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.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/sec-edgar/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured, executable, and uses progressive disclosure effectively with real reference files. Minor conciseness trimming and a touch more inline error-handling guidance would push it to full marks.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence (compact Quick Start, terse parameter notes), but the link-convention blockquote and a few 'Notes' entries (e.g. explaining it is not a backtest loader) are mild over-explanation that could be trimmed, fitting the score-4 anchor rather than the fully lean score-5 anchor.	4 / 5
Actionability	Provides copy-paste-ready, executable guidance for both paths — concrete JSON tool calls and a complete Python snippet with real imports (`from backtest.loaders.sec_edgar_client import cik_for, get_submissions, get_company_facts`) — plus a referenced runnable end-to-end script, matching the score-5 anchor.	5 / 5
Workflow Clarity	The two retrieval paths (preferred tool path, then script path) are clearly sequenced and the ticker→CIK→filings→(optional) metric flow is legible; it sits at score 4 rather than 5 because error-handling/checkpoints are delegated to reference docs rather than stated inline, though the read-only non-batch nature means the score-3 destructive-operations cap does not apply.	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to real bundle files (references/sec_edgar_client.md, get_sec_filings_tool.md, endpoints_and_limits.md, forms_and_concepts.md, and scripts/sec_filings_example.py — all verified present), with content appropriately split and easy to navigate, matching the score-5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive about what the fetch interface does, with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g. 'Use when fetching SEC/EDGAR filings, 10-K/10-Q/8-K documents, or XBRL financial series for a U.S. ticker').

Include a couple of lay synonyms ('annual reports', 'quarterly reports', 'earnings filings') alongside the form codes to broaden trigger-term coverage.

Add a one-line trigger cue distinguishing this fetch skill from the edgar-sec-filings methodology skill at the description level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'resolve a ticker to its CIK, list recent filings (10-K / 10-Q / 8-K ...) with primary-document URLs, and pull XBRL companyfacts financial series' — giving comprehensive coverage of the fetch interface, matching the score-5 anchor rather than the score-4 'minor gaps' anchor.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — per the judging guidelines a missing trigger clause caps completeness at 3, which fits the score-3 anchor better than the score-4 anchor that requires both what and when.	3 / 5
Trigger Term Quality	Strong natural terms a user would say ('SEC EDGAR', 'filings', '10-K / 10-Q / 8-K', 'ticker', 'XBRL'), but it is missing common synonyms a lay user might use ('annual report', 'quarterly report', 'earnings'), keeping it just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	'U.S. SEC EDGAR fetch interface' names a clear niche and 'United States only' bounds it, but a closely related sibling skill (edgar-sec-filings methodology) creates minor overlap risk with no explicit trigger phrase in the description itself to disambiguate, placing it at score 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/sec-edgar/SKILL.md
Commit: f9cb061

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.