skill-evolution-manager

Skill Evolution Manager

This is the "evolution hub" of the entire AI skill system. It is responsible not only for optimizing individual Skills, but also for cross-Skill experience review and consolidation.

Core Responsibilities

1. Session Review: At the end of a conversation, analyze the performance of all Skills that were invoked.
2. Experience Extraction: Convert unstructured user feedback into structured JSON data (evolution.json）。
3. Smart Stitching: Automatically write the consolidated experience into SKILL.md, ensuring persistence and preventing it from being overwritten by version updates.

Use Cases

Trigger:

• /evolve
• "Review the conversation just now"
• "I think that tool just now wasn't very easy to use, make a note of it"
• "Save this experience to the Skill"

Workflow (The Evolution Workflow)

1. Review & Extract

When the user triggers a review, the Agent must perform:

1. Scan Context: Identify points the user was dissatisfied with (errors, wrong style, incorrect parameters) or satisfied with (a specific Prompt worked well).
2. Locate Skill: Determine which Skill needs to evolve (e.g., yt-dlp or baoyu-comic）。
3. Generate JSON: Build the following JSON structure in memory:

   {
     "preferences": ["用户希望下载默认静音"],
     "fixes": ["Windows 下 ffmpeg 路径需转义"],
     "custom_prompts": "在执行前总是先打印预估耗时"
   }
   

2. Persist Experience

The Agent calls scripts/merge_evolution.py, writing the above JSON incrementally into the target Skill's evolution.json file.

• Command: python scripts/merge_evolution.py <skill_path> <json_string>

3. Stitch Documentation

The Agent calls scripts/smart_stitch.py, converting the content of evolution.json into Markdown and appending it to the end of SKILL.md .

• Command: python scripts/smart_stitch.py <skill_path>

4. Align Across Versions

When skill-manager has updated a certain Skill, the Agent should proactively run smart_stitch.pyto "re-stitch" the previously saved experience into the new version of the documentation.

Core Scripts

• scripts/merge_evolution.py: Incremental Merge Tool. Responsible for reading the old JSON, deduplicating and merging the new List, and saving.
• scripts/smart_stitch.py: Documentation Generation Tool. Responsible for reading the JSON and generating or updating the SKILL.md section at the end of ## User-Learned Best Practices & Constraints .
• scripts/align_all.py: Full Alignment Tool. With one click, traverse all Skill folders and re-stitch the existing evolution.json experience back into the corresponding SKILL.md. Commonly used for skill-manager experience restoration after batch updates.

Best Practices

• Do not directly modify the body of SKILL.md: Unless it is an obvious spelling error. All experience corrections should go through the evolution.json channel, so that experience is not lost when the Skill is upgraded.
• Multi-Skill Collaboration: If a single conversation involves multiple Skills, execute the above process for each Skill in turn.