Agent skill

Skill Creator Skill

by OpenLoaf in OpenLoaf/OpenLoaf

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 .openloaf/skills/ 目录下…

AGPL-3.0Auto-check passedAgent Workflows

Install Skill Creator Skill

skills CLI
$ npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenLoaf/OpenLoaf skill-creator-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/skill-creator .claude/skills/skill-creator-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-creator-skill
GitHub stars
108
Token cost
~1.2k tokens
SKILL.md length
258 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
AGPL-3.0

At a glance

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 .openloaf/skills/ 目录下…

  • Works in 4 steps: 这个技能让 AI 做什么? — 核心能力描述 → 什么情况下应该触发? — 用户会怎么说、在什么场景下用到 → 预期输出是什么? — 文件、数据、操作结果,还是对话回复 → …
  • Tasks that involve Skill authoring
  • SKILL.md covers 工具清单, 作用域:全局技能 vs 项目技能, 第一步:理解需求 and 第二步:编写 SKILL.md, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Creator Skill is an agent skill from OpenLoaf/OpenLoaf. 当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 .openloaf/skills/ 目录下 SKILL.md 的创建 / 修改 / 调优请求都应加载本技能。也适用于用户想理解技能格式、排查触发问题、或把对话里的工作流固化成可复用能力的场景。不用于:内置技能(如 file-ops、email-ops 等)的修改——那些是平台随版本发布的只读能力。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Skill authoring

Example prompts

  • “帮我创建一个技能”
  • “做一个新 skill”
  • “把刚才的操作封装成技能”
  • “/skill-creator-skill”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 这个技能让 AI 做什么? — 核心能力描述
  2. 什么情况下应该触发? — 用户会怎么说、在什么场景下用到
  3. 预期输出是什么? — 文件、数据、操作结果,还是对话回复
  4. 属于全局还是项目作用域? — 按上面决策树判断

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Creator Skill loads about 1.2k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 258 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 258 words, ~1,211 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator-skill/SKILL.md (or your agent's skills folder).
name
skill-creator-skill
description
当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 `.openloaf/skills/` 目录下 `SKILL.md` 的创建 / 修改 / 调优请求都应加载本技能。也适用于用户想理解技能格式、排查触发问题、或把对话里的工作流固化成可复用能力的场景。不用于:内置技能(如 file-ops、email-ops 等)的修改——那些是平台随版本发布的只读能力。
tools
Read, Write, Edit, Grep

技能创建与优化指南

本技能指导你为 OpenLoaf 创建、编辑和改进自定义 Skill。Skill 是一段 Markdown 指令,当用户的请求匹配 description 时会被自动加载进对话,让 AI 按照里面的方法执行任务。

工具清单

工具职责只读
Read / Glob / Grep读取现有 skill 与定位锚点(常驻工具)是
Write创建新的 SKILL.md / openloaf.json / 辅助脚本(常驻工具)否
Edit修改已有 skill 内容(常驻工具)否

加载:全部为核心工具,始终可用,无需 ToolSearch 激活。本 skill 没有专有 deferred 工具 — 它是指导型 skill,教 AI 如何组织自定义 skill 文件。

作用域:全局技能 vs 项目技能

用户自定义技能分两种作用域,先搞清楚该放哪里再动手。优先级由低到高:builtin < global < project,同名时项目技能覆盖全局技能。

全局技能(Global Skill)
  • 路径:~/.openloaf/skills/<skill-name>/SKILL.md
  • 可见范围:所有项目的所有对话
  • 适用:跨项目通用的能力 / 个人工作习惯 / 通用文档生成 / 默认的输出风格
  • 典型例子:"我写日报的固定模板"、"提交代码前先跑 lint"、"翻译时的术语表"
项目技能(Project Skill)
  • 路径:{projectRoot}/.openloaf/skills/<skill-name>/SKILL.md
  • 可见范围:仅当前项目的对话
  • 适用:项目特有的知识 / 代码约定 / 业务流程 / 只在这个仓库里有意义的工作流
  • 典型例子:"这个仓库的模块约定"、"本项目的 API 鉴权流程"、"该怎么跑 E2E 测试"
怎么选
能力只在当前项目有意义(文件路径、业务术语、仓库约定)?
  └─ 是 → 项目技能(默认首选)
  └─ 否 → 跨项目复用(个人习惯、通用模板)?
        └─ 是 → 全局技能
        └─ 不确定 → 先建项目技能,将来发现多项目用得上再提升为全局

铁律:项目特有的业务知识不要放进全局技能——会污染其他项目。反过来,通用能力放进项目技能会错过复用机会。拿不准时先问用户:"这个能力只有这个项目用得上,还是你其他项目也想用?"

