{"id":47557263,"url":"https://github.com/xvary-research/claude-code-stock-analysis-skill","last_synced_at":"2026-04-01T17:01:17.630Z","repository":{"id":346242186,"uuid":"1189060136","full_name":"xvary-research/claude-code-stock-analysis-skill","owner":"xvary-research","description":"Claude Code stock analysis skill: SEC EDGAR + market data, /analyze /score /compare — free, local Python tools. By XVARY Research.","archived":false,"fork":false,"pushed_at":"2026-03-23T18:00:31.000Z","size":1383,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-23T18:29:00.254Z","etag":null,"topics":["ai-skills","anthropic","claude-code","claude-plugin","edgar","equity-research","investing","python","sec-edgar","stock-analysis","xvary"],"latest_commit_sha":null,"homepage":"https://xvary.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xvary-research.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-22T23:46:02.000Z","updated_at":"2026-03-23T18:00:40.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/xvary-research/claude-code-stock-analysis-skill","commit_stats":null,"previous_names":["xvary-research/stock-research"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/xvary-research/claude-code-stock-analysis-skill","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xvary-research%2Fclaude-code-stock-analysis-skill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xvary-research%2Fclaude-code-stock-analysis-skill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xvary-research%2Fclaude-code-stock-analysis-skill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xvary-research%2Fclaude-code-stock-analysis-skill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xvary-research","download_url":"https://codeload.github.com/xvary-research/claude-code-stock-analysis-skill/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xvary-research%2Fclaude-code-stock-analysis-skill/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31290538,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T13:12:26.723Z","status":"ssl_error","status_checked_at":"2026-04-01T13:12:25.102Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-skills","anthropic","claude-code","claude-plugin","edgar","equity-research","investing","python","sec-edgar","stock-analysis","xvary"],"created_at":"2026-03-29T12:00:36.114Z","updated_at":"2026-04-01T17:01:17.610Z","avatar_url":"https://github.com/xvary-research.png","language":"Python","funding_links":[],"categories":["XVARY Stock Research","Skills"],"sub_categories":["🗓 April 2026 Highlights","Agent Communication \u0026 Coding","Quick Setup with cc-safe-setup"],"readme":"# XVARY Stock Research\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)\n[![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)\n[![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-orange)](./SKILL.md)\n[![xvary.com](https://img.shields.io/badge/Full%20Deep%20Dives-xvary.com-black)](https://xvary.com)\n\nType `/analyze NVDA` in Claude Code and get a thesis-driven equity report with conviction scoring, kill criteria, and an EDGAR-backed financial snapshot -- in under two minutes, from public data, for free.\n\nThis is the open skill layer of [XVARY Research](https://xvary.com). We run a 21-stage pipeline to produce institutional-depth stock analysis. This repo gives you the methodology framework, the data tools, and the scoring models. The full 22-section deep dives live at [xvary.com](https://xvary.com).\n\n*We recognize Linux Do community*\n\n## From the live site (NVDA deep dive)\n\nCaptured from **[xvary.com/stock/nvda/deep-dive/](https://xvary.com/stock/nvda/deep-dive/)** — same product surface the skill is designed to complement.