 自由现金流 | | | | | |\n\nFor Feishu: use bullet list format (tables unsupported in some channels):\n- **营收**: $X (同比 +Y%, 预期 $Z, beat/miss by W%)\n- **EPS**: $X (同比 +Y%, 预期 $Z)\n\n### 三、管理层基调分析 (Management Sentiment)\n\nCategorize as: 🟢 信心充足 / 🟡 谨慎乐观 / 🔴 偏谨慎\n\nEvidence from transcript:\n- CEO key phrases → quote 2-3 notable statements\n- CFO tone on margin/expense → quote 1-2 statements\n- Language shifts vs prior call (new cautious phrases, removed optimistic phrases)\n\n### 四、战略亮点 (Strategic Highlights)\n\n- **M&A / Partnerships**: Any announced or completed deals\n- **Product Launches**: New products, features, or services\n- **Market Expansion**: Geographic or segment expansion\n- **Cost Initiatives**: Restructuring, efficiency programs\n- **Capital Allocation**: Buyback, dividend changes\n\n### 五、Q&A 重点 (Q&A Highlights)\n\nTop 3-5 analyst questions with management response summary:\n1. **[Analyst Firm]**: [Question topic] → Management: [Key response point]\n2. ...\n\n### 六、前瞻指引 (Forward Guidance)\n\n| 指标 | 公司指引 | 一致预期 | 含义 |\n|------|----------|----------|------|\n| 下季营收 | | | 上调/下调/维持 |\n| 全年EPS | | | 上调/下调/维持 |\n| CapEx | | | |\n\nAlso note: raised guidance, lowered guidance, or maintained.\n\n### 七、股价数据关联 (Stock Data Correlation)\n\n- **盘后/盘前反应**: +X% / -X%\n- **成交量**: vs 20日平均\n- **行业对比**: 同期同行业公司表现\n- **技术位**: 关键支撑/阻力\n\n### 八、投资要点 (Investment Takeaways)\n\n3-5 bullet takeaways:\n- 📈 Bull case: ...\n- 📉 Bear case: ...\n- ⚠️ Risk factors: ...\n- 🎯 Key watch items for next quarter: ...\n\nArchive v2.1.0: 5 files, 7455 bytes\n\nFiles: _meta.json (142b), references/analysis_framework.md (2413b), scripts/process_call.py (6872b), scripts/transcribe.py (2102b), SKILL.md (3778b)\n\nFile v2.1.0:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call transcript processing and analysis. Use when the user provides an earnings call audio file or transcript and wants structured analysis including key metrics, management sentiment, forward guidance, and stock data correlation. Triggers on phrases like \"process earnings call\", \"analyze earnings call\", \"财报电话会\", \"财报分析\", \"处理财报\", or when an audio/transcript file related to quarterly earnings is provided. Outputs structured analysis as a Feishu draft document. Fully automated pipeline: audio → transcript → stock data → structured analysis → Feishu draft.\nversion: 1.1.0\n---\n\n# Earnings Call Processor v1.1.0\n\nFully automated pipeline: audio → transcript → stock data → structured analysis → Feishu draft.\n\n## Quick Start\n\nProvide an audio file or transcript with ticker and quarter:\n\n```\nUser: \"处理这份AAPL Q1 2025财报电话会 audio.mp3\"\nUser: \"分析这份MSFT Q4 2024财报\" (with transcript file)\n```\n\nAgent executes the full pipeline automatically—no manual step-by-step.\n\n## Automated Workflow\n\n### 1. Run Pipeline Script\n\n```bash\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --audio {path}\n# or\npython3 scripts/process_call.py --ticker {TICKER} --quarter \"{QUARTER}\" --transcript {path}\n```\n\nScript outputs JSON with transcript, stock data, and next-step instructions.\n\nIf `--audio` is given, `scripts/transcribe.py` runs automatically (requires faster-whisper).\nStock data is fetched via yfinance (price, 5d history, company info).\n\n### 2. Apply Analysis Framework\n\nRead `references/analysis_framework.md` and apply it to the transcript + stock data from step 1.\n\nGenerate structured markdown with all 8 required sections:\n1. 执行摘要 (beat/miss/meet, headline numbers, market reaction)\n2. 核心财务指标 (revenue, EPS, margins with YoY and vs-consensus)\n3. 管理层基调 (sentiment: 🟢/🟡/🔴 with quoted evidence)\n4. 战略亮点 (M&A, products, expansion, capital allocation)\n5. Q&A 重点 (top 3-5 analyst questions + responses)\n6. 前瞻指引 (raised/lowered/maintained guidance)\n7. 股价关联 (after-hours reaction, volume, sector comparison)\n8. 投资要点 (bull/bear/risk/watch)\n\n### 3. Create Feishu Draft\n\n```bash\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"财报分析: {COMPANY} {QUARTER}\" --content \"<markdown>\"\n```\n\nTitle format: `财报分析: {公司名} {YEAR} Q{N}`\n\n### 4. Notify User\n\nAfter draft creation, send the user a brief summary with the Feishu doc link:\n- Company + quarter\n- Beat/miss verdict\n- Key metric highlights\n- Sentiment classification\n- Doc link\n\n## Transcription (Audio Input)\n\n```bash\npython3 scripts/transcribe.py <audio_file> [--model base] [--language en] [--output out.txt]\n```\n\nUses faster-whisper (CPU, int8). Models: tiny/base/small/medium/large.