CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

investment-research

AI Berkshire skill: 投资研究:巴菲特-芒格-段永平-李录 四大师综合分析框架. Source: skills/investment-research.md.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/investment-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An unusually rigorous, highly actionable research workflow: every phase has executable tool commands, hard validation gates with pass/fail loops, and explicit anti-hallucination rules for the simulated-master commentary. Its weaknesses are a description-free monolithic layout — the deep terminal-value methodology should be split into a reference file — and redundant repetition of the same position-sizing constraint.

Suggestions

Move the ten-year discounted-valuation sub-workflow (Step 7's 长期折现估值 section: input table, C1–C3 rules, flip/sweep/config details) into a single reference file, keeping only the role-division table, the three-step audit gate, and the link in SKILL.md.

State the '十年折现未覆盖 r 只能收紧仓位建议、不得一票否决' constraint once as a hard-constraint callout and reference it from Step 8 instead of repeating it three times.

Document concrete example values for under-specified flags such as --g-shift {币种平移} so the flip command is copy-paste ready for a new company.

DimensionReasoningScore

Conciseness

The body is mostly efficient, domain-specific instruction (tool commands, currency bands, hard constraints) rather than concepts Claude already knows, but it is noticeably padded: the '十年折现未覆盖 r 只能收紧仓位、不得一票否决' constraint is restated three times (Step 7 intro, the role-division table, and the Step 8 估值解除语), and passages like 'C3 为什么是硬的' and the circular-reasoning aside repeat rationale that could be trimmed to one statement. Fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because nearly all content is non-generic, repo-specific guidance.

3 / 5

Actionability

Guidance is fully executable: copy-paste-ready commands for every stage (e.g. 'python3 tools/financial_rigor.py verify-market-cap --price {股价} --shares {总股本} --reported {报告市值} --currency {币种}', 'terminal_value.py audit ... --discrete-risks', 'report_audit.py verdict'), a concrete --config JSON schema with a field-by-field table, exact tolerance rules (偏差 ≤1%), and explicit output/report requirements. Fits the 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

The eight-step pipeline (前置偏见自查 → 数据收集 → … → 综合决策备忘录 → 数据抽检) is clearly sequenced, with explicit validation checkpoints and feedback loops: the audit 打回 conditions C1–C3, exit-code gating ('【准出】(退出码 0) → 报告可发布; 【打回】 → 修正后重跑,直到准出'), the 报告抽检 verdict loop, and the rationale for why the final audit matters ('写报告的过程中经常会回头调 g 或 r'). This matches the top anchor: clear sequence, explicit validation, error-recovery loops, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so everything lives in one ~400-line SKILL.md. Section and step headers give real structure and external docs are signaled where cited ('数据源规范:参见 skills/financial-data.md'), but the ~120-line ten-year terminal-value sub-workflow (inputs table, C1–C3 audit rules, flip/sweep procedures, config format) is exactly the deep material that belongs in a one-level-deep reference file. Fits 'Some structure but could be better organized; content that should be separate is inline'; not a 2 because headers and tool references are clear and navigable, not a wall of text.

3 / 5

Total

16

/

20

Passed

Description

48%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 essentially a title plus a source pointer: it identifies a distinctive niche (four-master investment analysis framework) but never states what the skill actually does (produce a structured research report with data cross-validation and valuation tooling) nor when to use it. It would rarely be selected on capability-match grounds alone.

Suggestions

Add an explicit 'Use when...' clause in Chinese and English, e.g. 'Use when the user asks to research/analyze a stock or company (股票分析, 公司研究, 估值, 买入建议) using the Buffett/Munger/Duan Yongping/Li Lu framework'.

State concrete actions: 'Produces a full investment research report covering business quality, moat, management, risk, secular trends, and valuation (three-scenario and ten-year discounted IRR) with mandatory tool-based data cross-validation.'

Remove or de-emphasize the 'Source: skills/investment-research.md' provenance note from the description — it consumes trigger space without helping skill selection.

DimensionReasoningScore

Specificity

The description quotes "AI Berkshire skill: 投资研究:巴菲特-芒格-段永平-李录 四大师综合分析框架" — it names the domain (investment research via the four masters' framework) but states no concrete actions whatsoever (no analyze/evaluate/produce verbs), and "Source: skills/investment-research.md" is provenance metadata, not a capability. This matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no action is listed at all.

2 / 5

Completeness

The 'what' is stated at a topic level (a comprehensive investment-research analysis framework based on four named masters) but the 'when' is entirely absent — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the guidelines. Not a 2 because the what is more specific than the vague-only anchor ('Has a vague "what" and no "when"'), and not a 4 because there is no 'when' at all.

3 / 5

Trigger Term Quality

Relevant keywords exist — "投资研究", "巴菲特", "芒格", "段永平", "李录" — which a user researching a stock in this style would plausibly say, but common natural variations are missing: 股票/公司分析, 估值, 买入/卖出建议, stock analysis, valuation. Fits 'Some relevant keywords but missing common variations or synonyms'; not a 4 because everyday phrasings like 股票分析 or 估值 dominate real usage.

3 / 5

Distinctiveness Conflict Risk

The four-master framework niche and the masters' names are distinctive triggers with low conflict risk against unrelated skills, e.g., "巴菲特-芒格-段永平-李录 四大师综合分析框架". It is not a 5 because the leading term "投资研究" is broad and would overlap with any generic stock/investment-analysis skill.

4 / 5

Total

12

/

20

Passed

Validation

100%

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-research/SKILL.md

Reviewed

Table of Contents

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.