code-changelog

AI가 만든 모든 코드 변경사항을 reviews 폴더에 기록하고 간단한 HTML 뷰어로 웹 브라우저에서 실시간 확인할 수 있습니다. 매 수정마다 문서가 생성되고 Python 서버로 즉시 확인 가능합니다.

Quality

22%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/code-changelog/SKILL.md

Quality

Discovery

17%

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 explains the technical mechanism (logging to reviews folder, HTML viewer, Python server) but fails to provide trigger terms users would naturally use and lacks explicit 'Use when' guidance. It's written in a feature-description style rather than a skill-selection style, making it difficult for Claude to know when to choose this skill over others.

Suggestions

Add explicit 'Use when...' clause with trigger scenarios like 'Use when user wants to review AI-generated code changes, track modifications, or view code diffs in browser'

Include natural user keywords such as 'code review', 'track changes', 'diff viewer', 'review history', '코드 리뷰', '변경 추적'

List specific concrete actions: 'Generates diff reports, creates timestamped change logs, provides side-by-side comparison views'

Dimension	Reasoning	Score
Specificity	Names domain (code review logging) and some actions (기록/record, HTML viewer, Python server), but lacks comprehensive list of specific concrete actions like 'diff generation', 'change tracking', or 'review approval'.	2 / 3
Completeness	Describes what it does (records AI code changes to reviews folder with HTML viewer) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Uses technical terms like 'reviews 폴더', 'HTML 뷰어', 'Python 서버' but lacks natural user keywords. Users would say 'code review', 'track changes', 'review my code' - none of these trigger terms are present.	1 / 3
Distinctiveness Conflict Risk	Somewhat specific to AI code change logging with HTML viewer, but 'AI가 만든 코드 변경사항' could overlap with general code review, git diff, or documentation skills without clear boundaries.	2 / 3
	Total	6 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, repeating the same information (server commands, save_and_build usage, port configuration) multiple times throughout the document. While it provides some executable code examples, the core implementation files are not included. The document would benefit from being reduced to about 20% of its current size by eliminating redundancy and assuming Claude's competence.

Suggestions

Reduce content by 80% - remove all repeated sections (server commands appear 5+ times, usage examples are duplicated across multiple scenarios)

Include the actual code_changelog_tracker.py implementation or clearly reference where it exists, rather than saying 'already generated'

Remove marketing language (emojis, feature bullets, comparison tables) that don't help Claude execute the task

Consolidate into a single Quick Start section with one complete example, then reference external files for edge cases and troubleshooting

Dimension	Reasoning	Score
Conciseness	Extremely verbose with excessive repetition. The same concepts (server startup, save_and_build, port commands) are repeated 5+ times. Contains unnecessary marketing language (emojis, '⭐ NEW!'), feature lists that Claude doesn't need, and a comparison table that adds no actionable value.	1 / 3
Actionability	Provides concrete Python code examples and bash commands that are executable. However, the actual implementation code (code_changelog_tracker.py, index.html) is not provided - it just says 'already generated file' or 'automatically generated'. The core functionality is referenced but not shown.	2 / 3
Workflow Clarity	Steps are listed (1. setup, 2. use logger, 3. run server) but there's no validation or error recovery for the main workflow. The troubleshooting section exists but is separate from the workflow. No explicit checkpoints for verifying the logger is working correctly before proceeding.	2 / 3
Progressive Disclosure	Monolithic wall of text with massive repetition. The same information (server commands, usage examples, port configuration) appears in multiple sections. No references to external files for detailed content. Everything is dumped into one long document with poor organization despite having many headers.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: bear2u/my-skills
Commit: 1be5394

Reviewed: 18 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.