跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 skill-creator

Skill Creator

脚手架新技能具有有效的前事,目录布局,以及启动器SKILL.md.

7747 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

脚手架新技能具有有效的前事,目录布局,以及启动器SKILL.md.

何时用

每一个:**

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Core Principles、Anatomy of a Skill、Creating a Skill、Step 1: Understand the Request、Step 2: Scaffold、Step 3: Plan Reusable Contents。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 scripts/init_skill.py、scripts/validate_skill.py,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Scaffold new skills with valid frontmatter, directory layout, and a starter SKILL.md.

Core PrinciplesAnatomy of a SkillCreating a SkillStep 1: Understand the RequestStep 2: ScaffoldStep 3: Plan Reusable ContentsStep 4: Write the SKILL.mdStep 5: Create / Update via `skill_manage`Always read_file first to get exact whitespace/contentStep 6: ValidateFrontmatter FormatOn-Chain Skills — Wallet Policy Prerequisite

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
skill-creator
description
Scaffold new skills with valid frontmatter, directory layout, and a starter SKILL.md.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 2
  • scripts/init_skill.py
  • scripts/validate_skill.py

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「skill-creator」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-89748b273ed7a7ed-%E6%8A%80%E8%83%BD%E5%88%9B%E5%BB%BA%E8%80%85.html
请存为 .cursor/skills/skill-creator/SKILL.md 或 .claude/skills/skill-creator/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/starchild-ai-agent/official-skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/starchild-ai-agent/official-skills' --list