\n\n## Stock Data Enrichment\n\nThe pipeline script auto-fetches via yfinance:\n- Current price, previous close, market cap, PE ratios, 52-week range\n- 5-day price history (earnings window)\n- Company name, sector, industry\n\nFallback: use `finance` skill tools (`yfinance_get_stock_price`, `yfinance_get_historical_data`, `yfinance_get_stock_info`) if inline yfinance fails.\n\n## Configuration\n\n| Env Var | Default | Description |\n|---------|---------|-------------|\n| `WHISPER_MODEL` | `base` | faster-whisper model size |\n| `WHISPER_DEVICE` | `cpu` | cpu or cuda |\n\n## v1.1.0 Changelog\n\n- End-to-end pipeline: `process_call.py` now fetches stock data automatically\n- Auto-notify user after Feishu draft creation\n- Structured JSON output with analysis instructions\n- Graceful fallback when yfinance unavailable\n- Version field in frontmatter\n- Improved analysis framework with investment takeaways\n\nFile v2.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"2.1.0\",\n  \"publishedAt\": 1778146435915\n}\n\nFile v2.1.0:references/analysis_framework.md\n\n# Earnings Call Analysis Framework\n\nUse this template to structure analysis output.\n\n## Document Title Format\n\n`财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n## Sections\n\n### 一、执行摘要 (Executive Summary)\n\n3-5 sentences covering:\n- Overall earnings result (beat/miss/meet)\n- Key headline number (revenue, EPS)\n- Market reaction (up/down/flat post-earnings)\n- One-line forward outlook\n\n### 二、核心财务指标 (Key Financial Metrics)\n\n| 指标 | 本期 | 上期 | 同比变化 | 一致预期 | vs预期 |\n|------|------|------|----------|----------|--------|\n| 营收 | | | | | |\n| EPS | | | | | |\n| 毛利率 | | | | | |\n| 运营利润率 | | | | | |\n| 自由现金流 | | | | | |\n\nFor Feishu: use bullet list format (tables unsupported in some channels):\n- **营收**: $X (同比 +Y%, 预期 $Z, beat/miss by W%)\n- **EPS**: $X (同比 +Y%, 预期 $Z)\n\n### 三、管理层基调分析 (Management Sentiment)\n\nCategorize as: 🟢 信心充足 / 🟡 谨慎乐观 / 🔴 偏谨慎\n\nEvidence from transcript:\n- CEO key phrases → quote 2-3 notable statements\n- CFO tone on margin/expense → quote 1-2 statements\n- Language shifts vs prior call (new cautious phrases, removed optimistic phrases)\n\n### 四、战略亮点 (Strategic Highlights)\n\n- **M&A / Partnerships**: Any announced or completed deals\n- **Product Launches**: New products, features, or services\n- **Market Expansion**: Geographic or segment expansion\n- **Cost Initiatives**: Restructuring, efficiency programs\n- **Capital Allocation**: Buyback, dividend changes\n\n### 五、Q&A 重点 (Q&A Highlights)\n\nTop 3-5 analyst questions with management response summary:\n1. **[Analyst Firm]**: [Question topic] → Management: [Key response point]\n2. ...\n\n### 六、前瞻指引 (Forward Guidance)\n\n| 指标 | 公司指引 | 一致预期 | 含义 |\n|------|----------|----------|------|\n| 下季营收 | | | 上调/下调/维持 |\n| 全年EPS | | | 上调/下调/维持 |\n| CapEx | | | |\n\nAlso note: raised guidance, lowered guidance, or maintained.\n\n### 七、股价数据关联 (Stock Data Correlation)\n\n- **盘后/盘前反应**: +X% / -X%\n- **成交量**: vs 20日平均\n- **行业对比**: 同期同行业公司表现\n- **技术位**: 关键支撑/阻力\n\n### 八、投资要点 (Investment Takeaways)\n\n3-5 bullet takeaways:\n- 📈 Bull case: ...\n- 📉 Bear case: ...\n- ⚠️ Risk factors: ...\n- 🎯 Key watch items for next quarter: ...\n\nArchive v2.0.0: 5 files, 6010 bytes\n\nFiles: references/analysis_framework.md (2413b), scripts/process_call.py (2749b), scripts/transcribe.py (2102b), SKILL.md (3253b), _meta.json (142b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call transcript processing and analysis. Use when the user provides an earnings call audio file or transcript and wants structured analysis including key metrics, management sentiment, forward guidance, and stock data correlation. Triggers on phrases like \"process earnings call\", \"analyze earnings call\", \"财报电话会\", \"财报分析\", or when an audio/transcript file related to quarterly earnings is provided. Outputs structured analysis as a Feishu draft document.\nversion: 1.1.0\n---\n\n# Earnings Call Processor v1.1.0\n\nFully automated pipeline: audio → transcript → analysis + stock data → Feishu draft.