investment-checklist

AI Berkshire skill: 巴菲特价值投资买入前 Checklist. Source: skills/investment-checklist.md.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/investment-checklist/SKILL.md

Quality

Content

71%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 a well-sequenced, largely actionable checklist with concrete tool commands and explicit pass/fail discipline, though slightly padded with aphorisms. Its main weakness is structure: it is a monolithic inline document with no reference files despite enough reusable content to warrant splitting.

Suggestions

Split the six scoring rubric tables and the three-scenario valuation command details into a reference file (e.g. references/scoring-rubric.md) referenced one level deep from SKILL.md.

Add an explicit validation checkpoint after the parallel data-collection step (e.g. confirm each company's ROE/PE data was retrieved; re-run collection for missing tickers before proceeding to 六关).

Trim the 段永平/芒格 epigram asides or move them to an optional 'commentary' reference to keep the main workflow lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse tables, code blocks, and imperatives that assume competence; only minor padding from the 段永平/芒格 epigram asides, fitting 'Efficient; minor instances of over-explanation'.	4 / 5
Actionability	Provides concrete executable commands (python3 tools/financial_rigor.py verify-valuation / three-scenario) with full argument specs, fill-in tables, and a fixed output filename; not a 5 because args are placeholders requiring substitution and the cited tool is not verified present.	4 / 5
Workflow Clarity	A clearly sequenced 7-step process with checkpoints (镜子测试, 快速否决清单, pass/fail/gray conclusions); not a 5 because the parallel batch data-collection step lacks an explicit validation/feedback loop for tool failure or data gaps.	4 / 5
Progressive Disclosure	No bundle files exist and the ~250-line body is a single monolithic document with all reusable rubric tables inline; well-sectioned by headers but content that could live in reference files is inlined, fitting 'Some structure but could be better organized'.	3 / 5
	Total	15 / 20 Passed

Description

28%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 a terse domain label plus a source-file pointer with no concrete capabilities, no natural trigger terms, and no explicit use-when guidance. It names the niche but is not actionable or distinctive enough for reliable skill selection.

Suggestions

Add concrete actions, e.g. 'Runs a Buffett-style pre-buy checklist on stocks: scores business quality, moat, management, and margin of safety, then outputs a pass/fail/gray verdict.'

Add an explicit trigger clause such as 'Use when the user is evaluating whether to buy a stock, asks for a value-investing analysis, or wants a Buffett/芒格 style buy decision.'

Include natural user-spoken keywords and synonyms (股票, 估值, 安全边际, 护城河, ticker, buy analysis) so the skill triggers reliably.

Dimension	Reasoning	Score
Specificity	Quotes only a domain label ('巴菲特价值投资买入前 Checklist') and a source path with no concrete actions, matching 'Names the domain but actions are minimal or generic'; not a 1 because the domain is named, not a 3 because zero concrete actions are listed.	2 / 5
Completeness	The 'what' is only vaguely implied (a checklist) and there is no 'when'/'Use when' guidance at all, matching 'Has a vague what and no when'; the missing trigger clause also caps completeness at 3 per guidelines, and this sits below that.	2 / 5
Trigger Term Quality	Phrases present are 'AI Berkshire skill' and a file path rather than natural user utterances like '股票', '估值', or '买入前分析'; missing the common phrases users would say, fitting 'one or two generic keywords'.	2 / 5
Distinctiveness Conflict Risk	The Buffett pre-buy checklist niche is somewhat specific but the terse 'AI Berkshire skill' framing could overlap with general investing skills; not a 4 because the description does not sharpen distinct triggers.	3 / 5
	Total	9 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xbtlin/ai-berkshire
Path: codex-skills/investment-checklist/SKILL.md
Commit: be46832

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.