What does this skill do, and when should you use it?
EdgarTools is an open-source Python library that converts SEC EDGAR filings into typed Python objects and pandas DataFrames, covering 20+ form types with history back to 1994. It provides XBRL-standardized financial statements, insider transactions, institutional holdings, and 8-K events, plus a built-in MCP server and LLM-ready text output. The skill is organized in SKILL.md with subdirectories for core, financials, reports, holdings, ownership, and xbrl, each carrying pattern examples and a common-mistakes list. It suits teams doing securities data analysis in their own code or inside an AI assistant.
- Look up companies by ticker or CIK, discover filings by form type and year, and locate a filing by accession number
- Extract XBRL-standardized income statements, balance sheets, and cash flow statements from 10-K/10-Q filings
- Parse Form 3/4/5 insider transactions and 13F institutional holdings into structured objects or DataFrames
- Extract section text from 10-K/10-Q/8-K (Risk Factors, MD&A) and convert it to clean RAG-ready text
- Query time series for any accounting concept across years via the Company Facts API
- A quant or researcher needs to batch-compare multi-year XBRL-standardized revenue and profit metrics across companies
- A compliance or investment analyst tracks a company's executives' Form 4 insider buys and sells over recent months
- An analyst wants the latest hedge fund 13F holdings as a DataFrame for further analysis
- An engineer building a filings Q&A RAG system needs 10-K Risk Factors and MD&A sections as clean text
- A user querying SEC data in natural language inside Claude Desktop / Claude Code via the built-in MCP server
- Teams that need a hosted API with vendor-run operations and an SLA — the open-source library runs on your own infrastructure (a separate paid hosted platform, edgar.tools, exists)
- Use cases outside SEC filing analysis — this skill focuses on structured EDGAR parsing, not general financial news or summaries
How do you install this skill?
- Core function depends entirely on SEC EDGAR; reachability from mainland-China networks is poor and rate limits are strict (HTTP 429 requires 10+ minute waits), with no mirror setup guidance provided;
- set_identity requires a name and email sent with every SEC request for SEC compliance auditing — be aware before use;
- Publisher identity is unverified in the FollowSkills registry and the project is maintained by a single person, posing continuity risk;
- This is a static source review with no code executed; example output correctness has not been independently verified.
- Shell / CLI
- Network access
- Local filesystem
- MCP Server
Pythonedgartools package (pip install edgartools)SEC EDGAR identity (name + email)
Install the library, optionally with AI skill support:
Claude Code / Claude Desktop (AI Skills, recommended)
pip install "edgartools[ai]"
python -c "from edgar.ai import install_skill; install_skill()"Claude Desktop (MCP server route)
uvx --from "edgartools[ai]" edgartools-mcp(requires configuring mcpServers in claude_desktop_config. and setting the EDGAR_IDENTITY env var; needs uv)
As a plain Python library
pip install edgartoolsHow do you use this skill?
Once installed, send your agent any of these to trigger it:
- Compare Apple and Microsoft's revenue growth rates over the past 3 years
- List Tesla executives who sold more than $1 million in stock in the past 6 months
- Get Apple's latest 10-K income statement and balance sheet
- Show the full holdings of the latest 13F filing
You must identify yourself to the SEC first: from edgar import set_identity; set_identity("Your Name [email protected]"), or set the EDGAR_IDENTITY environment variable in MCP deployments. Core flow: start from a Company or Filing, call .obj() to get a typed object for that form. Common entry points: Company("AAPL"), find("0000320193-25-000079"), get_filings(form="10-K", year=2024). Every object exposes a .docs attribute for searching API usage. The skill tree splits into core/financials/reports/holdings/ownership/xbrl, each with skill.yaml (patterns and examples) and sharp-edges.yaml (mistakes to avoid).
What are this skill's strengths and limitations?