\n\n## Quick Start (One Command)\n\n```bash\npython3 scripts/process_call.py --ticker AAPL --quarter \"Q1 2025\" --audio call.mp3\n```\n\nThis outputs structured JSON. The agent then automatically:\n1. Fetches stock data via `finance` skill\n2. Applies analysis framework → structured markdown\n3. Creates Feishu draft via `feishu-doc` skill\n\n## Workflow Details\n\n### Step 1: Input\n\nAccept one of:\n- **Audio file** (mp3/wav/m4a) → transcribe via `scripts/transcribe.py`\n- **Transcript file** (txt/md) → use directly\n- **Ticker + quarter** → fetch from public sources\n\n### Step 2: Transcription (audio only)\n\n```bash\npython3 scripts/transcribe.py <audio_file> [--model base] [--language en] [--output out.txt]\n```\n\nUses faster-whisper (CPU, int8 quantized). Model sizes: tiny/base/small/medium/large.\n\n### Step 3: Stock Data Enrichment\n\nCall these `finance` skill tools:\n- `yfinance_get_stock_price(symbol)` — current price\n- `yfinance_get_historical_data(symbol, period=\"5d\")` — earnings window price action\n- `yfinance_get_stock_info(symbol)` — market cap, PE, sector, industry\n\n### Step 4: Structured Analysis\n\nRead `references/analysis_framework.md` for the full template. Required sections:\n\n1. **执行摘要** — beat/miss/meet, headline numbers, market reaction\n2. **核心财务指标** — revenue, EPS, margins with YoY and vs-consensus\n3. **管理层基调** — sentiment classification with quoted evidence\n4. **战略亮点** — M&A, products, expansion, capital allocation\n5. **Q&A 重点** — top 3-5 analyst questions + management responses\n6. **前瞻指引** — raised/lowered/maintained with details\n7. **股价关联** — after-hours reaction, volume, sector comparison\n8. **投资要点** — bull/bear/risk/watch items\n\n### Step 5: Feishu Draft\n\n```bash\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"财报分析: {COMPANY} {QUARTER}\" --content \"<structured markdown>\"\n```\n\nTitle format: `财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n### Step 6: Auto-Notify (v1.1.0 new)\n\nAfter Feishu draft creation, send a brief summary message to the user channel with doc link.\n\n## Configuration\n\n| Env Var | Default | Description |\n|---------|---------|-------------|\n| `WHISPER_MODEL` | `base` | faster-whisper model size |\n| `WHISPER_DEVICE` | `cpu` | cpu or cuda |\n\n## v1.1.0 Changelog\n\n- Added `scripts/process_call.py` end-to-end pipeline script\n- Added auto-notify after Feishu draft creation\n- Added version field to frontmatter\n- Improved analysis framework with investment takeaways section\n- Added quick start one-command workflow\n\nFile v2.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"2.0.0\",\n  \"publishedAt\": 1778098168536\n}\n\nFile v2.0.0:references/analysis_framework.md\n\n# Earnings Call Analysis Framework\n\nUse this template to structure analysis output.\n\n## Document Title Format\n\n`财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n## Sections\n\n### 一、执行摘要 (Executive Summary)\n\n3-5 sentences covering:\n- Overall earnings result (beat/miss/meet)\n- Key headline number (revenue, EPS)\n- Market reaction (up/down/flat post-earnings)\n- One-line forward outlook\n\n### 二、核心财务指标 (Key Financial Metrics)\n\n| 指标 | 本期 | 上期 | 同比变化 | 一致预期 | vs预期 |\n|------|------|------|----------|----------|--------|\n| 营收 | | | | | |\n| EPS | | | | | |\n| 毛利率 | | | | | |\n| 运营利润率 | | | | | |\n| 自由现金流 | | | | | |\n\nFor Feishu: use bullet list format (tables unsupported in some channels):\n- **营收**: $X (同比 +Y%, 预期 $Z, beat/miss by W%)\n- **EPS**: $X (同比 +Y%, 预期 $Z)\n\n### 三、管理层基调分析 (Management Sentiment)\n\nCategorize as: 🟢 信心充足 / 🟡 谨慎乐观 / 🔴 偏谨慎\n\nEvidence from transcript:\n- CEO key phrases → quote 2-3 notable statements\n- CFO tone on margin/expense → quote 1-2 statements\n- Language shifts vs prior call (new cautious phrases, removed optimistic phrases)\n\n### 四、战略亮点 (Strategic Highlights)\n\n- **M&A / Partnerships**: Any announced or completed deals\n- **Product Launches**: New products, features, or services\n- **Market Expansion**: Geographic or segment expansion\n- **Cost Initiatives**: Restructuring, efficiency programs\n- **Capital Allocation**: Buyback, dividend changes\n\n### 五、Q&A 重点 (Q&A Highlights)\n\nTop 3-5 analyst questions with management response summary:\n1. **[Analyst Firm]**: [Question topic] → Management: [Key response point]\n2. ...