management-deep-dive

Deep management assessment — the 'buying a stock is buying a person' layer. For a company or a named executive, evaluate integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record) and governance (equity structure, compensation, related-party deals). Outputs a weighted score across integrity / ability / capital-allocation / governance plus Duan Yongping's 3-question verdict ('would you hand this person your money for 10 years'). Use when standard research leaves management quality uncertain, or when management IS the investment thesis.

Quality

88%

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with a clear multi-step workflow and an explicit quality-gate checkpoint. Its main weakness is conciseness (editorial quotes/philosophy) and the absence of any progressive-disclosure file split for a ~185-line skill.

Suggestions

Trim the 'Design Philosophy' section and repeated motivational quotes; the 'Use when' guidance already lives in the description, so remove the duplicate to improve conciseness.

Consider moving the detailed scoring rubrics (delivery-rate thresholds, capital-allocation tables, governance tables) into a reference file referenced one level deep from SKILL.md to improve progressive disclosure.

Keep the report_audit quality gate but make its pass/fail handling explicit (e.g., what to do when verdict fails) so the workflow feedback loop is unambiguous.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic-concept explanations), but includes editorial padding — the 'Design Philosophy' section, repeated motivational quotes ('Buying a stock is buying a person'), and a 'Use when' line that duplicates the description — that could be trimmed; not every token earns its place.	2 / 3
Actionability	Gives concrete, executable guidance: named tools to call (web_search, get_sec_filings, get_stock_profile, get_financial_statements, run_swarm, write_file, report_audit), fillable tables, explicit scoring thresholds (>80%/60-80%/40-60%/<40%), weight tables (35/25/25/15), and a verdict mapping — copy-paste ready for an instruction-only skill.	3 / 3
Workflow Clarity	A clearly sequenced 9-step process (Step 1 identify people → Step 9 Save) with an explicit validation checkpoint: Step 9 runs report_audit (extract → verify → verdict) 'as a quality gate on the numbers', providing a feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all content is inline in a single ~185-line file with no signaled one-level-deep references or navigation; sections are well-organized, but content that could be split (detailed scoring tables, philosophy) is monolithic rather than appropriately distributed.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete capabilities, gives an explicit 'Use when' trigger, and occupies a distinct niche. Voice is correctly third person throughout with no first/second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions, e.g. 'evaluate integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record) and governance (equity structure, compensation, related-party deals)' and 'Outputs a weighted score ... plus Duan Yongping's 3-question verdict', matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (evaluate integrity/ability/governance, output a weighted score) and when via an explicit 'Use when standard research leaves management quality uncertain, or when management IS the investment thesis' clause.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say for this niche — 'management quality uncertain', 'management IS the investment thesis', 'named executive', 'company' — giving good coverage of natural trigger terms; it is not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (deep management/person assessment for investing) with distinct triggers unlikely to fire for unrelated skills; it would not conflict with general research or financial-statement skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/management-deep-dive/SKILL.md
Commit: 8643fcd

Reviewed: 2 days 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.