- Free, MIT-licensed — no API key, no quotas, no vendor lock-in
- XBRL-standardized financials enabling cross-company and cross-period comparison
- Typed objects and DataFrame output for 20+ form types
- Built-in MCP server and LLM-friendly text output for RAG and AI workflows
- Rate-limit aware, smart caching, enterprise/academic mirrors, 1000+ tests
- SEC amends filing formats quarterly and ships a new XBRL taxonomy yearly — 20+ parsers need continuous maintenance by a single maintainer
- You run and operate it yourself — no hosted SLA unless you pay for corporate sponsorship tiers
- EDGAR requires an identity (name + email) with every request, even though no key or signup is needed
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| EdgarTools — SEC EDGAR Filing Analysis Skill this page | 67 · Recommended | ★ 2.8k | 11d ago | MIT |
| StockValuation.io Local Valuation Workflow | 58 · Recommended | ★ 33 | 1mo ago | Apache-2.0 |
| Earnings Review: Deep Dive into Primary Sources | 52 · Use with care | ★ 17k | 13d ago | MIT |
| Value Investing Agent | 55 · Use with care | ★ 23 | 8mo ago | MIT |
| Investment Masters | 50 · Use with care | ★ 634 | 1mo ago | MIT |
The source compares EdgarTools with sec-api.io: EdgarTools is a free, MIT-licensed Python library running in your process, returning typed objects and DataFrames with built-in MCP/AI support, inspectable and forkable; sec-api is a hosted API from $49/mo returning JSON you parse yourself, requiring keys and rate tiers, proprietary and closed-source.
How did FollowSkills review this skill?
Read-only SEC EDGAR queries: no file writes, no external egress (requests go only to official SEC endpoints), no credentials (SEC requires only a declared identity; set_identity data flow is transparent and documented). sharp-edges.yaml explicitly discloses rate limits, identity requirements, and error semantics. Deductions: publisher unverified; set_identity collects a user email sent with every request to SEC — a privacy implication not spelled out; no explicit confirmation/rollback mechanisms (limited impact for read-only scope). Not full marks.
Highly self-consistent documentation: skill.yaml, sharp-edges.yaml, and validations.yaml reference each other coherently; a clear error vocabulary (TransportError/NotFoundError/None semantics) with strong failure feedback (429 wait policy, progressive fallback). The repository contains real CI workflows and an extensive test suite, meeting the static-calibration condition to exceed 10; however, the skill itself is mostly documentation/pattern files whose specific guidance paths (e.g., get_financials-first preference) lack dedicated skill-level test coverage, and runtime behavior cannot be verified statically, so no higher score.
Scenarios are clear (company lookup, filing discovery, content search); collaboration.yaml declares core-skill boundaries and delegation ranges with concrete trigger tables and a disclosed token budget. Deductions: core function depends entirely on SEC EDGAR (sec.gov/data.sec.gov), whose reachability from mainland-China networks is poor with strict rate limits; no mirror or offline guidance (enterprise mirrors only mentioned); no Chinese-language support; some boundaries rely on skill directories outside this review's scope.
Good layered architecture (SKILL.md entry → skill.yaml patterns → sharp-edges/validations/collaboration), versioned at 1.1 in skill.yaml, clear MIT license, thorough install notes and dependency rationale (high-quality pyproject comments). Deductions: no skill-level changelog; maintenance concentrated in a single maintainer (README self-describes as such) with an update path tied to sponsorship continuity; some example accessions may decay over time.
Clear marginal value for AI agents using SEC data: one-line XBRL parsing, str()/to_context() optimized for LLM output, README includes a cost comparison against alternatives (sec-api), and CI/test infrastructure provides execution evidence allowing the score above 7. Deductions: static review cannot verify the actual correctness/completeness of example outputs (e.g., financial-data standardization quality); effectiveness claims rest largely on author assertion.
The repository has genuine CI workflows (cassette safety gate, offline audit, 65% coverage floor, red-main tracking) and extensive test infrastructure, so many claims are auditable; sharp-edges claims to be 'discovered through skill testing' but no corresponding skill-level test records are shown. Facts and inferences are mostly separated. Nothing was executed in this review and skill-doc path coverage is not visible, capping at 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →