Sec Edgar logo

Sec Edgar

OrganizationPopular
HKUDS
sec-edgar

U.S. SEC EDGAR fetch interface — resolve a ticker to its CIK, list recent filings (10-K / 10-Q / 8-K and friends) with primary-document URLs, and pull XBRL companyfacts financial series. Free, no API key; rate-limited by IP so every request is throttled and carries a contact User-Agent. United States only.

Overview

PublisherHKUDS
RepositoryVibe-Trading
Skill namesec-edgar
Stars
35.2K
Forks
5.7K
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by HKUDS on GitHub. Read the source before you install it.

Installation

Install the Sec Edgar AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/sec-edgar
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git /tmp/Vibe-Trading
mkdir -p .claude/skills
cp -r /tmp/Vibe-Trading/agent/src/skills/sec-edgar .claude/skills/sec-edgar
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sec Edgar in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sec Edgar on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sec Edgar is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SEC EDGAR

Overview

The U.S. Securities and Exchange Commission (SEC) publishes free, no-auth JSON endpoints for every reporting company on its EDGAR system: a ticker-to-CIK directory, a recent-filings index, and the full set of XBRL ("companyfacts") financial concepts a company has reported. This skill documents how Vibe-Trading fetches that data through the bundled sec_edgar_client transport and the get_sec_filings agent tool.

This is the fetch skill — it covers how to get filing-index rows, document URLs, and us-gaap metric series out of EDGAR. The separate edgar-sec-filings skill is the methodology layer (how to read a 10-K, score insider activity, interpret 8-K items); for any actual data retrieval it delegates here.

Scope is the United States only. EDGAR has no coverage of A-shares, HK, or other non-U.S. markets — route those through tushare / yfinance / akshare instead.

Link convention: every link below that points into references/ is written relative to this document (references/...) — the form GitHub resolves when someone opens the file in a browser. The read_file tool resolves the same string against the skill that owns it, so the agent and a human reader reach one file. Keep the relative form when adding new docs, and keep reference paths unique across skills: a path two skills both carry is reported as ambiguous rather than guessed.

Quick Start

Preferred path — the get_sec_filings tool (read-only, throttled, returns strict JSON):

json
{ "ticker": "AAPL", "form": "10-K", "limit": 5 }
json
{ "ticker": "MSFT", "metric": "Revenues", "limit": 8 }

The tool resolves the ticker to a CIK, fetches the filing index (optionally filtered by form), and — when metric is set — also pulls the XBRL series for that us-gaap concept. See sec-edgar/references/get_sec_filings_tool.md for the full parameter and envelope contract.

Script path — call the sec_edgar_client transport directly when you need raw JSON the tool does not surface (e.g. company address, all units of a concept):

python
from backtest.loaders.sec_edgar_client import cik_for, get_submissions, get_company_facts

cik = cik_for("AAPL")            # "0000320193", or None if not in the SEC table
submissions = get_submissions(cik)   # recent-filings index + company metadata
facts = get_company_facts(cik)       # all reported XBRL concepts

A runnable end-to-end example lives at sec-edgar/scripts/sec_filings_example.py.

Parameter & Format Notes

  • Ticker: U.S. equity symbol, case-insensitive (AAPL, msft). Resolved to a CIK via the SEC company-tickers table; an unlisted ticker returns an error envelope (tool) or None (cik_for).
  • CIK: the SEC Central Index Key, normalized to a zero-padded 10-digit string (320193 → "0000320193"). The submissions and companyfacts endpoints require the padded form; document URLs use the un-padded form.
  • Form: SEC form type, case-insensitive (10-K, 10-Q, 8-K, DEF 14A, 4). Omit to return all recent forms.
  • Metric: an XBRL us-gaap concept name (Revenues, NetIncomeLoss, Assets, StockholdersEquity). Case-sensitive — these are exact taxonomy element names.
  • Dates: SEC returns ISO YYYY-MM-DD strings (e.g. 2023-09-30).
  • Return shape: the tool returns a JSON-string envelope; the client returns decoded JSON (dict).

Reference Docs

Scripts

Notes

  • Free, no API key: EDGAR is public. The only requirement is a descriptive User-Agent carrying a contact address; the client ships a compliant default and honors the VIBE_TRADING_SEC_UA override.
  • Rate-limited by IP: the SEC throttles per source IP and temporarily blocks clients that burst without a contact UA. Every request routes through the shared backtest.loaders._http throttle under the "sec" host bucket (≈0.12s spacing floor, overridable via VIBE_TRADING_SEC_MIN_INTERVAL). Do not bypass the client with raw requests loops.
  • United States only: a non-U.S. symbol will not resolve to a CIK.
  • Transport, not a backtest loader: sec_edgar_client is a thin REST client, not a DataLoaderProtocol. There is no source: "sec_edgar" backtest mode — EDGAR feeds the get_sec_filings tool, not the bar-loading layer.
  • Reporting lag: filings appear after the company submits; XBRL companyfacts trail the filing. Insider (Form 4) and 13F latency caveats are covered in the edgar-sec-filings methodology skill.
  • Research only: this data supports research and does not constitute investment advice.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sec Edgar AI skill do?

U.S. SEC EDGAR fetch interface — resolve a ticker to its CIK, list recent filings (10-K / 10-Q / 8-K and friends) with primary-document URLs, and pull XBRL companyfacts financial series. Free, no API key; rate-limited by IP so every request is throttled and carries a contact User-Agent. United States only.

Why use Sec Edgar on TypingMind?

Because you install it once and use it with any model. Sec Edgar is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sec Edgar in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/sec-edgar. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sec Edgar?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sec Edgar?

As many as you like. As long as a model supports skills, you can use Sec Edgar with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sec Edgar AI skill free?

Yes. It is published on GitHub by HKUDS under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