agentleFS
Sign inStart free
TashanGKDTashanGKD/cc_plugins/.claude/skills/archive-skill/SKILL.md

archive-skill

Skill4 starsChanged 10 months agoMITView on GitHub

对话归档技能。将当前对话流程提取并生成可重用的 skill 文件。

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. lelborn/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

/archive-skill - 对话归档

将成功对话转化为可复用技能

分析当前对话，识别模式，生成可重用的 skill 文件。

核心分析流程

阶段 1：对话结构分析

识别对话模式

特征维度简单流程迭代协作
工具数量1-23-53+5+
执行顺序线性顺序循环并行/嵌套
重复模式无无有可能
Skill 调用无无无有
决策节点0-12-31-23+

判断逻辑：

IF 调用其他 skills/agents THEN 协作模式
ELIF 包含重复循环 THEN 迭代模式
ELIF 工具调用 >= 3 THEN 流程模式
ELSE 简单模式

提取关键信息

决策节点关键词：

  • 条件判断：if, 是否, 是否需要
  • 选项选择：选择 A/B, 方案 1/2
  • 验证检查：检查, 验证, 确认
  • 错误处理：失败, 错误, 异常

变量识别规则：

变量来源识别规则参数化
用户输入用户明确提供的值{{user_input}}
文件路径文件操作中的路径{{file_path}}
项目名仓库名/项目名{{project_name}}
函数/类名代码标识符{{function_name}}
数值数字、计数{{count}}
配置项配置文件内容{{config}}

阶段 2：抽象化处理

通用化规则

保留去除示例
工具名称具体参数值Read() → Read({{file_path}})
步骤顺序用户特定内容编辑 src/auth.py → 编辑 {{file_path}}
条件判断项目路径/home/user/project → {{project_path}}
输出格式时间戳2025-01-15 → (删除)

模板选择

模式模板文件提取重点
简单templates/simple.md核心步骤、主要工具
流程templates/workflow.md步骤序列、依赖关系、输出文件
迭代templates/iterative.md循环阶段、验证条件、退出条件
协作templates/workflow.md调用的 skills/agents、编排方式

阶段 3：生成输出

信息推断

缺失项推断规则
skill 名称从对话主题提取，如 "TDD 开发" → "tdd-workflow"
描述总结对话目的
使用场景从对话初始问题提取
工具依赖从实际调用的工具提取

输出路径

# 默认
.claude/skills/{{skill_name}}/SKILL.md

# 用户指定
/archive-skill --output ./my-skills/

质量检查

生成后验证：

  • frontmatter 完整（name, description, user-invocable）
  • 所有 {{变量}} 都有说明
  • 工具依赖表与实际使用一致
  • 步骤顺序与原对话一致
  • 代码示例可运行（如果有）

使用方式

/archive-skill                          # 自动分析并生成
/archive-skill --name my-workflow       # 指定 skill 名称
/archive-skill --output ./skills/       # 指定输出目录
/archive-skill --template workflow      # 指定模板类型
/archive-skill --interactive            # 交互式确认

一次成功对话，永久可用技能

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free