第一步:理解需求

在动手写文件前,先明确四件事(对话上下文可能已经包含答案,不要重复问):

  1. 这个技能让 AI 做什么? — 核心能力描述
  2. 什么情况下应该触发? — 用户会怎么说、在什么场景下用到
  3. 预期输出是什么? — 文件、数据、操作结果,还是对话回复
  4. 属于全局还是项目作用域? — 按上面决策树判断

如果用户说"把刚才的操作封装成技能",回顾对话历史提取实际使用的工具序列、决策逻辑和用户修正过的地方——那些才是技能真正要固化的知识。

第二步:编写 SKILL.md

每个技能是一个文件夹,核心只有一个文件:SKILL.md。

文件结构
<skill-name>/
├── SKILL.md          # 必需 — 技能指令(YAML frontmatter + Markdown 正文)
├── openloaf.json     # 可选 — UI 展示元数据(icon、颜色、中文名)
└── scripts/          # 可选 — 辅助脚本(python/bash 等)
SKILL.md 格式
markdown
---
name: my-skill-name        # kebab-case,与文件夹名一致
description: >             # 决定 AI 何时加载这个技能——写好这一行至关重要
  当用户...时触发。典型说法:"..."。不用于:...
---

# 技能标题

正文内容...
description 写法要点

description 是技能触发的唯一入口,触发得准不准几乎全看它:

  • 同时说清"做什么"和"何时用" — 缺一不可
  • 列举典型说法,用引号包住用户可能说的原话 — AI 做触发判断时会直接比对这些例子
  • 适度激进,宁宽勿窄 — 漏触发的危害远大于偶尔多触发。与其写"如何生成日报",不如写"当用户提到日报、周报、工作汇总、工时记录、或想把今天做的事整理成任何形式的汇报时触发"
  • 用'不用于'划清边界 — 避免误触发。例:"不用于:Office 文档(→ docx/xlsx/pptx-skill)"
  • 包含同义词和口语表达 — 用户不会总用标准术语,要覆盖"给我来一份"、"整一个"、"搞个"之类的口语
正文写法要点
  • 告诉 AI 为什么,而不是堆叠 MUST/NEVER — 用因果解释代替强制命令,模型能推理出边界情况
  • 用决策树替代长篇说明 — 用 ├─ 是 → ... 格式清晰表达分支逻辑
  • 给出具体示例 — JSON 参数、命令调用、对话片段,比抽象描述有用十倍
  • 保持精简 — 理想长度 < 500 行;超长时拆分到 scripts/ 或分层引用
  • 使用祈使语气 — 写"用 Write 创建文件"而不是"你应该用 Write"
正文推荐结构
markdown
# 技能标题

一段话概述本技能覆盖什么。

## 触发条件
列举哪些用户说法 / 场景应触发本技能。

## 工作流程
按步骤描述 AI 应该怎么做。用编号步骤 + 决策树。

## 工具使用
列出本技能依赖的工具及用法要点。

## 示例
1-2 个端到端完整示例。

## 常见陷阱
容易犯的错误和注意事项。

## 铁律
3-5 条不可违反的核心规则。

第三步:创建 openloaf.json(可选但推荐)

openloaf.json 提供 UI 展示信息,和 SKILL.md 同目录:

json
{
  "name": "技能中文名",
  "description": "一句话中文描述",
  "icon": "🔧",
  "version": "0.1.0",
  "sourceLanguage": "zh-CN",
  "targetLanguage": "zh-CN",
  "colorIndex": 0
}

colorIndex 配色:0=青 1=紫 2=琥珀 3=天蓝 4=玫瑰 5=祖母绿 6=靛蓝 7=酸橙

icon:选一个最能代表技能功能的 emoji。

第四步:保存到磁盘

用 Write 工具写文件。路径按作用域严格区分:

作用域写入路径
全局技能~/.openloaf/skills/<skill-name>/SKILL.md
项目技能{projectRoot}/.openloaf/skills/<skill-name>/SKILL.md

