edgar-sec-filings

SEC EDGAR filing analysis — 10-K, 10-Q, 8-K, proxy statements, insider Form 4. Extract key financials, risk factors, management discussion, and generate investment signals from US public company filings.

Quality

70%

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/edgar-sec-filings/SKILL.md

Quality

Content

57%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.

A dense, actionable analytical framework with strong concrete code and well-organized sections, but it functions as a monolithic inline reference rather than a lean overview with one-level-deep references, and lacks an explicit sequenced analysis workflow with checkpoints.

Suggestions

Add a short numbered analysis workflow at the top (retrieve filings -> extract financials -> score MD&A tone -> compare risk factors -> score insider/13F -> composite -> emit output) with a validation checkpoint (e.g. confirm filing date/currency consistency before scoring).

Move the detailed per-filing frameworks (10-K/10-Q deep dive, insider scoring, 13F analysis) into separate reference files (e.g. ANALYSIS.md, INSIDER.md) and keep SKILL.md as a lean overview with one-level-deep links.

Trim explanatory prose Claude already knows (e.g. the definition of MD&A, generic positive/negative tone word lists) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain reference (filing tables, signal rules, scoring template) that earns its place, but includes unnecessary explanations Claude already knows ('The MD&A section is the most qualitative and forward-looking part of the filing') and obvious tone word-lists; fits the 'mostly efficient with some unnecessary explanation' anchor rather than 4.	3 / 5
Actionability	Provides concrete executable code (yfinance Ticker usage, EDGAR URLs, score_insider_activity, analyze_13f_changes, composite scoring template, output format) with only minor template-ish gaps (filing_score dict of zeros); fits the 'mostly executable with minor gaps' anchor.	4 / 5
Workflow Clarity	Content is organized by topic/filing type rather than as a sequenced analysis workflow, and lacks explicit validation checkpoints; the implied retrieve->analyze->score->output sequence has no checkpoints, matching the score-3 anchor. Not capped lower since this is read-only analysis, not destructive/batch.	3 / 5
Progressive Disclosure	Well-sectioned with clear headers, but at ~290 lines all content is inline with no bundle files and no external references; detailed frameworks (10-K deep dive, insider, 13F) that could live in separate reference files are inlined, fitting the score-3 anchor. The under-50-line exception does not apply.	3 / 5
	Total	13 / 20 Passed

Description

82%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.

A specific, well-targeted description with strong trigger terms and concrete actions, written in correct third-person voice. Its only material weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about SEC/EDGAR filings, 10-K/10-Q/8-K reports, proxy statements, insider Form 4 transactions, or fundamental analysis of US public companies.'

Optionally include common synonyms/extensions users might say (e.g. 'annual report', 'quarterly report', 'earnings filings') to broaden natural-term coverage further.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Extract key financials, risk factors, management discussion, and generate investment signals') plus enumerated filing types (10-K, 10-Q, 8-K, proxy, Form 4), matching the comprehensive-coverage anchor; not below 5 since coverage is broad and concrete.	5 / 5
Completeness	Clear 'what' (extract financials/risk/MD&A, generate signals) but no explicit 'Use when...' trigger clause; the rubric caps completeness at 3 for a missing when-clause, so not 4.	3 / 5
Trigger Term Quality	Includes natural terms users say ('SEC EDGAR', '10-K', '10-Q', '8-K', 'proxy statements', 'insider Form 4', 'US public company filings') with synonyms and filing codes, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Narrow niche (SEC EDGAR US public-company filings) with specific filing-type triggers gives minimal overlap with other skills; matches the clear-niche anchor.	5 / 5
	Total	18 / 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/edgar-sec-filings/SKILL.md
Commit: e90b6c6

Reviewed: 3 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.