financial-statement

财报三表深度解读——三表勾稽关系、盈利质量(应计vs现金流)分析、杜邦分解、10+财务造假红旗指标

Quality

66%

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/financial-statement/SKILL.md

Quality

Content

50%

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

The body is well-structured and rich with concrete tables, formulas, and templates, but it is a monolithic 263-line reference with no progressive disclosure and code snippets that are formula illustrations rather than fully executable pipelines. Splitting reference material into bundled files and adding an explicit validation workflow would lift the weaker dimensions.

Suggestions

Move dense reference material (the 12 red-flag table, industry ROE benchmarks, earnings-quality scorecard, output template) into referenced files under references/ and link to them one level deep from SKILL.md.

Turn the verification snippets into an explicit sequenced workflow with validation checkpoints (e.g. compute accrual_ratio → if >10% flag earnings quality → then proceed), including how to fetch the underlying data.

Trim basic accounting glosses ('资产 = 负债 + 所有者权益', parenthetical '赚了多少' captions) that Claude already knows, and provide executable Python that loads real fields (e.g. via tushare) rather than undefined-variable formulas.

Dimension	Reasoning	Score
Conciseness	Mostly efficient via tables and compact formulas, but includes basic accounting glosses Claude already knows ('资产 = 负债 + 所有者权益', '利润表（赚了多少）') and a 263-line body that could be tightened.	2 / 3
Actionability	Provides concrete verification formulas, scoring thresholds, and templates, but the Python snippets use undefined variables with no data-fetching code, falling short of copy-paste executable guidance.	2 / 3
Workflow Clarity	A logical topical sequence exists and an output template is given, but verification appears as isolated snippets rather than an explicit validate→fix→retry workflow with checkpoints.	2 / 3
Progressive Disclosure	Well-organized by sections but monolithic — no bundle files exist and substantial reference material (12-flag table, industry ROE table, scoring rubric, output template) is all inline rather than split into one-level-deep references.	2 / 3
	Total	8 / 12 Passed

Description

82%

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 specific, distinctive description naming concrete capabilities and natural trigger terms, but it omits an explicit 'Use when...' trigger clause, capping completeness at 2. Adding usage-trigger guidance would round it out.

Suggestions

Append an explicit trigger clause, e.g. 'Use when interpreting financial statements, checking three-statement consistency, assessing earnings quality, or screening for financial fraud red flags.'

Add the data source context to the description (e.g. A-share financials via tushare) so users know the applicable market.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities: '三表勾稽关系', '盈利质量(应计vs现金流)分析', '杜邦分解', and '10+财务造假红旗指标', matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes natural terms users would actually say — '财报三表', '杜邦分解', '财务造假红旗指标' — with good coverage across the financial-analysis domain.	3 / 3
Distinctiveness Conflict Risk	The niche — financial-statement cross-checking, DuPont decomposition, and fraud red-flag detection — is specific and clearly distinguishable from generic analysis skills, and uses third-person voice.	3 / 3
	Total	11 / 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/financial-statement/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.