agentleFS
wlkerwong-boopwlkerwong-boop/family-ai-skills/skills/skill-authoring/SKILL.md

skill-authoring

Skill0 starsChanged 2 months agoMITView on GitHub

Triggers: 做成skill/写成技能. How to author and verify skills.

89 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cloud-api-recipe-authoring, codebuddy-ide-mcp-upgrade and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TencentCloudBaseSkill

    cloud-api-recipe-authoring

    Author or revise a cloud-api-operations recipe (config/source/skills/cloud-api-operations/references/recipes/). Encodes why the long tail of control-plane capabilities is deliberately NOT wrapped as MCP/CLI tools, the API-first admission test for whether a capability deserves a recipe, the negative and positive lists, the fixed recipe structure, the writing rules distilled from writing-for-agents, the user-facing copy red lines, and the product regeneration/verification pipeline. Also routes contributors (and their agents) to the contribution flow and the pre-PR self-test protocol in references/contributing.md. Use when adding a recipe, judging whether a scenario belongs in the recipe set, updating the recipes index, re-checking existing recipes against the admission test, or onboarding someone who wants to submit one.

    Also in 3 projects that use this

  • TencentCloudBaseSkill

    codebuddy-ide-mcp-upgrade

    升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP 发版要同步什么」时使用。覆盖:解包定位内置 bundle 与内嵌配置、重新构建 mcp bundle、生成新的工具白名单与系统提示词、安全注入 IDE 并备份、用 MCP 协议验证工具清单、人工端到端验收、一键回滚。

    Also in 3 projects that use this

  • DIL8654Skill

    api-contract-review

    Review ASP.NET Core Web API contracts for HTTP semantics, versioning, backward compatibility, and response consistency. Use when the user asks to review an API, check endpoints, validate REST behavior, or before releasing contract changes.

    Also in 5 projects that use this

  • zaxbysauceSkill

    pr-review-fix

    Codex adapter for addressing pull request review feedback in opencode-swarm. Use when the user asks to fix PR review comments, requested changes, reviewer findings, CI-review notes, or a pasted review summary with low false-positive tolerance.

    Also in 3 projects that use this

  • albertdobmeyerSkill

    git-workflows

    Advanced git operations beyond add/commit/push. Use when rebasing, bisecting bugs, using worktrees for parallel development, recovering with reflog, managing subtrees/submodules, resolving merge conflicts, cherry-picking across branches, or working with monorepos.

    Also in 3 projects that use this

  • rogue-dev-studioSkill

    frontend-engineering

    Expert frontend application engineering: accessible UI structure, state and data-fetching discipline, form/validation UX, responsive layouts, performance budgets, and integration with API contracts. Use when building or refining SPA/web screens, design-system consumption, client-side routing, or fixing UI reliability (loading, empty, and error states).

    Also in 3 projects that use this

  • +6 more from TencentCloudBase

The file

Files
SKILL.md

Skill 编写规范 · 把方法论做成可触发的技能卡

一句话:在本机创建或修订技能的标准做法——frontmatter 触发词设计、正文固定骨架、单次写入 ≤~8K token(大内容拆成 SKILL.md 精华版 + references/ 全文版)、创建后必须验证注册成功。

什么时候触发

  • 用户说"把这个做成 skill""写成技能""存为技能""沉淀下来"
  • 需要把一篇文章、一套提示词、一个调试过程转化为可复用技能时
  • 技能文件写入中途超时/截断,需要按正确姿势重写时

文件解剖(SKILL.md 标准骨架)

---
name: <与目录名完全一致>
description: "Triggers: 中文触发词 / English triggers. 一句话能力描述。"
license: MIT
---
# 名称 · 一句话定位
**一句话**:这个技能干什么
## 什么时候触发
## 你的执行规则(编号、可执行、写给未来 AI 执行者)
## 可复制的完整提示词(如适用)
## 本机适配场景举例(绑定用户真实项目才算"适配")
## 关联技能(工作流串联)
  • description 开头放触发词;正文规则是操作指令,不是给人看的散文。

尺寸铁律(踩过坑,2026-08-24)

  1. 单次工具调用的参数 ≤~8K token。超长内容一次 write_file 会流式中途超时、整个动作不执行。
  2. 正确拆法:SKILL.md 只放精华操作版(目标 ≤~4KB);逐字长文(完整提示词全文、原始资料、案例记录)放 references/<名>.md,SKILL.md 加一行指针。
  3. 多文件批量任务:每次消息并行发 2 个中等 write_file,绝不单发巨型调用。
  4. 被超时打断后不要原样重试同一大调用——先拆小再写。

验证闭环(写完必做)

  1. shell 循环 grep -m1 '^name:' ~/.hermes/skills/<s>/SKILL.md 校验 frontmatter name 与目录名一致;
  2. skill_view(name) 确认 readiness_status=available;
  3. 带 references/ 的核对文件数量。

卡片族模式(一套方法论拆多张卡时)

  • 每张卡一个独立技能(保证触发独立性)+ 一张总索引技能(选卡表、组合拳、出处 URL 存档)。
  • 完整案例(12+1 卡实战、结构模板、教训):见 references/case-kazike-prompt-cards.md。

多端分发(用户流程:先在 Hermes 跑项目验证,再装给其他 agent)

各 agent 技能目录(copytree 同步后逐一校验 SKILL.md + references 完整):

Agent路径
Hermes~/.hermes/skills/<name>/
Codex + Gemini CLI(共享)~/.agents/skills/<name>/
Claude Code~/.claude/skills/<name>/
DeepSeek Harness~/.dsh/skills/<name>/
Kimi Code~/.kimi-code/skills/<name>/
  • 本机确有 Gemini CLI 0.43(~/.hermes/node/bin/gemini),读 ~/.agents/skills,与 Codex 一份共享。
  • ⚠️ 用户纠正过的流程:新技能先在 Hermes 跑真实项目验证通过,再分发其他 agent。不要跳过验证直接分发(2026-09-07 skill-navigator 未验证先装的教训)。
  • 修改技能后要同步全部分发副本(各端逐个覆写 SKILL.md),否则知识漂移。
  • ⚠️ skill_manage 建 description 限 ≤60 字符(中文字符按字数计),超限直接拒批——触发词放最前,一句话正文压短,细节进正文。
  • ⚠️ 自建技能默认非 curator 管理时,后台自动审查无法 patch(报 user-owned 拒绝);需前台 hermes curator adopt <name> 后才能自主维护。

产出归档

随技能交付用户的指南/报告,按 LifeOS 宪法命名法(YYYY-MM-DD-HHMMSS-内容.md)归入对应分类区,不放桌面。

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.