\n\n### 六、前瞻指引 (Forward Guidance)\n\n| 指标 | 公司指引 | 一致预期 | 含义 |\n|------|----------|----------|------|\n| 下季营收 | | | 上调/下调/维持 |\n| 全年EPS | | | 上调/下调/维持 |\n| CapEx | | | |\n\nAlso note: raised guidance, lowered guidance, or maintained.\n\n### 七、股价数据关联 (Stock Data Correlation)\n\n- **盘后/盘前反应**: +X% / -X%\n- **成交量**: vs 20日平均\n- **行业对比**: 同期同行业公司表现\n- **技术位**: 关键支撑/阻力\n\n### 八、投资要点 (Investment Takeaways)\n\n3-5 bullet takeaways:\n- 📈 Bull case: ...\n- 📉 Bear case: ...\n- ⚠️ Risk factors: ...\n- 🎯 Key watch items for next quarter: ...\n\nArchive v1.0.0: 5 files, 5556 bytes\n\nFiles: references/analysis_framework.md (2413b), scripts/process_call.py (2749b), scripts/transcribe.py (2102b), SKILL.md (2524b), _meta.json (142b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call transcript processing and analysis. Use when the user provides an earnings call audio file or transcript and wants structured analysis including key metrics, management sentiment, forward guidance, and stock data correlation. Triggers on phrases like \"process earnings call\", \"analyze earnings call\", \"财报电话会\", \"财报分析\", or when an audio/transcript file related to quarterly earnings is provided. Outputs structured analysis as a Feishu draft document.\n---\n\n# Earnings Call Processor\n\nAutomated pipeline: audio → transcript → structured analysis → Feishu draft.\n\n## Workflow\n\n### 1. Input Validation\n\nAccept one of:\n- **Audio file** (mp3/wav/m4a) → transcribe via `scripts/transcribe.py`\n- **Transcript file** (txt/md) → use directly\n- **Ticker symbol + quarter** → fetch from public sources\n\n### 2. Transcription (if audio)\n\n```bash\npython3 scripts/transcribe.py <audio_file> [--model base] [--language en]\n```\n\nOutputs: transcript text to stdout, optional `--output` to file.\n\n### 3. Stock Data Enrichment\n\nUse the `finance` skill tools:\n- `yfinance_get_stock_price` — current price\n- `yfinance_get_historical_data` — price action around earnings date (period=\"5d\")\n- `yfinance_get_stock_info` — company fundamentals (market cap, PE, sector)\n\n### 4. Structured Analysis\n\nRead `references/analysis_framework.md` for the full analysis template. Key sections:\n\n1. **Executive Summary** — 3-5 sentence overview\n2. **Key Financial Metrics** — revenue, EPS, guidance vs consensus\n3. **Management Sentiment** — tone analysis (confident/cautious/defensive)\n4. **Strategic Highlights** — M&A, new products, market expansion\n5. **Q&A Highlights** — analyst concerns, management responses\n6. **Forward Guidance** — raised/lowered/maintained\n7. **Stock Data Correlation** — price reaction, volume, vs sector\n\n### 5. Feishu Draft Output\n\nUse the `feishu-doc` skill to create a structured draft:\n\n```bash\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"财报分析: {COMPANY} {QUARTER}\" --content \"<markdown content>\"\n```\n\nApply the analysis template from `references/analysis_framework.md` to format content.\n\n## Configuration\n\nOptional env vars:\n- `WHISPER_MODEL` — faster-whisper model size (default: `base`)\n- `WHISPER_DEVICE` — `cpu` or `cuda` (default: `cpu`)\n\n## Dependencies\n\n- `faster-whisper` — audio transcription\n- `finance` skill — stock data\n- `feishu-doc` skill — document output\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1778097909226\n}\n\nFile v1.0.0:references/analysis_framework.md\n\n# Earnings Call Analysis Framework\n\nUse this template to structure analysis output.\n\n## Document Title Format\n\n`财报分析: {COMPANY_NAME} {YEAR} Q{N}`\n\n## Sections\n\n### 一、执行摘要 (Executive Summary)\n\n3-5 sentences covering:\n- Overall earnings result (beat/miss/meet)\n- Key headline number (revenue, EPS)\n- Market reaction (up/down/flat post-earnings)\n- One-line forward outlook\n\n### 二、核心财务指标 (Key Financial Metrics)\n\n| 指标 | 本期 | 上期 | 同比变化 | 一致预期 | vs预期 |\n|------|------|------|----------|----------|--------|\n| 营收 | | | | | |\n| EPS | | | | | |\n| 毛利率 | | | | | |\n| 运营利润率 | | | | | |\n| 自由现金流 | | | | | |\n\nFor Feishu: use bullet list format (tables unsupported in some channels):\n- **营收**: $X (同比 +Y%, 预期 $Z, beat/miss by W%)\n- **EPS**: $X (同比 +Y%, 预期 $Z)\n\n### 三、管理层基调分析 (Management Sentiment)\n\nCategorize as: 🟢 信心充足 / 🟡 谨慎乐观 / 🔴 偏谨慎\n\nEvidence from