CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deep-company-series

AI Berkshire skill: 看懂XX公司(深度公司系列):3-8 篇长文拆一家公司. Source: skills/deep-company-series.md.

Quality

69%

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

70%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.

A dense, highly actionable editorial workflow with genuinely strong sequencing and validation (the fact-check checklist, revision triage, and pre-push scans are its core IP and are well specified). The main weaknesses are inlined content that belongs in separate reference files, references to artifacts that don't exist in the bundle, and cross-section redundancy that inflates token cost.

Suggestions

Move stable, reusable material — the 8-axis article template table, the per-article skeleton table, and the style/banned-word rules — into references/ files (e.g. references/templates.md, references/style-rules.md) and keep SKILL.md as a workflow overview with clearly signaled one-level-deep links.

Deduplicate the probability-weighting prohibition (stated in section 四, re-stated in section 七, and again in the closing summary) and the article-count guidance (repeated across sections 一 and 二) into a single authoritative statement.

Remove or fix dangling references to artifacts absent from the bundle (`reports/腾讯/《看懂腾讯》/`, `tools/financial_rigor.py`, `skills/deep-company-series.md`), since the workflow directs the agent to consult them.

DimensionReasoningScore

Conciseness

Mostly efficient: the content is domain-specific editorial standards Claude would not know (banned-word tables, pseudo-precision traps, revision triage), with no explaining of concepts Claude already knows. But there is noticeable redundancy — the no-probability-weighting rule appears in section 四, again in section 七, and again in the closing summary; the article-count rule is stated in both section 一 and 二; and the 'Codex adapter note' block is harness meta-commentary rather than skill content. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened', not the level-4 'minor instances'.

3 / 5

Actionability

Largely concrete and executable: exact storage paths (`reports/{公司名}/《看懂{公司名}》/0X-XX.md`), a dated-suffix directory-conflict rule, a runnable privacy grep with patterns, a git sequence, a 7-item revision checklist with literal grep strings, and named known-error examples (Riot 33x not 58x, Tencent–Meituan 1.5% not 6.4%). It falls short of 5 because several referenced artifacts do not exist in the bundle — the sample `reports/腾讯/《看懂腾讯》/`, `tools/financial_rigor.py`, and `skills/deep-company-series.md` — so parts of the guidance cannot actually be executed as written.

4 / 5

Workflow Clarity

The multi-phase process is clearly sequenced (调研 → 写作 → 跨篇一致性扫描 → 发布前最终核查) with explicit validation checkpoints: a 7-box checklist before revision sign-off, a dedicated cross-article consistency scan, a pre-push privacy grep, and 'only after confirmation, git push'. The revision-handling flow adds feedback loops (fact-check first, triage by error level, linked-update checks after each fix), matching 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists'.

5 / 5

Progressive Disclosure

The body is well-sectioned, but no bundle files exist (no references/, scripts/, or assets/), and everything — the 8-article template table, per-article skeletons, style rules, fact-check standards — is inlined in one ~260-line file where some of it (templates, checklists) clearly belongs in separate reference files. The references it does point to (`reports/腾讯/`, `tools/financial_rigor.py`) are not part of the bundle, so navigation to them fails. This fits 'some structure but could be better organized; content that should be separate is inline' rather than level 4.

3 / 5

Total

15

/

20

Passed

Description

53%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 communicates a specific niche deliverable but reads more like a title plus file metadata than a skill description. It lacks any 'when to use' trigger guidance, contains meta-clutter ('AI Berkshire skill:', 'Source: ...') that crowds out actionable keywords, and misses common trigger synonyms. Triggerability and completeness are the main weaknesses.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a multi-part deep-dive series on a company (看懂X / 深度拆解 / 系列长文), not for single-report or industry research.'

Remove meta-clutter ('AI Berkshire skill:', 'Source: skills/deep-company-series.md.') — it wastes description budget and adds no capability or trigger information.

Broaden natural trigger terms with synonyms users actually say: 深度公司分析, 财报拆解, 公司研究系列, 公众号长文, alongside the existing 看懂XX公司.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action — "3-8 篇长文拆一家公司" (write a 3-8 part long-form series breaking down one company) — matching 'names domain and 1-2 concrete actions, but not comprehensive'. It is more informative than the level-2 anchor ('Processes PDF files'), but the trailing meta-clutter ('AI Berkshire skill:', 'Source: skills/deep-company-series.md.') pads it without adding capability, and the action list is not comprehensive, so it does not reach 4.

3 / 5

Completeness

The 'what' is clear (a 3-8 article deep-dive series on one company) but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not level 2 because the 'what' is specific, not vague; not level 4 because no usage condition is stated or implied.

3 / 5

Trigger Term Quality

Relevant natural phrases are present — "看懂XX公司" and "深度公司系列" are what a Chinese-speaking user would plausibly say — but coverage is thin: no synonyms, no variations like 深度分析/公司研究/财报拆解, and no English triggers. This fits 'some relevant keywords but missing common variations or synonyms' rather than the level-4 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"看懂XX公司(深度公司系列):3-8 篇长文拆一家公司" carves out a clear niche (multi-part public long-form company series) with a distinct name, so conflict risk is low — 'mostly distinct; minor overlap risk'. It does not reach 5 because the description itself gives no boundary against adjacent research skills (the body's '/investment-research' / '/industry-research' distinction is not surfaced here), leaving minor overlap with general company-research requests.

4 / 5

Total

13

/

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/deep-company-series/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.