CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

80%

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 ./agent/src/skills/management-deep-dive/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable management-assessment workflow with concrete tool calls and a validation gate. The main weakness is conciseness — the philosophy/epigraph padding could be trimmed — and validation is concentrated at the end rather than staged throughout.

Suggestions

Trim the Design Philosophy section and repeated epigraph quotes; keep one framing quote and move Buffett/Li Lu rationale into the relevant steps to reduce padding Claude already understands.

Add per-stage validation checkpoints (e.g. after Step 3 and Step 4) rather than a single end-of-process `report_audit` gate, with a brief fix-and-retry loop on validation failure.

Make guidance-level steps more executable by providing example search queries or templates for steps like 'Search for major crises' and stakeholder-treatment analysis.

DimensionReasoningScore

Conciseness

The bulk is efficient structured tables and concrete guidance, but the Design Philosophy section and repeated epigraph quotes (Duan Yongping, Buffett) add motivational padding Claude does not need; more than minor tightening is possible.

3 / 5

Actionability

Provides concrete, named tool calls throughout (`web_search`, `get_sec_filings`, `financial_rigor command=verify_valuation`, `write_file`) plus specific scoring bands and weighted tables, but some steps remain guidance-level without exact query templates (e.g. 'Search for major crises... analyze management's response').

4 / 5

Workflow Clarity

A clearly sequenced 9-step process with an explicit final validation gate (`report_audit` extract → verify → verdict as a quality gate), though validation is a single end-of-process gate rather than per-stage checkpoints and the error-recovery loop is not detailed.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (9 steps, tables, Key Principles) with no nested or buried references, and no external bundle files are needed; structure is good though the single document is fairly long.

4 / 5

Total

15

/

20

Passed

Description

92%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.

A strong, specific description that clearly conveys a unique management-assessment niche with concrete capabilities and an explicit use-when clause. Keyword coverage could be broadened with common synonyms like 'CEO' or 'leadership'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three domains — integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record), and governance (equity structure, compensation, related-party deals) — plus a weighted-score output and Duan Yongping's 3-question verdict, giving comprehensive coverage.

5 / 5

Completeness

Clearly answers both 'what' (evaluate integrity/ability/governance, output a weighted score and 3-question verdict) and 'when' ('Use when standard research leaves management quality uncertain, or when management IS the investment thesis') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes explicit, natural trigger phrases ('management quality uncertain', 'management IS the investment thesis'), but lacks common synonyms a user might naturally say such as 'CEO', 'leadership', 'executive', or 'board', leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — deep management/character assessment framed as 'buying a stock is buying a person' — with distinct triggers unlikely to fire for general research skills, giving minimal conflict risk.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
HKUDS/Vibe-Trading
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.