transcript:\n- CEO key phrases → quote 2-3 notable statements\n- CFO tone on margin/expense → quote 1-2 statements\n- Language shifts vs prior call (new cautious phrases, removed optimistic phrases)\n\n### 四、战略亮点 (Strategic Highlights)\n\n- **M&A / Partnerships**: Any announced or completed deals\n- **Product Launches**: New products, features, or services\n- **Market Expansion**: Geographic or segment expansion\n- **Cost Initiatives**: Restructuring, efficiency programs\n- **Capital Allocation**: Buyback, dividend changes\n\n### 五、Q&A 重点 (Q&A Highlights)\n\nTop 3-5 analyst questions with management response summary:\n1. **[Analyst Firm]**: [Question topic] → Management: [Key response point]\n2. ...\n\n### 六、前瞻指引 (Forward Guidance)\n\n| 指标 | 公司指引 | 一致预期 | 含义 |\n|------|----------|----------|------|\n| 下季营收 | | | 上调/下调/维持 |\n| 全年EPS | | | 上调/下调/维持 |\n| CapEx | | | |\n\nAlso note: raised guidance, lowered guidance, or maintained.\n\n### 七、股价数据关联 (Stock Data Correlation)\n\n- **盘后/盘前反应**: +X% / -X%\n- **成交量**: vs 20日平均\n- **行业对比**: 同期同行业公司表现\n- **技术位**: 关键支撑/阻力\n\n### 八、投资要点 (Investment Takeaways)\n\n3-5 bullet takeaways:\n- 📈 Bull case: ...\n- 📉 Bear case: ...\n- ⚠️ Risk factors: ...\n- 🎯 Key watch items for next quarter: ...\n\nArchive v1.2.1: 4 files, 6409 bytes\n\nFiles: clawhub.json (781b), SKILL.md (992b), src/process_earnings_call.py (16510b), _meta.json (142b)\n\nFile v1.2.1:SKILL.md\n\n---\nname: earnings-call-processor\nversion: 1.2.1\ndescription: Transcribe earnings call audio, analyze stock data, and generate structured Feishu documents.\ntags: ['earnings', 'feishu', 'transcription', 'financial-analysis']\n---\n\n# Earnings Call Processor\n\nEnd-to-end pipeline: Whisper transcription → stock analysis → Feishu structured document.\n\n## Usage\n\n```bash\npython3 src/process_earnings_call.py \\\n  --audio audio_transcripts/earnings_call_sample.wav \\\n  --stock financial_reports/aapl_stock_history.csv \\\n  --output feishu_docs/earnings_summary_draft.json\n```\n\n## What It Does\n\n1. **Transcribe** audio via Whisper CLI\n2. **Analyze** stock CSV (price trend, volatility, moving averages)\n3. **Generate** a Feishu-structured JSON document with all findings\n4. **Draft** mode by default; pass `--publish` to push to Feishu immediately\n\n## Requirements\n\n- `whisper` CLI installed\n- Python 3.9+ with `pandas`\n- Feishu app credentials in environment (`FEISHU_APP_ID`, `FEISHU_APP_SECRET`)\n\nFile v1.2.1:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.2.1\",\n  \"publishedAt\": 1778097420279\n}\n\nFile v1.2.1:clawhub.json\n\n{\"name\": \"earnings-call-processor\", \"slug\": \"earnings-call-processor\", \"version\": \"1.2.1\", \"description\": \"Transcribe earnings call audio, analyze stock data, and generate structured Feishu documents.\", \"changelog\": \"v1.2.1 — Complete Feishu document generation with stock analysis integration, Whisper transcription with CLI/Python fallback, draft/publish workflow, and structured Key Takeaways section.\" \"author\": \"finance-operations\", \"tags\": [\"earnings\", \"feishu\", \"transcription\", \"financial-analysis\"], \"entrypoint\": \"src/process_earnings_call.py\", \"requirements\": {\"python\": \">=3.9\", \"packages\": [\"pandas\"], \"optional_packages\": [\"openai-whisper\"], \"bins\": [\"whisper\"], \"env\": [\"FEISHU_APP_ID\", \"FEISHU_APP_SECRET\"]}, \"files\": [\"SKILL.md\", \"src/process_earnings_call.py\"]}\n\nArchive v1.1.1: 3 files, 5257 bytes\n\nFiles: _meta.json (142b), SKILL.md (1702b), src/process_earnings_call.py (14537b)\n\nFile v1.1.1:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Process earnings call audio into structured Feishu documents with Whisper transcription and financial analysis.\ntags: ['earnings', 'finance', 'feishu', 'whisper', 'transcript']\n---\n\n# Earnings Call Processor\n\nTranscribes earnings call audio, analyzes historical stock data, and generates structured Feishu documents.