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。

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 ./bundled/skills/commit-with-reflection/SKILL.md

Quality

Content

42%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 skill is richly detailed and well-sequenced but heavily padded: it duplicates its own workflow, inlines template content that already lives in assets, and references many bundle files that do not exist. Conciseness and verification integrity are the main weaknesses.

Suggestions

Remove the duplicated '工作流详解' section (keep only the Quick Reference workflow) and replace the inlined 10-section template with a pointer to assets/template-chinese.md, cutting hundreds of lines.

Create or remove the missing bundle files (validate-report.js, extract-errors.js, template-feature/bugfix/refactor.md, references/report-schema.md, examples/*) so every referenced path resolves.

Add an explicit validation checkpoint before staging/amending (e.g. run validate-report.js and only proceed on pass) to satisfy the destructive-operations requirement for workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~830-line body inlines a full 10-section report template, JS pseudocode, and a duplicated workflow (Quick Reference vs 工作流详解 repeat the same four phases), plus padded sections (Unified Template Integration, ToolSearch) that overlap content already covered.	2 / 5
Actionability	Provides concrete git commands, file paths, a commit-message template and validation commands, but several referenced scripts and templates (validate-report.js, extract-errors.js, template-feature.md, examples/*) do not exist in the bundle, and the JS logic blocks are illustrative pseudocode rather than executed code.	3 / 5
Workflow Clarity	Four phases are clearly sequenced, but destructive/batch Git operations (git add ., git commit --amend) lack real validation checkpoints — the cited validate-report.js script is missing — so per the destructive-operations cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	A real bundle exists (references/index.md, error-taxonomy.md, best-practices.md, assets/template-chinese.md, scripts/update-index.js), but the body inlines the full report template instead of pointing to assets and lists several non-existent files (report-schema.md, template-feature/bugfix/refactor.md, validate-report.js, extract-errors.js, examples/*), leaving references partly broken and structure muddled.	3 / 5
	Total	11 / 20 Passed

Description

78%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 specific, well-targeted description with strong trigger phrases and clear distinctiveness. It could be tightened into a cleaner 'Use when...' clause and add a few more natural variations to reach the top anchors.

Suggestions

Convert the trigger guidance into an explicit 'Use when... 反思提交 / commit with reflection / 完成多次调试迭代后...' clause separate from the capability sentence.

Add a couple more natural trigger synonyms (e.g. '调试总结提交', 'reflection report commit') and any relevant format/file cues.

Tighten to a single concise sentence for 'what' before the 'Use when' clause to reduce padding.

Dimension	Reasoning	Score
Specificity	Names several 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' — but does not mention index updates or type-detection logic, leaving minor coverage gaps.	4 / 5
Completeness	Both 'what' (Git提交与反思报告生成技能) and 'when' ('用于...', '显式请求词:...') are present and concrete, but the 'when' is bundled into a '用于/显式请求词' clause rather than a clean standalone 'Use when...' statement.	4 / 5
Trigger Term Quality	Explicit natural trigger phrases ('反思提交', '智能提交', '生成调试报告', 'commit with reflection', 'reflective commit') including bilingual synonyms, but missing common variations and format cues.	4 / 5
Distinctiveness Conflict Risk	Clear niche (reflective Chinese debug-report commits) with distinctive triggers ('反思提交', 'commit with reflection') and minimal overlap risk with generic commit-message skills.	5 / 5
	Total	17 / 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 (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
Path: bundled/skills/commit-with-reflection/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.