CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

management-deep-dive

AI Berkshire skill: 管理层纵深研究:买股票就是买人. Source: skills/management-deep-dive.md.

Quality

66%

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/management-deep-dive/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-structured, highly actionable research workflow with explicit sequencing, concrete tooling, scoring rubrics, and output conventions. Its weaknesses are minor: validation guidance lives only in the adapter note rather than as in-flow checkpoints, and the long per-step detail could be offloaded to reference files for better progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and purposeful — tight tables with explicit headers, thresholds, and scoring weights, with investor quotes serving as method framing rather than explaining concepts Claude already knows. It matches anchor 4: efficient with minor trimmable padding (the 设计理念 rationale section and the Codex adapter meta-note); not a 5 because some framing could still be trimmed.

4 / 5

Actionability

Concrete guidance throughout: four parallel agent task assignments, evaluation tables with explicit thresholds (e.g., 兑现率 >80% = 优秀), a runnable command (`python3 tools/financial_rigor.py verify-valuation`), an output path pattern (`reports/{公司名}-management-{YYYYMMDD}.md`), and a weighted scoring rubric. It matches anchor 4 rather than 5 because WebSearch queries and agent prompts are not templated, leaving minor execution gaps.

4 / 5

Workflow Clarity

Nine explicitly sequenced steps (第一步 through 第九步) with substeps, a defined report structure, and a weighted composite score. Validation/cross-checking is required only via the adapter note ('cross-check financial data... clearly label uncertainty') rather than as in-flow checkpoints, matching anchor 4's 'clear sequence with most checkpoints present; minor validation gaps'. This is research/report work, not a destructive or batch operation, so no cap applies.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the body is well-sectioned with clear headers plus one-level-deep external pointers (`tools/financial_rigor.py`, `reports/`). It matches anchor 4 ('good structure; references mostly clear; minor organization gaps') rather than 5 because ~280 lines of per-step evaluation criteria are all inlined with no overview-to-detail split or reference files for the heavier step criteria.

4 / 5

Total

16

/

20

Passed

Description

40%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 functions as a title with provenance metadata, not as a capability description. It identifies the niche well but omits what the skill actually does and, critically, when to use it. Adding a concrete action list and an explicit 'Use when...' clause would move it into good-example territory.

Suggestions

Add a 'Use when...' clause stating the trigger conditions, e.g., 'Use when standard investment research yields an uncertain management score (★★★ or below) or when management quality is central to the investment thesis.'

Replace the topic-only label with concrete actions, e.g., 'Tracks management promises vs. delivery, scores capital allocation decisions (M&A, buybacks, dividends), audits governance and related-party transactions, and outputs a weighted management report.'

Include natural trigger keywords users would actually say, such as '管理层评估', 'CEO 诚信度', '资本配置', '公司治理', '投资研究', alongside the existing phrasing.

DimensionReasoningScore

Specificity

The description names the domain ("管理层纵深研究:买股票就是买人" — deep-dive management research) but lists no concrete actions or capabilities, matching the anchor for naming a domain with minimal/generic actions. It is not a 1 because the domain is specific rather than entirely vague, and not a 3 because no concrete actions (e.g., evaluating integrity, capital allocation, governance) are enumerated.

2 / 5

Completeness

The 'what' is only a topic label rather than a stated capability, and the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance (which alone would cap this dimension at 3). This matches the anchor for a vague 'what' with no 'when'; it is not a 3 because even the 'what' is not stated as a clear action.

2 / 5

Trigger Term Quality

It contains some relevant domain keywords ("管理层", "纵深研究", "买股票", "买人") but misses the natural phrases users would say such as "管理层评估", "CEO", "公司治理", "投资分析". This matches the 'some relevant keywords but missing common variations' anchor, falling short of anchor 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

The "AI Berkshire skill" prefix plus the niche management-evaluation framing ("买股票就是买人") gives it a clear niche with minor overlap risk against sibling investment-research skills. It is not a 5 because no distinct trigger phrases are stated to fully separate it from related research skills.

4 / 5

Total

11

/

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/management-deep-dive/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.