创建前先检查同名冲突,避免意外覆盖:

Glob: ~/.openloaf/skills/<skill-name>/SKILL.md        # 查全局
Glob: {projectRoot}/.openloaf/skills/<skill-name>/SKILL.md  # 查项目

冲突时询问用户:覆盖 / 换名 / 取消。

创建完成后务必告知用户:技能列表在对话初始化时加载,当前对话看不到新建技能,需要开启新对话才会生效。

第五步:验证与迭代

技能创建后,建议用户测试:

  1. 开启新对话
  2. 用触发说法让 AI 加载技能(观察是否出现技能加载提示)
  3. 检查 AI 是否按照技能指令执行
  4. 有问题回来修改 SKILL.md,再开新对话重试
常见问题排查
症状原因修复
技能不触发description 太窄加更多典型说法,覆盖口语和同义词
技能误触发description 太宽加"不用于"限定,划清与其他技能的边界
AI 不遵守指令正文太长或太模糊缩短、加决策树、加具体示例
工具调用出错没说明工具用法加参数示例和调用顺序
其他项目误用到误放到了全局移到项目作用域({projectRoot}/.openloaf/skills/)

改进已有技能

用户要求改进已有技能时:

  1. Read 现有 SKILL.md 理解当前内容
  2. 与用户确认改进方向(触发准确度 / 输出质量 / 覆盖范围)
  3. 只改有问题的部分,不要重写整个文件——保持用户已验证过的部分稳定
  4. 保存后让用户新开对话验证

description 优化专项:如果用户反馈"该触发时没触发",聚焦优化 description:

  • 问用户"你当时说的原话是什么?",把原话加进典型说法
  • 补充同义词、口语表达、中英文变体
  • 检查"不用于"是否写得过于激进把正例排除了

铁律

  1. 先问清楚再动手 — 做什么 / 何时触发 / 输出什么 / 全局还是项目,四个问题没搞清楚前不写文件
  2. 作用域不要选错 — 项目特有的业务知识不进全局;通用能力别埋在单项目里
  3. description 宁宽勿窄 — 漏触发的危害远大于偶尔多触发
  4. 正文讲为什么而不是堆命令 — 用因果解释代替 MUST/NEVER
  5. 创建前 Glob 查冲突,创建后提示用户新对话测试 — 技能列表在对话初始化时加载

© OpenLoaf, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/server/src/ai/builtin-skills/skill-creator of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6

Compare with similar skills

Skill Creator Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Creator Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Creator Skill this skillOpenLoaf/OpenLoaf108—~1.2kAutomated safety check: PassAGPL-3.0
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed
  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from OpenLoaf/OpenLoaf

All 33 skills in this repo
  • Agent Orchestration Skill

    OpenLoaf/OpenLoaf

    Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Browser Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…

    108 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Canvas Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.

    108 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Email Operations

    OpenLoaf/OpenLoaf

    Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.

    108 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check passed
  • macOS Desktop Control

    OpenLoaf/OpenLoaf

    Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.

    108 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Skill Creator Skill

What does Skill Creator Skill do?

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能(Skill)时触发。典型说法:"帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 .openloaf/skills/ 目录下…. Skill Creator Skill is an agent skill from OpenLoaf/OpenLoaf.

When should I use Skill Creator Skill?

Skill Creator Skill fits situations like: tasks that involve Skill authoring.

How do I install Skill Creator Skill in Claude Code?

Run `npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/skill-creator in OpenLoaf/OpenLoaf) into .claude/skills/skill-creator-skill in your project. Claude Code loads it when a task matches its description.

How do I install Skill Creator Skill in Codex?

Run `npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/skill-creator in OpenLoaf/OpenLoaf) into .agents/skills/skill-creator-skill in your project. Codex loads it when a task matches its description.

Can I use Skill Creator Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLoaf/OpenLoaf --skill skill-creator-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-creator-skill, .gemini/skills/skill-creator-skill, .github/skills/skill-creator-skill and .opencode/skills/skill-creator-skill in your project.

What does Skill Creator Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Creator Skill is instructions for the agent only.

Does Skill Creator Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Creator Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Creator Skill use?

Skill Creator Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator Skill use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Creator Skill?

Skills that share tags, products or a category with Skill Creator Skill: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Creator Skill?

OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.

Source: OpenLoaf/OpenLoaf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.