CtrlK
BlogDocsLog inGet started
Tessl Logo

commit-with-reflection

Git提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、智能提交、生成调试报告、commit with reflection。

67

Quality

82%

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

65%

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

The body is highly actionable with concrete git commands and a clear sequenced workflow, but it suffers from significant redundancy (duplicated workflow, inlined template) and references several non-existent bundle files. Destructive git steps lack verification checkpoints.

Suggestions

Remove the duplicate Detailed Workflow section or collapse it into the Quick Reference so the 4-phase flow appears once, and replace the inlined ~200-line template with a pointer to the existing assets/template-chinese.md.

Delete or actually create the referenced files that do not exist (references/report-schema.md, assets/template-feature.md, assets/template-bugfix.md, assets/template-refactor.md, scripts/validate-report.js, scripts/extract-errors.js, examples/*.md) so the References block is accurate.

Add an explicit verification checkpoint before 'git add .' and 'git commit --amend' (e.g., confirm staged files and that no unrelated changes are included) to satisfy the destructive/batch-operation validation requirement.

DimensionReasoningScore

Conciseness

Useful concrete content is padded with redundancy — the entire 4-phase workflow is presented twice (Quick Reference and Detailed Workflow) and a ~200-line report template is inlined in the body. Not a score of 1 because the material is genuinely actionable; not 3 because it could be cut substantially.

2 / 3

Actionability

Provides executable bash commands (git status/diff, mkdir -p, echo, git add, git commit), concrete file paths, a copy-paste commit-message format, and specific validation commands — fully concrete and actionable.

3 / 3

Workflow Clarity

The 4 phases are clearly sequenced and report validation exists, but the batch/destructive git operations ('git add .' and 'git commit --amend') lack explicit pre-flight verification checkpoints, which caps the score per the destructive-operation guideline.

2 / 3

Progressive Disclosure

Has sectioned structure and a References block with an index.md, but inlines content that should be separate (the template that already exists as assets/template-chinese.md) and references 7 bundle files that do not exist (report-schema.md, template-feature/bugfix/refactor.md, validate-report.js, extract-errors.js, examples/*). Not 1 because real references and navigation exist; not 3 because of broken references and inline bloat.

2 / 3

Total

9

/

12

Passed

Description

100%

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 well-crafted description that states concrete capabilities, includes natural bilingual trigger terms, and explicitly covers both 'what' and 'when' in third-person voice. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '分析开发过程中的错误、调试步骤和解决方案', '生成结构化的中文反思报告', '创建包含报告引用的Git提交' — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Clearly answers both what it does (analyze errors, generate reflection report, create commit) and when to use it via the explicit '显式请求词' trigger clause.

3 / 3

Trigger Term Quality

Provides natural trigger phrases users would actually say in both Chinese and English: '反思提交、智能提交、生成调试报告、commit with reflection', giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — Chinese debugging reflection reports combined with git commits — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (834 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

14

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-Skills
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.