← Back to Skills Marketplace
beachanger

协作造技师

by BeAChanger · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
163
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install collab-to-skill
Description
将“人类 + Agent”共同打磨出来的流程、决策与方法,提炼成可复用的 Skill。适用于把高质量协作过程从聊天/项目推进中抽取出来,沉淀为可分发的技能包。
README (SKILL.md)

协作造技师

用途

这只 skill 用来把“共同打磨出来的能力”变成 skill。

它处理的不是单个 Agent 独立完成的能力, 而是以下这类协作产物:

  • 人类先给方向、判断、反证与修正
  • Agent 负责结构化、收敛、打包与落地
  • 双方来回迭代后,形成一套稳定流程

这类能力如果不提炼,通常会散落在聊天记录里。 本 skill 的目标,就是把它们提纯成可复用、可发布、可迭代的 skill。


什么时候用

当你发现以下情况时,优先触发:

  • 一个有价值的方法不是单边生成的,而是共同磨出来的
  • 聊天过程中出现了多个关键决策点、边界修正、流程补全
  • 你想把“这次是怎么做出来的”沉淀为下一次可直接复用的 skill
  • 想验证:某个能力仅靠 skill 是否足够成立

核心原则

  1. 协作过程本身就是资产
  2. 关键决策点比表面流程更值钱
  3. 先抽“为什么成立”,再抽“怎么执行”
  4. 能拆成独立 skill 就不要都塞进一个母 skill
  5. Less is more:单一 skill 只承载一类清晰能力

标准流程

第 1 步:识别协作成果

先确认本次成果是不是协作磨出来的,而不是普通对话输出。

第 2 步:抽关键决策点

优先抽:

  • 中途新增了什么关键步骤
  • 为什么要加
  • 如果不加会怎样
  • 这是否具备跨项目复用价值

第 3 步:提炼方法论骨架

把协作过程压缩成:

  • 输入
  • 关键判断
  • 核心步骤
  • 输出
  • 边界

第 4 步:判断独立成 skill 还是并入母 skill

如果它是独立能力,就拆成单独 skill。 如果只是母流程的一小段,就并入母 skill。

第 5 步:打包 skill

输出:

  • SKILL.md
  • 必要的 references/
  • 必要的 templates/

第 6 步:记忆沉淀

把“为什么这么设计”写进短期记忆;稳定后再升格长期记忆。


输出要求

至少交付:

  1. 这次协作抽出了什么能力
  2. 为什么值得 skill 化
  3. 应拆成独立 skill 还是并入母 skill
  4. skill 的边界与价值
  5. 后续如何验证它是否真的成立

不要做的事

  • 不要把完整聊天记录原样塞进 skill
  • 不要只写步骤,不写决策原因
  • 不要把多个不相干能力硬捏成一个 skill
  • 不要把“还没稳定的方法”过早包装成发布版
Usage Guidance
This skill is instruction-only and appears coherent with its stated purpose. Before using, avoid pasting raw chat logs or secrets into prompts (the SKILL.md already recommends this). Decide how your agent's memory and publishing workflow handle extracted artifacts (e.g., where SKILL.md and templates will be stored and who can access them). If you want stronger guarantees, review any generated SKILL.md output before publishing or adding it to shared repositories.
Capability Analysis
Type: OpenClaw Skill Name: collab-to-skill Version: 1.0.0 The skill bundle is a meta-utility designed to help the agent extract and package collaborative workflows into new skill definitions. It contains only Markdown instructions (SKILL.md) and metadata (_meta.json), with no executable code, network activity, or evidence of malicious intent or prompt injection.
Capability Assessment
Purpose & Capability
The name/description match the SKILL.md: the skill's goal is to extract collaboration-derived processes into SKILL.md bundles. No unrelated binaries, environment variables, or credentials are requested.
Instruction Scope
SKILL.md contains procedural guidance (identify decisions, extract inputs/outputs, package SKILL.md/templates). It does not instruct the agent to read arbitrary system files, access environment variables, transmit data to external endpoints, or run code. It explicitly warns against including full chat logs.
Install Mechanism
There is no install spec and no code files. Being instruction-only means nothing will be written to disk or downloaded during installation.
Credentials
Requires no environment variables, credentials, or config paths. The guidance about memory ('short-term' vs 'long-term') is conceptual and does not imply access to additional secrets or external services.
Persistence & Privilege
always is false and disable-model-invocation is default (agent may invoke it autonomously, which is normal). The skill does not request persistent installation or modification of other skills/configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install collab-to-skill
  3. After installation, invoke the skill by name or use /collab-to-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: extract reusable skills from human + agent co-creation, collaborative decisions, and iterative workflow refinement.
Metadata
Slug collab-to-skill
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 协作造技师?

将“人类 + Agent”共同打磨出来的流程、决策与方法,提炼成可复用的 Skill。适用于把高质量协作过程从聊天/项目推进中抽取出来,沉淀为可分发的技能包。 It is an AI Agent Skill for Claude Code / OpenClaw, with 163 downloads so far.

How do I install 协作造技师?

Run "/install collab-to-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 协作造技师 free?

Yes, 协作造技师 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 协作造技师 support?

协作造技师 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 协作造技师?

It is built and maintained by BeAChanger (@beachanger); the current version is v1.0.0.

💬 Comments