\n\n## Prerequisites\n\n- Python 3 with `openai-whisper`, `pandas`\n- Feishu doc skill installed (for publishing)\n- `clawhub` CLI (for publishing skill updates)\n\n## Usage\n\n```bash\n# Full pipeline: transcribe + analyze + generate draft\npython3 src/process_earnings_call.py \\\n  --audio audio_transcripts/earnings_call_sample.wav \\\n  --stock financial_reports/aapl_stock_history.csv \\\n  --output feishu_docs/earnings_summary_draft.json\n\n# Transcribe only\npython3 src/process_earnings_call.py \\\n  --audio audio_transcripts/earnings_call_sample.wav \\\n  --output feishu_docs/transcript_only.json\n\n# Analyze stock data only (no audio)\npython3 src/process_earnings_call.py \\\n  --stock financial_reports/aapl_stock_history.csv \\\n  --output feishu_docs/stock_analysis.json\n```\n\n## Output\n\nGenerates a JSON file with Feishu-structured document content, ready for `doc_ctl.py create` or `append`.\n\n## Publish to Feishu\n\nAfter generating the draft JSON, use the feishu-doc skill:\n\n```bash\n# Create as draft\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"Earnings Call Summary\" --content \"$(cat feishu_docs/earnings_summary_draft.txt)\"\n\n# Publish as shared doc (after confirmation)\npython3 .claude/skills/feishu-doc/scripts/doc_ctl.py create \"Earnings Call Summary\" --content \"$(cat feishu_docs/earnings_summary_draft.txt)\" --share ou_xxxxx\n```\n\nFile v1.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.1.1\",\n  \"publishedAt\": 1778097279988\n}\n\nArchive v1.2.0: 7 files, 9325 bytes\n\nFiles: _meta.json (142b), references/analysis-template.md (1339b), scripts/assemble_analysis.py (6594b), scripts/fetch_stock_data.py (1724b), scripts/process_call.sh (3153b), scripts/transcribe_openai.py (742b), SKILL.md (3725b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: earnings-call-processor\ndescription: Automated earnings call processing workflow. Transcribes earnings call audio, fetches related stock/financial data, generates structured analysis, and publishes output as a Feishu document draft. Use when the user wants to process an earnings call (财报电话会), analyze a quarterly earnings call recording, or generate an earnings call report. Triggers on phrases like \"处理财报电话会\", \"分析earnings call\", \"生成财报分析\", \"earnings call report\".\nversion: 1.1.0\n---\n\n# Earnings Call Processor v1.1.0\n\n全自动财报电话会处理工作流: 音频 → 转录 → 股票数据 → 结构化分析 → 飞书草稿\n\n## Quick Start (Agent Mode)\n\n当用户请求处理财报电话会时，按以下流程自动执行：\n\n```\n用户: \"处理AAPL Q1-2025财报电话会\" 或 \"分析这个earnings call录音\"\n```\n\n### 自动工作流\n\n1. **获取音频** — 确认音频文件路径或URL\n2. **转录音频** — 调用 Whisper (本地) 或 OpenAI Whisper API\n3. **抓取股票数据** — 调用 finance skill 获取实时行情和基本面\n4. **AI深度分析** — Agent 基于转录+财务数据生成结构化分析（填充模板中的占位区域）\n5. **输出飞书草稿** — 调用 feishu-doc skill 创建飞书文档\n\n## Step-by-Step\n\n### 1. Transcribe Audio\n\n优先使用 OpenAI Whisper API（质量更稳定）：\n\n```bash\n# 方式A: OpenAI API（推荐，需 OPENAI_API_KEY）\npython3 scripts/transcribe_openai.py <audio_file> /tmp/ecp/transcript.txt\n\n# 方式B: 本地 whisper（需安装 openai-whisper）\nwhisper <audio_file> --model turbo --language en --output_format txt --output_dir /tmp/ecp\n```\n\n支持的音频格式: mp3, wav, m4a, flac, webm\n\n### 2. Fetch Stock Data\n\n```bash\npython3 scripts/fetch_stock_data.py AAPL /tmp/ecp/stock_data.json\n```\n\n或使用 finance skill 的 yfinance 工具获取更详细数据。\n\n### 3. Assemble Analysis\n\n```bash\npython3 scripts/assemble_analysis.py \\\n  --transcript /tmp/ecp/transcript.txt \\\n  --ticker AAPL \\\n  --stock-data /tmp/ecp/stock_data.json \\\n  --quarter \"Q1-2025\" \\\n  --output /tmp/ecp/analysis.md\n```\n\n### 4. AI Deep Analysis (Agent Step)\n\n`assemble_analysis.py` 生成的框架包含占位区域（如 `[AI Agent将基于...]`）。\nAgent 需阅读完整转录文本和股票数据，填充以下关键区域：\n\n- **执行摘要** — 3-5句核心要点\n- **核心议题与管理层评论** — 3-5个议题，含管理层原话和解读\n- **Q&A精选** — 提取最重要的3-5个问答\n- **展望与要点** — 看多/风险/关注点\n\n### 5. Publish to Feishu\n\n```bash\nFEISHU_SCRIPT=$(find ~/.openclaw -path \"*/feishu-doc/scripts/doc_ctl.py\" | head -1)\npython3 \"$FEISHU_SCRIPT\" create \"财报电话会分析: {COMPANY} {QUARTER}\" --content \"<完整分析markdown>\"\n```\n\n## One-Command Workflow\n\n```bash\nbash scripts/process_call.sh \\\n  --audio /path/to/earnings_call.mp3 \\\n  --ticker AAPL \\\n  --quarter Q1-2025 \\\n  --feishu\n```\n\n## Output Structure\n\n参见 [references/analysis-template.md](references/analysis-template.md) — 包含完整模板和字段说明。\n\n## Dependencies\n\n- **finance** skill — 股票数据获取\n- **feishu-doc** skill — 飞书文档发布\n- **Whisper** — 音频转录 (本地 whisper 或 OpenAI API 二选一)\n- **yfinance** — Python 股票数据库 (fetch_stock_data.py 使用)\n\n## v1.1.0 Changes\n\n- 新增 `process_call.sh` 一键工作流脚本\n- 新增 `transcribe_openai.py` OpenAI Whisper API 转录\n- 新增 `fetch_stock_data.py` 独立股票数据抓取\n- `assemble_analysis.py` 增强: 支持 `--stock-data` 预加载数据、发言人提取、Q&A自动分段、更丰富的财务字段\n- SKILL.md 重写为 Agent 自动执行指南\n\nFile v1.