\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://xvary.com/stock/nvda/deep-dive/\" title=\"Open NVDA deep dive\"\u003e\u003cimg src=\"assets/nvda-deep-dive-hero.png\" alt=\"XVARY NVDA deep dive — report shell, section map, and subscribe gate\" width=\"720\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://xvary.com/stock/nvda/deep-dive/\" title=\"Open NVDA deep dive\"\u003e\u003cimg src=\"assets/nvda-deep-dive-thesis.png\" alt=\"XVARY NVDA deep dive — thesis pillars and variant view\" width=\"720\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://xvary.com/stock/nvda/deep-dive/\" title=\"Open NVDA deep dive\"\u003e\u003cimg src=\"assets/nvda-deep-dive-scenarios.png\" alt=\"XVARY NVDA deep dive — bear, base, and bull scenario framing\" width=\"720\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n*Regenerate these assets:* `npm install \u0026\u0026 npm run screenshots:nvda` (see `scripts/screenshot_xvary_nvda.mjs`).\n\n## What you get that raw data tools don't\n\n- **A verdict, not a spreadsheet** -- \"Constructive at 74/100 conviction\"\n- **Named kill criteria** -- exactly what would break the thesis\n- **Composite scores across four dimensions**, not just price ratios\n- **Analysis that reads like a research desk**, not a terminal dump\n\n## Quick Start\n\n### Clone and verify\n\n```bash\ngit clone git@github.com:xvary-research/claude-code-stock-analysis-skill.git\ncd claude-code-stock-analysis-skill\npython3 tools/edgar.py AAPL    # pulls SEC XBRL data\npython3 tools/market.py AAPL   # pulls price + ratios\n```\n\n**XVARY monorepo:** if you already have the full workspace, this skill lives at `9. Marketing/xvary skill/`.\n\n### Install as a Claude Code skill\n\n```bash\nmkdir -p ~/.claude/skills/xvary-stock-research\ncp SKILL.md ~/.claude/skills/xvary-stock-research/SKILL.md\ncp -R references tools examples ~/.claude/skills/xvary-stock-research/\n```\n\nOr skip the install entirely -- open Claude Code in this repo and say:\n\n```\nRead SKILL.md and run /analyze AAPL\n```\n\n**Plugin marketplace (same folder):** open this directory as the marketplace root (it contains `.claude-plugin/marketplace.json`), then in Claude Code run `/plugin marketplace add .` and `/plugin install xvary-stock-research@xvary-research`. Validate with `claude plugin validate .` before you tag a release.\n\n**Public GitHub checkout:** `/plugin marketplace add xvary-research/claude-code-stock-analysis-skill` then `/plugin install xvary-stock-research`.\n\n### Commands\n\n| Command | What it does |\n|---|---|\n| `/analyze {ticker}` | 1-page thesis + scorecard + risks + EDGAR-backed financial snapshot |\n| `/score {ticker}` | Momentum, Stability, Financial Health, and Upside Estimate |\n| `/compare {A} vs {B}` | Side-by-side score, thesis, and risk differential |\n\n## Example: `/analyze NVDA`\n\nFull example: [examples/nvda-analysis.md](./examples/nvda-analysis.md)\n\n```\nVerdict: CONSTRUCTIVE (Conviction 74/100)\n\n┌─────────────────┬───────┬──────────────────────────────────────────────┐\n│ Score           │ Value │ Read                                         │\n├─────────────────┼───────┼──────────────────────────────────────────────┤\n│ Momentum        │  88   │ Demand + operating leverage remain strong    │\n│ Stability       │  70   │ Strong execution, non-zero cyclicality risk  │\n│ Financial Health│  84   │ Robust balance sheet vs obligations          │\n│ Upside Estimate │  64   │ Positive setup, expectations already high    │\n└─────────────────┴───────┴──────────────────────────────────────────────┘\n\nThesis pillars:\n  1. AI infrastructure spend durability\n  2. CUDA ecosystem lock-in + pricing power\n  3. Operating leverage on incremental revenue\n  4. Balance-sheet capacity through cycle volatility\n\nKill criteria: hyperscaler capex pullback + export control\nescalation + gross-margin break with rising capex intensity\n\nFinancial snapshot (public, 10-K 2026-01-25):\n  Revenue $215.9B · Net income $120.1B · OCF $102.7B\n  Assets $206.8B / Liabilities $49.5B\n  Price $172.70 · Market cap ~$4.20T · P/E 35.23 · Beta 2.34\n```\n\n**This is the free layer.