一键导入
skill-evolution-manager
专门用于在对话结束时,根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的"精华"(如成功的解决方案、失败的教训、特定的代码规范)来持续演进 Skills 库。
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
专门用于在对话结束时,根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的"精华"(如成功的解决方案、失败的教训、特定的代码规范)来持续演进 Skills 库。
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
Install and maintain the upstream Frontend Slides skill from GitHub so agents can create high-quality HTML slide decks and convert PPTX content.
Lifecycle manager for GitHub-based skills. Use this to batch scan your skills directory, check for updates on GitHub, and perform guided upgrades of your skill wrappers.
Generate a static function and method call graph for a Python repository. Use this skill when the user wants a Python call graph, function dependency map, Mermaid call diagram, or static call-chain analysis from a local repo.
Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
GitHub仓库提交管理技能,用于检查、验证和提交代码到GitHub仓库。当用户需要提交代码到GitHub时使用此技能,包括:1) 检查当前Git仓库状态和远程链接,2) 验证或更新GitHub远程仓库链接,3) 审核代码更改并生成提交消息,4) 创建提交并可选推送到远程仓库。特别适用于需要确保正确提交到指定GitHub仓库的场景。
| name | skill-evolution-manager |
| description | 专门用于在对话结束时,根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的"精华"(如成功的解决方案、失败的教训、特定的代码规范)来持续演进 Skills 库。 |
| license | MIT |
这是整个 AI 技能系统的"进化中枢"。它不仅负责优化单个 Skill,还负责跨 Skill 的经验复盘和沉淀。
evolution.json)。SKILL.md,确保持久化且不被版本更新覆盖。Trigger:
/evolve当用户触发复盘时,Agent 必须执行:
yt-dlp 或 baoyu-comic)。{
"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"
}
Agent 调用 scripts/merge_evolution.py,将上述 JSON 增量写入目标 Skill 的 evolution.json 文件中。
python skill-evolution-manager/scripts/merge_evolution.py <skill_path> <json_string> [--json]Agent 调用 scripts/smart_stitch.py,将 evolution.json 的内容转化为 Markdown 并追加到 SKILL.md 末尾。
python skill-evolution-manager/scripts/smart_stitch.py <skill_path> [--json]当 skill-manager 更新了某个 Skill 后,Agent 应主动运行 smart_stitch.py,将之前保存的经验"重新缝合"到新版文档中。
scripts/merge_evolution.py: 增量合并工具。负责读取旧 JSON,去重合并新 List,保存。scripts/smart_stitch.py: 文档生成工具。负责读取 JSON,在 SKILL.md 末尾生成或更新 ## User-Learned Best Practices & Constraints 章节。scripts/align_all.py: 全量对齐工具。一键遍历技能根目录(默认自动推断为当前仓库根目录)并缝合所有存在 evolution.json 的技能。python skill-evolution-manager/scripts/merge_evolution.py <skill_path> <json_string> [--json]python skill-evolution-manager/scripts/smart_stitch.py <skill_path> [--json]python skill-evolution-manager/scripts/align_all.py [skills_root] [--json]退出码约定:
0: 成功1: 运行时错误2: 参数错误evolution.json 通道进行,这样可以保证在 Skill 升级时经验不丢失。# 记录用户对github-commit技能的偏好
python skill-evolution-manager/scripts/merge_evolution.py github-commit '{
"preferences": ["提交前总是检查git状态", "使用语义化版本提交消息"],
"fixes": ["修复子模块处理问题"],
"custom_prompts": "在提交前运行git status和git diff确认更改"
}'
# 将经验缝合到技能文档
python skill-evolution-manager/scripts/smart_stitch.py github-commit
# 记录paper-detailed-analysis技能的经验
python skill-evolution-manager/scripts/merge_evolution.py paper-detailed-analysis '{
"preferences": ["优先分析论文的方法论部分", "提取关键算法伪代码"],
"fixes": ["修复PDF解析中的编码问题"],
"custom_prompts": "为每篇论文生成执行摘要和技术要点"
}'
# 记录humanizer技能的经验
python skill-evolution-manager/scripts/merge_evolution.py humanizer '{
"preferences": ["保留专业术语", "调整语气为学术风格"],
"fixes": ["修复过度人性化导致的语义丢失"],
"custom_prompts": "针对学术文本使用更保守的人性化策略"
}'
# 批量缝合所有技能的经验
python skill-evolution-manager/scripts/align_all.py .
# 当skill-manager更新技能后,恢复进化数据
python skill-manager/scripts/scan_and_check.py .
python skill-evolution-manager/scripts/align_all.py .
# 验证经验恢复结果
grep -r "User-Learned" . --include="SKILL.md"
# 与skill-manager协同
python skill-manager/scripts/scan_and_check.py .
python skill-evolution-manager/scripts/align_all.py .
# 与update-readme协同
python scripts/align_all.py
python update-readme/scripts/analyze_project.py .
# 与github-commit协同
python skill-evolution-manager/scripts/merge_evolution.py github-commit '{"preferences": ["自动生成有意义的提交消息"]}'
python skill-evolution-manager/scripts/smart_stitch.py github-commit
python github-commit/scripts/create_commit.py . "feat: 添加技能进化经验"
# 查看特定技能的进化数据
cat github-commit/evolution.json | python -m json.tool
# 查看所有技能的进化章节
find . -name "SKILL.md" -exec grep -l "User-Learned" {} \;
# 统计进化数据
find . -name "evolution.json" | wc -l
This skill is used when its description in frontmatter matches the user request. Prefer existing scripts under scripts/ over ad-hoc rewrites.
scripts/: executable helpers for deterministic stepsreferences/: additional docs loaded on demandassets/: templates or static files used by the skilldescription