CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-company-series

AI Berkshire skill: 深度公司系列:8 篇长文拆一家公司. Source: skills/deep-company-series.md.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/deep-company-series/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 high-quality, densely actionable workflow: it pairs concrete templates and executable commands with sequenced phases, validation checkpoints, and a rigorous fact-check/revision discipline. It earns top marks across all four content dimensions.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows; every section adds novel domain rules (the 禁用词 table, the 7-item fact-check checklist, the revision-level matrix) and assumes competence, matching the anchor-3 'lean and efficient; every token earns its place'.

3 / 3

Actionability

It provides a concrete 8-article template table with word counts, real executable commands (e.g., `grep "显然|必然|严重|教科书|完美"` and `git pull --rebase && git commit && git push`), and explicit path templates like `reports/{公司名}/《看懂{公司名}》/0X-XX.md`, matching the anchor-3 'fully executable; copy-paste ready'.

3 / 3

Workflow Clarity

Section 五 lays out four sequenced phases (调研→写作→跨篇扫描→发布核查) with explicit validation checkpoints (an Explore-agent cross-article consistency scan and a pre-push privacy grep) plus a 7-item checklist and a revise→verify→linked-update feedback loop, matching the anchor-3 'clear sequence with explicit validation steps'.

3 / 3

Progressive Disclosure

No bundle files are present and none are needed; the skill is a single cohesive instruction document organized into clearly headed numbered sections with a TOC-style article template, which per the scoring notes warrants a 3 for a well-organized self-contained skill even without external references.

3 / 3

Total

12

/

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 conveys a clear deliverable (an 8-article company deep-dive series) but lacks an explicit 'when to use' trigger clause and is padded with adapter/metadata noise. It is adequate but not exemplary, scoring uniformly at the midpoint.

Suggestions

Add an explicit 'Use when...' trigger clause naming the scenarios (e.g., deep company research published as a multi-article public series) and contrasting against single-report skills.

Drop the 'AI Berkshire skill:' prefix and 'Source: skills/deep-company-series.md.' metadata from the description so it reads as a natural trigger phrase.

List a few concrete actions (e.g., generate 8 templated articles, run cross-article consistency scans, enforce fact-check checks) to raise specificity.

DimensionReasoningScore

Specificity

The phrase "8 篇长文拆一家公司" names the domain and a concrete deliverable (an 8-article company dissection), but it does not enumerate multiple specific actions in the way the anchor-3 example does; it is more than the vague anchor-1 'Helps with documents' yet falls short of listing several concrete actions.

2 / 3

Completeness

It answers 'what' (an 8-article deep-dive series on one company) but provides no 'when'/trigger guidance — there is no 'Use when...' clause, which per the judging guidelines caps completeness at 2; this matches the anchor-2 'Has what, but when is missing or only implied'.

2 / 3

Trigger Term Quality

It includes relevant terms a user might say ("深度公司系列", "拆一家公司", "8 篇长文"), but these are prefixed with jargon ("AI Berkshire skill:") and metadata ("Source: skills/deep-company-series.md."), and common trigger variations are missing, matching the anchor-2 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The "8 篇长文拆一家公司" public-series niche is fairly specific, but the description by itself does not disambiguate the skill from sibling research skills (that scoping lives in the body), so it sits at the anchor-2 'somewhat specific but could still overlap with similar skills'.

2 / 3

Total

8

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
xbtlin/ai-berkshire
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.