sec-edgar
Skill2 starsChanged 9 months agoMITView on GitHub
Pull primary-source data on US-listed companies from SEC EDGAR's free APIs (10-K/10-Q/8-K/proxy text, full-text search across all filings since 2001, XBRL financials). Use whenever a task needs a US public company's filings, reported financials, risk factors, segment data, exec comp, or "which companies mention X" — for valuation, job/employer research or coursework — instead of scraping finance sites.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kansoku-trade/kansokutheir own version, first seen Sep 9, 2026
- Barrios88/barrios-skillstheir own version, first seen Jun 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- kansoku-trade/kansoku★ 322same name
- Barrios88/barrios-skills★ 63same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- compileSkill
- context-statusSkill
- create-documentSkill
- deploySkill
- devils-advocateSkill
- diagramSkill
- doc-reviewSkill
- excellenceSkill
- extract-diagramsSkill
- finishSkill
- google-tasksSkill
- image-searchSkill
- learnSkill
- mindmapSkill
- pedagogy-reviewSkill
- proofreadSkill
- qaSkill
- translateSkill
- typstSkill
- validate-bibSkill
- verifySkill
- visual-auditSkill
- waybackSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Every request needs a User-Agent with a contact, or SEC returns 403: curl -s -A "$SEC_USER_AGENT" ..., where SEC_USER_AGENT is an app name …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SEC EDGAR
Every request needs a User-Agent with a contact, or SEC returns 403:
curl -s -A "$SEC_USER_AGENT" ..., where SEC_USER_AGENT is an app name plus a contact email
(export SEC_USER_AGENT="my-research me@example.com"). If it is unset, ask the user for a contact
email before the first request; never invent one. Stay under 10 requests/second.
| Need | Endpoint |
| Ticker to CIK | https://www.sec.gov/files/company_tickers.json (cik_str; zero-pad to 10 digits for data.sec.gov) |
| Filing list | https://data.sec.gov/submissions/CIK##########.json (filings.recent: parallel arrays form, accessionNumber, filingDate, primaryDocument) |
| Full-text search | https://efts.sec.gov/LATEST/search-index?q=%22exact%20phrase%22&forms=10-K&dateRange=custom&startdt=YYYY-MM-DD&enddt=YYYY-MM-DD |
| All XBRL facts | https://data.sec.gov/api/xbrl/companyfacts/CIK##########.json |
| One concept over time | https://data.sec.gov/api/xbrl/companyconcept/CIK##########/us-gaap/<Tag>.json |
| Same concept across companies | https://data.sec.gov/api/xbrl/frames/us-gaap/<Tag>/USD/CY2024Q4I.json |
Document URL: https://www.sec.gov/Archives/edgar/data/<CIK without padding>/<accession without dashes>/<primaryDocument>.
Full-text search hits have _id = <accession>:<filename>, which gives both parts.
Gotchas:
- XBRL tags vary by filer and year (
RevenuesvsRevenueFromContractWithCustomerExcludingAssessedTax); check which tags exist in companyfacts before concluding data is missing. - companyfacts repeats a value in every later filing that restates it; dedupe on
accn/fy/fp/form, or filterform == "10-K"andfp == "FY". - Filings come back as raw HTML; strip tags before analysing, and quote section names (Item 1A, Item 7) when citing.
- US issuers only. Foreign private issuers file 20-F/6-K with sparse XBRL; UK companies go through the companies-house MCP.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.