industry-research

AI Berkshire skill: 行业投资研究：产业链全景扫描 + 四大师个股分析框架. Source: skills/industry-research.md.

Quality

63%

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 ./codex-skills/industry-research/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 body is a well-sequenced, highly actionable research workflow with concrete templates, rating scales, and a real exit-gate validation step. Its main weaknesses are a monolithic structure with no reference-file split and some conceptual prose that could be trimmed.

Suggestions

Split the long body into one-level-deep reference files (e.g. references/four-masters-framework.md, references/report-audit.md) and link to them from a concise overview in SKILL.md to enable progressive disclosure.

Condense the 'AI研究偏见自觉' conceptual prose and the repeated per-section 追问 prompts into tighter checklists to reduce token load.

Confirm the referenced tool paths (tools/financial_rigor.py, tools/report_audit.py, skills/financial-data.md) exist in the repo, since broken in-body references would undercut the otherwise executable guidance.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient structured tables and step lists, but the conceptual 'AI研究偏见自觉' section and repeated 追问 prompts are prose that could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides concrete templates (护城河评分表, 风险清单, 仓位配置表), explicit star-rating scales, exact output paths, and real executable commands like 'python3 tools/report_audit.py extract/verdict', giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	The eight-step sequence (第一步–第八步) ends in an explicit validation gate (数据抽检) with a pass/fail verdict and a fix-and-re-review feedback loop, satisfying the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic: no references/scripts/assets bundle exists and all detail lives inline in SKILL.md, so content that could be split (the four-masters framework, the audit process) is not progressively disclosed.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 identifies a clear niche (industry investment research via chain scanning and a four-masters stock framework) but reads more as a domain label than an invocation guide. It lacks any explicit 'Use when' trigger and leans on framework jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when researching an industry investment thesis, mapping its supply chain, or analyzing candidate stocks with the four-masters framework.'

Broaden trigger terms to natural variations users would actually say — 选股, 估值, 投资组合配置, 产业链分析 — in addition to the existing framework labels.

Drop the meta boilerplate 'Source: skills/industry-research.md.' from the description; it adds no signal for deciding whether to invoke the skill.

Dimension	Reasoning	Score
Specificity	It names the domain and two concrete components — "产业链全景扫描" and "四大师个股分析框架" — but these are high-level framework labels rather than a list of multiple discrete, concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "行业投资研究", "产业链", and "个股分析" are natural enough, but common variations a user might say (选股, 估值, 投资组合配置) are missing, so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	The four-masters framework niche is fairly specific, but the absence of distinct trigger phrasing means it could still overlap with a generic stock-analysis or investing skill.	2 / 3
	Total	8 / 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/industry-research/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.