npx skills add 'https://github.com/starchild-ai-agent/official-skills' --skill 'skill-creator'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: skill-creator version: 1.2.1 description: | Scaffold new skills with valid frontmatter, directory layout, and a starter SKILL.md. Use when building a new reusable workflow or wrapping a new API (e.g. create a kalshi skill, scaffold an API helper, start a charting skill). metadata: starchild: emoji: "\U0001F6E0\uFE0F" skillKey: skill-creator user-invocable: true --- ## Core Principles **Concise is key.** The context window is a shared resource between the system prompt, skills, conversation history, and your reasoning. Every line in a SKILL.md competes with everything else. Only add what you don't already know — don't document tool parameters visible in the system prompt, don't prescribe step-by-step workflows for things you can figure out. Focus on domain knowledge, interpretation guides, decision frameworks, and gotchas. **Progressive disclosure.** Skills load in three levels: 1. **Always in context** — name, emoji, and description appear in `` in every conversation. This is how you decide which skill to activate. The description must be a strong trigger. 2. **On activation** — the full SKILL.md body is loaded via `read_file` when you decide the skill is relevant. This is where workflow, guidelines, and decision trees live. 3. **On demand** — scripts/, references/, and assets/ are only loaded when explicitly needed. Heavy content goes here, not in the body. This means: keep the SKILL.md body lean (< 500 lines). Put detailed API docs in `references/`. Put automation in `scripts/`. The body should be what you need to *start working*, not an encyclopedia. **Degrees of freedom.** Match instruction specificity to task fragility: - **High freedom** (text guidance) — When multiple approaches are valid. Write natural language explaining WHAT and WHY, not step-by-step HOW. Example: "Check funding rates and social sentiment to gauge market mood." - **Medium freedom** (pseudocode + params) — When a preferred pattern exists but details can vary. Describe the approach with key parameters. Example: "Use RSI with period 14, buy below 30, sell above 70." - **Low freedom** (scripts in `scripts/`) — When operations are fragile, require exact syntax, or are repetitive boilerplate. Put the code in standalone scripts that get executed, not loaded into context. Example: Chart rendering with exact color codes and API calls. Default assumption: you are already smart. Only add context you don't already have. ## Anatomy of a Skill ``` my-skill/ ├── SKILL.md # Required: Frontmatter + instructions ├── scripts/ # Optional: Executable code (low freedom) │ └── render.py # Run via bash, not loaded into context ├── references/ # Optional: Docs loaded on demand (medium freedom) │ └── api-guide.md # Loaded via read_file when needed └── assets/ # Optional: Templates, images, data files └── template.json # NOT loaded into context, used in output ``` **When to use each:** | Directory | Loaded into context? | Use for | |-----------|---------------------|---------| | SKILL.md body | On activation | Core workflow, decision trees, gotchas | | `scripts/` | Never (executed) | Fragile operations, exact syntax, boilerplate | | `references/` | On demand | Detailed API docs, long guides, lookup tables | | `assets/` | Never | Templates, images, data files used in output | ## Creating a Skill ### Step 1: Understand the Request Before scaffolding, understand what you're building: - **What capability?** API integration, workflow automation, knowledge domain? - **What triggers it?** When should the agent activate this skill? (This becomes the description.) - **What freedom level?** Can the agent improvise, or does it need exact scripts? - **What dependencies?** API keys, binaries, Python packages? Examples: - "I want to generate charts" → charting skill with scripts (low freedom rendering) - "Help me think about trading strategies" → knowledge skill (high freedom, conversational) - "Integrate with Binance API" → API skill with env requirements and reference docs ### Step 2: Scaffold Use the init script: ```bash python skills/skill-creator/scripts/init_skill.py my-new-skill --path ./workspace/skills ``` With resource directories: ```bash python skills/skill-creator/scripts/init_skill.py api-helper --path ./workspace/skills --resources scripts,references ``` With example files: ```bash python skills/skill-creator/scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts --examples ``` ### Step 3: Plan Reusable Contents Before writing, decide what goes where: - **SKILL.md body**: Core instructions the agent needs every time this skill activates. Decision trees, interpretation guides, "when to do X vs Y" logic. - **scripts/**: Any code that must run exactly as written — API calls with specific auth, rendering with exact formats, data processing pipelines. - **references/**: Detailed docs the agent might need occasionally — full API endpoint lists, schema definitions, troubleshooting guides. - **assets/**: Output templates, images, config files that the agent copies/modifies for output. ### Step 4: Write the SKILL.md Plan the content first — frontmatter trigger, body structure, freedom level. Then: 1. **Frontmatter** — Update description (CRITICAL trigger), add requirements, set emoji 2. **Body** — Write for the agent, not the user. Short paragraphs over bullet walls. Opinions over hedging. Design patterns for the body: - **Workflow-based** — Step-by-step process (charting: fetch data → configure chart → render → serve) - **Task-based** — Organized by what the user might ask (trading: "analyze a coin" / "compare strategies" / "check sentiment") - **Reference/guidelines** — Rules and frameworks (strategy: core truths, conversation style, when to pull data) - **Capabilities-based** — Organized by what the skill can do (market-data: price tools / derivatives tools / social tools) ### Step 5: Create / Update via `skill_manage` **`skill_manage` is the primary workflow** — it validates frontmatter, runs a security scan, and auto-reloads the cache. Do NOT use `write_file` as the main path. **Creating a new skill:** ```python skill_manage(action="create", name="my-skill", content="---\nname: my-skill\n...") ``` **Patching an existing skill (preferred for targeted changes):** ```python # Always read_file first to get exact whitespace/content skill_manage(action="patch", name="my-skill", old_string="exact old text", new_string="new text") ``` **Full rewrite of existing skill:** ```python skill_manage(action="edit", name="my-skill", content="---\nname: my-skill\n...") ``` ⚠️ **Known gotchas:** - `create` errors if skill already exists → use `edit` or `patch` instead. - `edit`/`patch` errors if skill does NOT exist → use `create` first. - `patch` requires exact `old_string` match (whitespace included) → always `read_file` before patching. - `execute()` must accept `**kwargs` — if you see `unexpected keyword argument 'action'`, it's a bug in the tool implementation (fix: `def execute(self, **kwargs)`). **Fallback only** — if `skill_manage` is unavailable, use `write_file` + `skill_refresh()` manually. ### Step 6: Validate ```bash python skills/skill-creator/scripts/validate_skill.py ./workspace/skills/my-new-skill ``` After `skill_manage`, validate is optional (auto-reloaded), but run it to catch schema issues early. ## Frontmatter Format The frontmatter uses `metadata.starchild` for Star Child-specific fields: ```yaml --- name: skill-name version: 1.0.0 description: "What this skill does. Use when [specific trigger scenarios]." metadata: starchild: emoji: "🔧" skillKey: skill-name requires: env: [API_KEY_NAME] bins: [python] anyBins: [curl, wget] install: - kind: pip package: pandas - kind: apt package: curl bins: [curl] user-invocable: true disable-model-invocation: false --- ``` **Field reference:** | Field | Location | Required | Purpose | |-------|----------|----------|---------| | `name` | top-level | Yes | Skill identifier (lowercase hyphen-case) | | `version` | top-level | Yes | Semantic version (e.g. `1.0.0`). Required for publishing. Always include. | | `description` | top-level | Yes | Trigger text — when should the agent use this? | | `emoji` | `metadata.starchild` | No | Display emoji | | `skillKey` | `metadata.starchild` | No | Dedup key | | `requires.env` | `metadata.starchild` | No | Required env vars | | `requires.bins` | `metadata.starchild` | No | Required binaries (ALL must exist) | | `requires.anyBins` | `metadata.starchild` | No | Required binaries (ANY one) | | `install` | `metadata.starchild` | No | How to install deps (pip, apt, npm, etc.) | | `user-invocable` | top-level | No | Can user trigger via /command (default: true) | | `disable-model-invocation` | top-level | No | Hide from `` (default: false) | ## On-Chain Skills — Wallet Policy Prerequisite If the skill involves **any on-chain operations** (sending transactions, token approvals, swaps, bridging, signing, deposits, withdrawals, smart contract interactions), add a Prerequisites section near the top of the SKILL.md: ```markdown ## Prerequisites — Wallet Policy Before executing any [operation], the wallet policy must be active. Load the **wallet-policy** skill and propose the standard wildcard policy (deny key export + allow `*`). This covers all [skill-name] operations across all chains. ``` This ensures the agent proposes a wallet policy **before** attempting any transaction. Without it, the first transaction will fail with a policy violation. ## What NOT to Include - **README.md** — The SKILL.md IS the readme. Don't duplicate. - **CHANGELOG.md** — Skills aren't versioned packages. - **Docs the agent already has** — Don't repeat tool descriptions from the system prompt. - **Step-by-step for simple tasks** — The agent can figure out "read a file then process it." - **Generic programming advice** — "Use error handling" is noise. Specific gotchas are signal. ## Best Practices 1. **Description is the trigger.** This is how the agent decides to activate your skill. Include "Use when..." with specific scenarios. Bad: "Trading utilities." Good: "Test trading strategies against real historical data. Use when a strategy needs validation or before committing to a trade approach." 2. **Write for the agent, not the user.** The skill is instructions for the AI. Use direct language: "You generate charts" not "This skill can be used to generate charts." 3. **Scripts execute without loading.** Good for large automation. The agent reads the script only when it needs to customize, keeping context clean. 4. **Don't duplicate the system prompt.** The agent already sees tool names and descriptions. Focus on knowledge it doesn't have: interpretation guides, decision trees, domain-specific gotchas. 5. **Request credentials last.** Design the skill first, then ask the user for API keys. 6. **Always validate** before refreshing — run `validate_skill.py` to catch issues early.

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…