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

60%

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 ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/credit-analysis/SKILL.md

The canonical home for this skill is credit-analysis in HKUDS/Vibe-Trading

Quality

Content

46%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 thorough, well-organized reference with strong, executable code templates and detailed domain coverage. It is held back by significant verbosity explaining standard fixed-income concepts Claude already knows and by a monolithic structure with no progressive disclosure into bundle files.

Suggestions

Trim or move into separate reference files the explanatory material on concepts Claude already knows (duration/convexity definitions, rating-scale primers, market-structure tables) so SKILL.md stays a lean overview.

Split the bulk reference content (rating-mapping tables, China market structure, full Python template library) into references/ files and link to them one level deep, leaving quick-start guidance inline.

Add explicit validation/verification checkpoints (e.g. 'verify solver converged', 'sanity-check spread against rating band') to the multi-step analytical workflows in §6 to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~1100-line body extensively explains concepts Claude already knows — definitions of Macaulay/modified duration, convexity, what bond ratings mean, the structure of the interbank vs exchange market — padded well beyond what a lean reference requires, even if individually accurate.	2 / 5
Actionability	Provides multiple complete, executable Python functions (bond_price, ytm_solve, macaulay_duration, nelson_siegel/svensson fitting, altman_z_score, merton_model) with docstrings and worked examples; minor gaps such as untested solver convergence handling keep it just below fully copy-paste-robust.	4 / 5
Workflow Clarity	Numbered procedures appear in §6.2/§6.3 (一级/二级市场分析, 底层信用评估步骤) and KMV/评分卡建模流程, but there are no explicit validation checkpoints or fix→retry feedback loops for these analytical/risky-assessment steps, which the cap guidance treats as a 3-level ceiling.	3 / 5
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files (references/scripts/assets absent) and no one-level-deep file references; the large reference material (rating tables, market structure, code templates) that clearly belongs in separate files is all inlined, with only cross-links to other skills rather than to detail files.	2 / 5
	Total	11 / 20 Passed

Description

58%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 third-person, names a clear niche, and enumerates several concrete capability areas, giving it solid specificity and distinctiveness. Its main weakness is the absence of any explicit 'Use when...' trigger guidance and limited natural user-facing trigger terms.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke the skill (e.g. '当用户提到债券定价、信用评级、利差、城投债、违约风险时使用').

Broaden trigger terms to include common user phrasings and synonyms such as '债券', 'YTM/到期收益率', '久期', '违约' alongside the current domain terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('固收与信用分析') and lists several concrete capabilities — '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' — but each is a single-word action area rather than the fully spelled-out concrete actions a 5 would list.	4 / 5
Completeness	It clearly states 'what' the skill does (the colon-separated capability list), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is entirely missing, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like '信用债评级', '利差分析', '城投债' are relevant domain keywords a specialist might say, but common user-facing variations (e.g. '债券', 'YTM', '违约') and any file extensions are absent, and the phrasing leans technical rather than the natural trigger phrases users say.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct — '固收与信用分析' with city-investment-bond (城投) and convertible-bond specifics — and unlikely to trigger for unrelated skills; minor overlap risk only with closely related finance skills.	4 / 5
	Total	14 / 20 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: charliedream1/ai_quant_trade
Path: a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/credit-analysis/SKILL.md
Commit: b612402

Reviewed: 3 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.