valuation-model

Valuation methodology — absolute valuation with DCF / DDM / SOTP, relative valuation with PE-Band / PB-ROE / EV-EBITDA, sensitivity analysis, and valuation-trap detection.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/valuation-model/SKILL.md

Quality

Content

71%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 content is a well-structured, actionable valuation reference rich in domain-specific data Claude lacks, with a clear decision tree and validation checkpoints. Its main weakness is progressive disclosure: everything is inlined in a single file with no bundle references split out.

Suggestions

Move the bulkier reference tables (valuation-trap table, industry WACC / EV-EBITDA ranges) into separate reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Keep SKILL.md as a lean overview (method-selection decision tree, output format, key formulas) pointing one level deep to the detailed tables.

Consider adding an explicit validation/review checkpoint in the DCF workflow between assumption-setting and final output, mirroring the cross-validation step.

Dimension	Reasoning	Score
Conciseness	The body is dense, domain-specific reference material (China A-share WACC ranges, EV/EBITDA industry medians, PE-band percentiles, valuation-trap table) that Claude would not already know, with minimal padding of familiar concepts; only slightly more voluminous than a lean reference need be.	4 / 5
Actionability	Provides concrete formulas, specific reference ranges, a method-selection decision tree, and a copy-paste-ready output-format template, giving mostly executable guidance with only minor gaps (no runnable code, but formulas are the actionable unit for a methodology skill).	4 / 5
Workflow Clarity	Clear sequenced workflow with explicit checkpoints: a method-selection decision tree, a cross-validation step ('If the difference >30% -> check assumptions'), DDM applicability checklist, and valuation-trap checklist; only minor validation gaps prevent a 5.	4 / 5
Progressive Disclosure	The skill ships no bundle files and the ~260-line body inlines content that could live in separate references (full trap table, industry WACC/EBITDA ranges); section headers give some structure, but there are no external references or navigation signaling.	3 / 5
	Total	15 / 20 Passed

Description

82%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 is highly specific and trigger-rich, naming concrete valuation methods a practitioner would naturally use, with minimal conflict risk. Its main weakness is the absence of any explicit 'Use when...' trigger clause, leaving the invocation context implied.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when valuing a company, building a DCF/relative-valuation model, or screening for valuation traps.'

Optionally surface the China A-share focus and the asset-class boundary (not for crypto) so the trigger context matches the body's scope.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete valuation methods (DCF / DDM / SOTP, PE-Band / PB-ROE / EV-EBITDA) plus sensitivity analysis and valuation-trap detection, giving comprehensive coverage of the domain.	5 / 5
Completeness	Provides a clear and comprehensive 'what', but has no explicit 'Use when...' or equivalent trigger guidance telling Claude when to invoke the skill, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Uses the exact natural terms a finance practitioner would say (DCF, DDM, SOTP, PE-Band, PB-ROE, EV-EBITDA, sensitivity analysis, valuation-trap), covering synonyms and method variants comprehensively.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (corporate valuation methodology) with distinct, specialized triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 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/valuation-model/SKILL.md
Commit: 1907e47

Reviewed: 1 day 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.