CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

private-company-research

AI Berkshire skill: 未上市公司研究:多Agent并行深度研究框架. Source: skills/private-company-research.md.

Quality

59%

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/private-company-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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.

This is a rich, highly specific research playbook with excellent task-level actionability and a well-sequenced multi-agent workflow including a real cross-validation step. Its two structural weaknesses are its monolithic 46KB size — the six task templates and report schema belong in reference files, with the confidence and search-source rules stated once — and the absence of failure-handling loops for the six parallel agents it orchestrates.

Suggestions

Split each of the six task description templates (任务1-6) and the final report skeleton into references/ files (e.g. references/task-business-model.md), leaving SKILL.md as a ~100-line orchestration overview that links to them.

State the shared conventions (confidence emoji scale, source-priority matrix, fact-vs-inference formatting) once in a single section instead of repeating them in the anti-bias preamble, the agent prompt template, and 重要注意事项.

Add explicit failure handling in 第五/六步: what to do when an agent finishes with '严重不足' information completeness, returns contradictory key data, or stalls — e.g. relaunch with adjusted keywords or fall back to the first-principles mode already defined.

DimensionReasoningScore

Conciseness

The body is ~1,086 lines / 46KB in a single file with clear redundancy: confidence-labeling rules (🟢/🟡/🔴) are restated in the anti-bias section, in the agent prompt template, and again in 重要注意事项; source-priority guidance appears in both 任务2 and the agent prompt; the Codex adapter note repeats project logistics. Not a 1 because almost all content is actionable instruction rather than explanation of concepts Claude already knows; not a 3 because the repetition and sheer bulk go noticeably beyond 'could be tightened'.

2 / 5

Actionability

The guidance is concrete and executable as instruction-only content: exact agent configs (subagent_type: general-purpose, run_in_background: true), a full copy-paste agent prompt template, specific search-keyword strategies, named sources (晚点LatePost, 天眼查, Google Patents), a dated output path format, and fully specified report table schemas. Not a 5 because placeholders like {公司名} and $XXB are never instantiated with a worked example, and some instructions ('搜索关键词策略') rely on the agent to fill in specifics.

4 / 5

Workflow Clarity

The 9-step sequence is clearly ordered with a genuine validation checkpoint (第六步 cross-verification with data-conflict arbitration, signal-consistency checks, and an anti-bias review) plus progress tracking in 第五步 and cleanup in 第九步. Not a 5 because there are no error-recovery feedback loops — nothing says what to do when an agent returns empty, contradicts fatally, or a report is late — so checkpoints are present but recovery paths are missing.

4 / 5

Progressive Disclosure

The bundle contains no references/, scripts/, or assets/ files at all; the six per-task analysis templates (each 80-150 lines) are inlined entirely in SKILL.md, which is exactly the 'content that clearly belongs in separate files is inlined' pattern. Not a 1 because the body has a clear section hierarchy and no nested/buried references; not a 3 because the failure is not marginal organization but the total absence of any file-level splitting for ~900 lines of template payload.

2 / 5

Total

12

/

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 identifies a specific niche but reads as file metadata plus a framework title rather than a capability statement: no concrete actions, no 'use when' trigger guidance, and a trailing source-path note that adds noise. It would rarely be selected by a user's natural phrasing beyond the literal domain term.

Suggestions

Replace the metadata framing ('AI Berkshire skill:', 'Source: skills/...') with a capability statement listing concrete actions, e.g. estimates valuation, reconstructs financials from scattered sources, and assesses moat, competition, and governance for private companies.

Add an explicit trigger clause such as 'Use when the user asks to research, evaluate, or estimate the value of a private/unlisted company (e.g. 蚂蚁集团, SpaceX, Stripe, a unicorn, or pre-IPO target)'.

Include natural synonyms users would say — 估值、尽调、投研、未上市/私有公司 — so the skill triggers on varied phrasings.

DimensionReasoningScore

Specificity

The description names the domain ("未上市公司研究") and a structural approach ("多Agent并行深度研究框架") but states no concrete actions like analyzing financials, estimating valuation, or assessing risk. It does not reach a 3 because there is no concrete action verb beyond generic 'research'; it is above 1 because the domain is named specifically.

2 / 5

Completeness

The 'what' is present but only as a framework label (multi-agent parallel deep-research framework for private companies) with no enumerated capabilities, and there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the 'what' is stated clearly enough to identify the domain; not a 4 because the 'when' is entirely missing rather than weakly implied.

3 / 5

Trigger Term Quality

"未上市公司研究" is a natural phrase a user would say, and "多Agent并行" signals the working style, but common synonyms and related trigger terms (估值、尽调、投研、独角兽、private company due diligence) are absent. Not a 4 because keyword coverage stops at the bare domain name, and half the string ('AI Berkshire skill:', 'Source: skills/private-company-research.md.') is file metadata, not trigger language.

3 / 5

Distinctiveness Conflict Risk

The private-company-research niche with a multi-agent framing is clearly distinguishable from general research or public-company analysis skills, so conflict risk is low. Not a 5 because 'AI Berkshire skill' and the generic '深度研究框架' wording could weakly overlap with other investment/research skills.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1087 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

xbtlin/ai-berkshire

Path

codex-skills/private-company-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.