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1778096778433\n}\n\nFile v1.2.0:references/analysis-template.md\n\n# Earnings Call Analysis Template\n\n## Title\n\n`财报电话会分析: {COMPANY} {FISCAL_QUARTER} ({DATE})`\n\n## Structure\n\n```markdown\n# 财报电话会分析: {COMPANY} {FISCAL_QUARTER}\n\n## 执行摘要\n3-5句核心要点概述：业绩表现、关键变化、管理层基调。\n\n## 财务亮点\n- 营收: {value} (同比 {change}%)\n- EPS: {value} (预期 {estimate}, 差异 {surprise}%)\n- 毛利率: {value}%\n- 自由现金流: {value}\n- 指引: {guidance_summary}\n\n## 核心议题与管理层评论\n### 议题1: {title}\n管理层原话摘要 + 解读\n\n### 议题2: {title}\n管理层原话摘要 + 解读\n\n## Q&A精选\n### Q1: {analyst_firm} — {question_summary}\nA: {response_summary}\n\n### Q2: {analyst_firm} — {question_summary}\nA: {response_summary}\n\n## 股价与估值背景\n- 当前股价: {price} ({change_on_day}%)\n- 市值: {market_cap}\n- P/E (TTM): {pe_ratio}\n- 近3月走势: {trend_description}\n\n## 展望与要点\n- 看多因素\n- 风险因素\n- 关键关注点\n\n---\n数据来源: 电话会录音转录 + yfinance | 生成时间: {timestamp}\n```\n\n## Notes\n\n- Replace all `{placeholders}` with actual data\n- Keep management quotes in original language; add Chinese summary when target audience is Chinese\n- If transcript is incomplete, mark sections as `[数据不足]`\n- Always include data source attribution at the bottom","readmeExcerpt":"Skill: Earnings Call Processor Owner: terrycarter1985 Summary: Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Tags: latest:3.0.0 Version history: v1.1.0-alpha.1 | 2026-05-12T00:14:48.331Z | user v1.1.0-alpha.1: Local whisper fallback, structured analysis pipeline, Feishu draft integration, stock data via yfinance v3.0.0 | 2","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Full pipeline: transcribe + stock data + analysis + Feishu draft\npython3 scripts/process_earnings_call.py ./call.wav AAPL\n\n# Use local whisper (no API key needed)\npython3 scripts/process_earnings_call.py ./call.wav AAPL --local\n\n# Skip Feishu (local output only)\npython3 scripts/process_earnings_call.py ./call.wav MSFT --no-feishu\n\n# Custom output dir, language, and local model size\npython3 scripts/process_earnings_call.py ./call.mp3 TSLA --output-dir ./results --language en --local --model small"},{"language":"bash","snippet":"# API mode (requires OPENAI_API_KEY)\npython3 scripts/transcribe.py ./call.wav --output transcript.json\n\n# Local mode (no API key needed)\npython3 scripts/transcribe.py ./call.wav --local --model base --output transcript.json"},{"language":"bash","snippet":"python3 scripts/fetch_stock.py AAPL --period 3mo --output stock.json"},{"language":"bash","snippet":"python3 scripts/create_feishu_draft.py --title \"AAPL Q4 Analysis\" --content-file analysis.md"},{"language":"bash","snippet":"python3 src/process_earnings_call.py \\\n  --audio audio_transcripts/earnings_call_sample.wav \\\n  --stock-csv financial_reports/aapl_stock_history.csv \\\n  --symbol AAPL \\\n  --output-dir /tmp/earnings_output"},{"language":"bash","snippet":"python3 /path/to/feishu-doc/scripts/doc_ctl.py create \"AAPL Earnings Call Summary\" --content \"$(cat /tmp/earnings_output/feishu_content.md)\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: earnings-call-processor\ndescription: Automated earnings call processing workflow. Transcribe earnings call audio (OpenAI Whisper API or local whisper), fetch stock/financial data, generate structured analysis, and publish as Feishu draft. Use when processing earnings call recordings, quarterly earnings audio, investor call transcripts, or when asked to analyze an earnings call. Triggers on phrases like \"process earnings call\", \"analyze this earnings call\", \"transcribe earnings call\", \"财报电话会\", \"处理财报\", \"earnings call analysis\".\n---\n\n# Earnings Call Processor\n\nEnd-to-end pipeline: audio → transcript + stock data → structured analysis → Feishu draft.