investment-checklist

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

Quality

67%

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

77%

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

The skill is highly actionable with a clear, checkpoint-driven workflow and real tooling commands. Its weaknesses are conciseness (some prose/meta preamble) and progressive disclosure (a long monolithic file with no reference bundles).

Suggestions

Move the detailed per-gate ★1-5 scoring rubrics and example tables into a references/ file (e.g. SCORING.md) and link to it from each gate, keeping SKILL.md a lean overview.

Trim the Codex-adapter preamble and the 段永平 quote, or relocate them to a short notes section, to reduce token weight without losing the workflow.

Verify the referenced 'tools/financial_rigor.py' exists at the repo root, or note where to locate it, so the executable commands resolve reliably.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is well structured, but at ~255 lines it includes prose asides (the 段永平 quote, the full 镜子测试 template) and a Codex-adapter preamble that could be tightened, fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides real executable commands (e.g. 'python3 tools/financial_rigor.py verify-valuation --price ... --eps ...'), concrete ★1-5 scoring rubrics with explicit thresholds, and ready-to-fill tables, matching 'fully executable code/commands; specific examples'.	3 / 3
Workflow Clarity	A clear 第一步–第七步 sequence with six gates is paired with explicit validation checkpoints (硬性否决, 快速否决清单, and the non-skippable 镜子测试), matching 'clear sequence with explicit validation steps; checklists for complex processes'.	3 / 3
Progressive Disclosure	Sections are well organized, but everything lives in one ~255-line SKILL.md with no bundle reference files (references/scripts/assets absent) and detailed scoring rubrics inline, fitting 'some structure but content that should be separate is inline' rather than split one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 names a clear, distinctive niche but reads more like a title than a capability statement: it lacks enumerated concrete actions and any explicit 'Use when' trigger. Adding an action list and a usage trigger would lift specificity and completeness.

Suggestions

Add concrete actions to the description, e.g. 'Evaluates ROE, moat, management, and valuation against a Buffett-style six-gate checklist before buying.'

Append an explicit trigger clause such as 'Use when deciding whether to buy a stock, or when the user asks for a Buffett/价值投资 pre-buy checklist.'

Drop the administrative 'Source: skills/investment-checklist.md.' meta-text, which adds no capability signal.

Dimension	Reasoning	Score
Specificity	The phrase '巴菲特价值投资买入前 Checklist' names the domain and the checklist artifact but does not enumerate concrete actions (e.g. evaluate ROE, test moat), matching the 'names domain and some actions' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill is (a Buffett pre-buy checklist) but provides no 'Use when...' trigger guidance, so per the rubric guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like '巴菲特', '价值投资', '买入前', and 'Checklist' appear, but it is a single narrow phrase missing common variations a user might say, fitting 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The niche (Buffett-style value-investing buy decision) is distinct and specific, making it unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 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: 634a399

Reviewed: 1 day 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.