CtrlK
BlogDocsLog inGet started
Tessl Logo

git-commit-specification

编写 BK-CI Git 提交信息和整理提交边界时使用,例如选择 commit type、撰写 commit message、判断是否拆分提交和准备 PR 前自检。当用户要提交代码而不是讨论实现细节时优先使用。

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-organized, appropriately lean instruction-only skill that assumes Claude's competence and provides a concrete commit-type taxonomy and format template. Main gaps are minor cross-section redundancy and the absence of an explicit validation feedback loop.

Suggestions

Dedupe commit-type guidance so type selection appears authoritatively in one place rather than across '适用场景' and '快速指导'.

Add an explicit pre-commit self-check feedback loop (e.g., 'if sensitive info detected or scope not focused → fix and re-check before committing') to strengthen the workflow validation checkpoint.

Trim '延伸阅读' so it only points forward rather than restating the high-risk-Git boundary already covered in '不适用场景'.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining Git basics Claude already knows, but has minor redundancy — commit-type selection recurs in both '适用场景' and '快速指导', and '延伸阅读' restates the high-risk-Git boundary already in '不适用场景'.

4 / 5

Actionability

Provides concrete, actionable guidance: type definitions (feat=新增能力, fix=修复问题…) and a copy-paste format example 'feat: 添加流水线模板功能 #1234', though some guidance stays principle-level ('类型选择要服务于改动意图,不要机械套用').

4 / 5

Workflow Clarity

The numbered '快速指导' gives a clear sequence and includes an explicit self-check checkpoint (item 5: 改动范围是否聚焦、是否包含敏感信息、是否通过必要验证), but lacks an explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized into clear, well-signaled sections (适用场景/不适用场景/快速指导/高信号规则/关键陷阱/延伸阅读), matching the simple-skill exception for a 5.

5 / 5

Total

17

/

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, well-scoped description that states concrete capabilities, gives an explicit use-trigger with negative boundary guidance, and uses natural bilingual trigger terms. Only minor weakness is trigger-term breadth not reaching full synonym comprehensiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '选择 commit type、撰写 commit message、判断是否拆分提交和准备 PR 前自检' — giving comprehensive coverage of the commit-specification domain, matching the 'multiple specific concrete actions' anchor.

5 / 5

Completeness

Explicitly answers 'what' ('编写 BK-CI Git 提交信息和整理提交边界') and 'when' with a concrete trigger clause ('当用户要提交代码而不是讨论实现细节时优先使用'), satisfying both halves with trigger phrases.

5 / 5

Trigger Term Quality

Contains natural user-facing terms (commit message, commit type, 提交代码, PR, 拆分提交) plus bilingual synonyms, but coverage is not exhaustive enough for the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear BK-CI Git-commit niche with distinct triggers and explicit negative boundary guidance ('不是讨论实现细节', excludes high-risk Git operations), minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TencentBlueKing/bk-ci
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.