credit-analysis

固收与信用分析：信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。

Quality

73%

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/credit-analysis/SKILL.md

Quality

Content

65%

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

A thorough, well-organized and highly actionable fixed-income/credit reference with strong executable code, but it is a monolithic 35KB document that explains concepts Claude already knows and lacks validation feedback loops in its workflows.

Suggestions

Split the Python code templates (Section 5) and the China market-structure/quick-reference material (Sections 6 and 8) into separate reference files and link them one level deep from a leaner SKILL.md overview to improve progressive disclosure.

Trim conceptual explanations of standard finance definitions (YTM, duration, convexity, the rating scale) that Claude already knows, keeping only China-specific and non-obvious material to improve conciseness.

Add explicit validate→fix→retry checkpoints to the multi-step analytical workflows (e.g. 评分卡建模, 城投一级市场分析) so workflow clarity can reach 3.

Dimension	Reasoning	Score
Conciseness	The ~1130-line body devotes substantial prose to standard finance concepts Claude already knows (what YTM, modified duration, convexity and the S&P/Moody's rating scale are), though the China-specific material and code templates genuinely earn their place.	2 / 3
Actionability	Section 5 supplies complete, executable, copy-paste-ready Python (bond pricing, YTM solver, duration/convexity, Nelson-Siegel/Svensson, Altman Z-Score, Merton) and the analytical sections give concrete thresholds (e.g. '货币资金/短期债务 < 0.3') and named data sources.	3 / 3
Workflow Clarity	Several processes are clearly sequenced (城投债一级/二级市场分析, 违约事后分析, 评分卡建模) but none include explicit validation checkpoints or validate→fix→retry feedback loops.	2 / 3
Progressive Disclosure	No bundle files exist and all content sits in one monolithic 35KB SKILL.md; sections are well-organized, but the code templates and market-structure reference are large inline blocks that should be split into separate files.	2 / 3
	Total	9 / 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 concise, specific Chinese-language description that names several concrete fixed-income/credit capabilities and uses natural trigger terms. Its only real gap is the missing explicit 'Use when…' usage trigger, which caps the completeness dimension.

Suggestions

Append an explicit usage trigger, e.g. '当用户提到固收、信用债、利差、城投债、可转债定价或违约风险时使用本 skill' to lift completeness to 3.

Lead with a third-person verb phrase (e.g. '分析固收与信用债…') to match the rubric's verb-led voice convention.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — '信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略' — naming specific fixed-income/credit actions rather than vague abstractions.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Natural domain terms a Chinese fixed-income user would actually say — '固收与信用分析', '利差', '城投债', '可转债', '违约风险' — with good coverage of the standard vocabulary.	3 / 3
Distinctiveness Conflict Risk	The '固收与信用分析' framing plus China-specific terms (城投债, 信用债, 可转债定价) carve a clear niche unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1132 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/credit-analysis/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.