** The full pipeline produces 22-section reports with DCF models, competitive matrices, risk scenarios, and adversarial challenge gates.\n\n**Open the live NVDA report:** [xvary.com/stock/nvda/deep-dive/](https://xvary.com/stock/nvda/deep-dive/) (free preview; full tabs with subscription)\n\n## How this compares\n\n|  | Raw data MCPs | Screener APIs | **This repo** |\n|---|---|---|---|\n| Free | Varies | Usually no | **Yes** |\n| Thesis with verdict | No | No | **Yes** |\n| Named kill criteria | No | No | **Yes** |\n| Composite scoring (4 dimensions) | No | Partial | **Yes** |\n| Works locally, no API key | N/A | No | **Yes** |\n| Methodology published | N/A | No | **Yes** |\n\n## Architecture\n\n**Skill layer (this repo):** public data in → methodology + scoring → structured output → link out to full deep dives on [xvary.com](https://xvary.com).\n\n### Claude Code plugin bundle (ships in this folder)\n\n| Path | Role |\n|------|------|\n| `.claude-plugin/marketplace.json` | Marketplace catalog **`xvary-research`** — users run `/plugin marketplace add` from this directory |\n| `plugins/xvary-stock-research/` | Plugin wrapper; `skills/xvary-stock-research/` symlinks to root `SKILL.md`, `references/`, `tools/`, `examples/` so there is a single source tree |\n\n**Monorepo checkout:** open a terminal in **`9. Marketing/xvary skill/`** (this folder), then run `/plugin marketplace add .` in Claude Code — same as a standalone `claude-code-stock-analysis-skill` clone where this folder is the repo root.\n\n```mermaid\nflowchart LR\n    A[\"/analyze ticker\"] --\u003e B[\"tools/edgar.py\\nSEC XBRL + filings\"]\n    A --\u003e C[\"tools/market.py\\nYahoo → Finviz → Stooq\"]\n    B --\u003e D[\"Methodology spine\\n+ scoring refs\"]\n    C --\u003e D\n    D --\u003e E[\"Structured analysis\\n+ kill criteria\"]\n    E --\u003e F[\"xvary.com deep dive\"]\n```\n\n### 21-stage research spine + finalize (operational DAG)\n\nSame DAG as [references/methodology.md](./references/methodology.md): **22 nodes in code** (research spine + `finalize`). Edges show real control flow—parallel paths merge at **phase_b**, **quality_gate**, and **completion_loop**.\n\n```mermaid\nflowchart TB\n  subgraph P1[\"① Intake \u0026 evidence integrity\"]\n    s1[directive_selection] --\u003e s2[phase_a] --\u003e s3[data_quality_gate] --\u003e s4[evidence_gap_analysis]\n  end\n\n  subgraph P2[\"② Hypothesis \u0026 quant scaffolding\"]\n    s5[kvd_hypothesis]\n    s6[pane_selection] --\u003e s7[quant_foundation] --\u003e s8[model_quality_gate]\n  end\n\n  subgraph P3[\"③ Deep enrichment \u0026 triangulation\"]\n    s9[phase_b] --\u003e s10[triangulation] --\u003e s11[pillar_discovery]\n  end\n\n  subgraph P4[\"④ Parallel synthesis \u0026 QA\"]\n    s12[phase_c]\n    s13[why_tree]\n    s14[quality_gate]\n  end\n\n  subgraph P5[\"⑤ Adversarial challenge \u0026 conviction\"]\n    s15[challenge] --\u003e s16[synthesis]\n  end\n\n  subgraph P6[\"⑥ Audit, packaging \u0026 release control\"]\n    s17[audit] --\u003e s18[report_json]\n    s19[audience_calibration]\n    s20[compliance_audit]\n    s21[completion_loop] --\u003e s22[finalize]\n  end\n\n  s4 --\u003e s5\n  s4 --\u003e s6\n  s5 --\u003e s9\n  s6 --\u003e s9\n  s11 --\u003e s12\n  s11 --\u003e s13\n  s12 --\u003e s14\n  s13 --\u003e s14\n  s14 --\u003e s15\n  s16 --\u003e s17\n  s18 --\u003e s19\n  s18 --\u003e s20\n  s19 --\u003e s21\n  s20 --\u003e s21\n```\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eStage index (one-line intent)\u003c/b\u003e — click to expand\u003c/summary\u003e\n\n| # | Stage | Intent |\n|---|--------|--------|\n| 1 | `directive_selection` | Choose sector/style evidence directives |\n| 2 | `phase_a` | Baseline facts, filings, market context |\n| 3 | `data_quality_gate` | Block low-integrity factual inputs |\n| 4 | `evidence_gap_analysis` | Find gaps; open targeted searches |\n| 5 | `kvd_hypothesis` | Candidate key value drivers |\n| 6 | `pane_selection` | Choose report panes for company profile |\n| 7 | `quant_foundation` | Valuation / risk scaffolding |\n| 8 | `model_quality_gate` | Sanity-check model outputs |\n| 9 | `phase_b` | Enrichment + deeper context |\n| 10 | `triangulation` | Cross-check independent reasoning vectors |\n| 11 | `pillar_discovery` | Weighted thesis pillars |\n| 12 | `phase_c` | Module-level synthesis (parallel) |\n| 13 | `why_tree` | Causal claims + dependency chains |\n| 14 | `quality_gate` | Consistency + evidence sufficiency |\n| 15 | `challenge` | Adversarial test of pillars |\n| 16 | `synthesis` | Conviction, variant view, scenarios |\n| 17 | `audit` | Multi-role verification + follow-ups |\n| 18 | `report_json` | Structured report payload |\n| 19 | `audience_calibration` | Readability + decision speed |\n| 20 | `compliance_audit` | Methodology + policy checks |\n| 21 | `completion_loop` | Repair sparse / inconsistent sections |\n| 22 | `finalize` | Release gating + artifact finalization |\n\n\u003c/details\u003e\n\n## XVARY Scores\n\nDefinitions: [references/scoring.md](./references/scoring.md)\n\n| Score | What it measures |\n|---|---|\n| **Momentum** | Direction and persistence of operating + market trajectory |\n| **Stability** | Earnings durability, cyclicality resilience, variance control |\n| **Financial Health** | Balance-sheet strength and cash-flow solvency |\n| **Upside Estimate** | Asymmetry vs. current implied expectations |\n\n## Methodology (Published Framework)\n\nFull framework: [references/methodology.md](./references/methodology.md)\n\nWhat's published:\n- 21-stage research DAG with stage purposes\n- 23 module map and what each module produces\n- Quality gate names and validation criteria\n- Conviction scoring and variant-perception philosophy\n- Kill-file risk discipline\n\nWhat stays proprietary:\n- LLM prompts and chain-of-thought templates\n- Threshold tables and scoring formulas\n- Triangulation and convergence algorithms\n- Sector-specific prompt libraries\n\n## Data Sources\n\n| Source | Access | Used for |\n|---|---|---|\n| **SEC EDGAR** | Public, free | Company facts (XBRL) + filing metadata |\n| **Yahoo Finance** | No API key | Quote, valuation, ratio fields |\n| **Finviz / Stooq** | Fallback | Resilience when Yahoo is unavailable |\n\nEDGAR patterns: [references/edgar-guide.md](./references/edgar-guide.md)\n\n## Full Deep Dives\n\n| Ticker | Link |\n|---|---|\n| NVDA | [xvary.com/stock/nvda/deep-dive/](https://xvary.com/stock/nvda/deep-dive/) |\n| All coverage (3,325 names) | [xvary.com/discover](https://xvary.com/discover) |\n| Methodology narrative | [xvary.com/methodology](https://xvary.com/methodology) |\n\n## Roadmap\n\n- [ ] MCP server for on-demand full deep dives\n- [ ] Earnings-season auto-refresh triggers\n- [ ] Additional scoring models (earnings quality, capital allocation)\n- [ ] Cursor / Windsurf / Codex skill mirrors (Claude Code marketplace ships from this folder)\n\n## Contributing\n\nPRs welcome for:\n- EDGAR taxonomy coverage and normalization\n- Market-data fallback robustness\n- Documentation clarity and examples\n\n## License\n\nMIT. See [LICENSE](./LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxvary-research%2Fclaude-code-stock-analysis-skill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxvary-research%2Fclaude-code-stock-analysis-skill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxvary-research%2Fclaude-code-stock-analysis-skill/lists"}