\n\n## Prerequisites\n\n- **OpenAI API key** (for Whisper API transcription) — set `OPENAI_API_KEY`; or use `--local` for offline transcription\n- **openai-whisper** — `pip install openai-whisper` (required for `--local` mode; auto-fallback if API unavailable)\n- **yfinance** — `pip install yfinance`\n- **ffmpeg** — required by whisper for audio processing\n- **Feishu** (optional, for draft creation) — requires feishu-doc skill configured\n\n## Quick Start\n\n```bash\n# Full pipeline: transcribe + stock data + analysis + Feishu draft\npython3 scripts/process_earnings_call.py ./call.wav AAPL\n\n# Use local whisper (no API key needed)\npython3 scripts/process_earnings_call.py ./call.wav AAPL --local\n\n# Skip Feishu (local output only)\npython3 scripts/process_earnings_call.py ./call.wav MSFT --no-feishu\n\n# Custom output dir, language, and local model size\npython3 scripts/process_earnings_call.py ./call.mp3 TSLA --output-dir ./results --language en --local --model small\n```\n\n## Pipeline Steps\n\n1. **Transcribe** (`scripts/transcribe.py`) — Sends audio to OpenAI Whisper API (or local whisper with `--local`), returns transcript + segments\n2. **Fetch Stock** (`scripts/fetch_stock.py`) — Pulls price history, company info, financials via yfinance\n3. **Analyze** (`scripts/process_earnings_call.py` → `build_analysis()`) — Combines transcript + stock data into structured markdown\n4. **Publish** (`scripts/create_feishu_draft.py`) — Creates Feishu document with the analysis\n\n## Individual Scripts\n\n### Transcribe only\n\n```bash\n# API mode (requires OPENAI_API_KEY)\npython3 scripts/transcribe.py ./call.wav --output transcript.json\n\n# Local mode (no API key needed)\npython3 scripts/transcribe.py ./call.wav --local --model base --output transcript.json\n```\n\n### Stock data only\n\n```bash\npython3 scripts/fetch_stock.py AAPL --period 3mo --output stock.json\n```\n\n### Feishu draft from existing content\n\n```bash\npython3 scripts/create_feishu_draft.py --title \"AAPL Q4 Analysis\" --content-file analysis.md\n```\n\n## Output\n\nAll outputs go to `--output-dir` (default: `./output`):\n\n| File | Description |\n|------|-------------|\n| `transcript.json` | Full transcript with segments and timestamps |\n| `stock_data.json` | Price history, company info, financials |\n| `analysis.md` | Structured analysis document (also sent to Feishu) |\n\n## Agent Workflow\n\nW"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72jmd20ws94jr0p8b3p24wyn82abgj\",\n  \"slug\": \"earnings-call-processor\",\n  \"version\": \"1.1.0-alpha.1\",\n  \"publishedAt\": 1778544888331\n}"},{"path":"references/output_format.md","content":"# Earnings Call Output Format\n\n## Document Structure\n\nThe Feishu draft follows this structure:\n\n1. **Header** — Company name, ticker, generation timestamp, call duration\n2. **Quick Metrics** — Current price, market cap, P/E, EPS, growth rates, price trend\n3. **Transcript Summary** — First 500 chars of transcript as preview; full transcript in raw JSON\n4. **Key Themes & Sentiment** — Template for analyst/LLM to fill: tone, key topics, guidance, risks\n5. **Financial Context** — Table: sector, industry, 52-week range, forward P/E\n6. **Price Action** — Recent 10 trading days table\n7. **Action Items** — Checklist for follow-up analysis\n\n## LLM Post-Processing (Optional)\n\nAfter generating the draft, an LLM can enrich \"Key Themes & Sentiment\" by:\n- Analyzing the full transcript for management tone (bullish/bearish/neutral)\n- Extracting specific forward guidance statements\n- Identifying risk factors mentioned\n- Comparing language vs. previous quarter's call\n\nThe `process_earnings_call.py` script produces the structural scaffold. The agent invoking it should follow up with LLM-based analysis to fill the template sections."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Skill: Earnings Call Processor Owner: terrycarter1985 Summary: Transcribe earnings call audio via Whisper, analyze stock price data, and generate structured Feishu documents summarizing financial results. Tags: latest:3.0.0 Version history: v1.1.0-alpha.1 | 2026-05-12T00:14:48.331Z | user v1.1.0-alpha.1: Local whisper fallback, structured analysis pipeline, Feishu draft integration, stock data via yfinance v3.0.0 | 2","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":949,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T01:32:55.565Z","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":"2026-10-12T01:32:55.565Z","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":"2026-10-12T04:41:46.411Z","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"}]}}}