skill-creator

openclaw/openclaw · Agent Skill

為 AI 代理建立、編輯和驗證 SKILL.md 檔案，對其進行結構化並準備好使用。

總覽

發布者	openclaw組織
儲存庫	openclaw/openclaw ↗
技能資料夾	`skill-creator`
星	389,030
附帶檔案	1
授權	MIT
最近更新	2026年8月10日
連結	技能原始碼 ↗ · 儲存庫 ↗

Mozgi 檢查

我們在技能檔案中發現的內容。詳細資訊需訂閱。

安全性

低風險 · 未發現明顯風險 — 完整報告會顯示細節

相容性

需要額外軟體

相似技能

找到 51 個相似技能

訂閱另含

安裝

技能就是一個含 SKILL.md 的資料夾。選擇你的代理，在專案根目錄的終端機（macOS、Linux 或 Windows 的 Git Bash）執行指令。

把提示貼到 Claude、Codex 或其他助理：它會自行檢查並安裝技能。

Install the “skill-creator” skill from mozgi.io (https://mozgi.io/skills/skill-creator-openclaw/) for me.

1. Download the archive: https://mozgi.io/skills/skill-creator-openclaw/download
   If it fails, take the skill folder from the source: https://github.com/openclaw/openclaw/tree/main/skills/skill-creator
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “skill-creator” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/skill-creator/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/openclaw/openclaw.git /tmp/openclaw
mkdir -p .claude/skills
cp -r /tmp/openclaw/skills/skill-creator .claude/skills/skill-creator

重新啟動 Claude Code — 技能就會出現在清單中，手動呼叫：/skill-creator。要套用到所有專案，請放在 ~/.claude/skills。

git clone --depth 1 --branch main https://github.com/openclaw/openclaw.git /tmp/openclaw
mkdir -p .agents/skills
cp -r /tmp/openclaw/skills/skill-creator .agents/skills/skill-creator

Codex 會從目前資料夾往上到儲存庫根目錄，在 .agents/skills 中尋找技能；用 /skills 或 $skill-creator 呼叫。所有專案：~/.agents/skills。

git clone --depth 1 --branch main https://github.com/openclaw/openclaw.git /tmp/openclaw
mkdir -p .cursor/skills
cp -r /tmp/openclaw/skills/skill-creator .cursor/skills/skill-creator

Cursor 啟動時會載入技能；在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案：~/.cursor/skills。

git clone --depth 1 --branch main https://github.com/openclaw/openclaw.git /tmp/openclaw
mkdir -p .gemini/skills
cp -r /tmp/openclaw/skills/skill-creator .gemini/skills/skill-creator

任務符合時，Gemini CLI 會提議啟用技能，由你確認。所有專案：~/.gemini/skills。

技能檔案

1 個檔案下載 ZIP

安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。

SKILL.md 內容

作者原文 · 唯讀

Skill Creator

Workflow

1. Establish the contract.

Read the existing skill and its resources, or collect concrete requests for a new skill.
Separate actual workflow branches from synonyms for the same branch.
Done when: every branch has a concrete trigger, expected outcome, and persistence target.

2. Choose invocation.

Model-discoverable: write a model-facing description; omit disable-model-invocation.
Manual-only: set disable-model-invocation: true; write a human-facing summary.
Direct tool command: add command-dispatch: tool, command-tool, and command-arg-mode only when the command bypasses the model.
Done when: frontmatter matches how the skill will actually be reached.

3. Structure the skill.

Map shared ordered procedure to SKILL.md; end every step with a checkable completion criterion and finish with verification.
Keep routing conditions in description; start the body with execution.
Map branch-only detail to references/, deterministic helpers to scripts/, output resources to assets/, and optional UI metadata to agents/.
Done when: every planned resource has one purpose and a direct pointer from SKILL.md.

4. Draft and persist.

Live workspace skill: use skill_workshop to create or revise a pending proposal; keep live files unchanged until apply.
Repository-owned skill source: use the repository's normal edit and review workflow.
Done when: the proposal or source diff implements every branch from step 1 and contains every resource from step 3.

5. Validate.

Run python {baseDir}/scripts/quick_validate.py <skill-directory> and execute every touched helper's focused test.
Done when: frontmatter passes, resource pointers resolve, and every touched helper passes its focused test.

Frontmatter

Required: name, description.

OpenClaw also supports metadata, homepage, license, allowed-tools, user-invocable, disable-model-invocation, command-dispatch, command-tool, and command-arg-mode. Add optional fields only when they change runtime behavior or discovery.

常見問題

skill-creator 技能有什麼用途？

為 AI 代理建立、編輯和驗證 SKILL.md 檔案，對其進行結構化並準備好使用。

如何安裝 skill-creator？

打開本頁的「安裝」區塊並選擇你的代理 — Claude Code、Codex、Cursor 或 Gemini CLI：那裡有把技能資料夾複製到正確位置的現成指令。也可以複製「透過助理」分頁中的提示，讓助理自行檢查並安裝技能。

skill-creator 適用哪些 AI 模型？

技能是純 Markdown 指示（Agent Skills 格式），因此 skill-creator 適用任何讀取 SKILL.md 的代理：Claude Code、Codex、Cursor、Gemini CLI、GitHub Copilot、OpenCode 等。只有在任務符合技能描述時，模型才會載入指示。

skill-creator 是免費的嗎？

此技能由 openclaw 公開發布，採用 MIT 授權。技能本身免費 — 你只需向 AI 供應商支付實際使用的 token 費用。

安裝技能安全嗎？

技能是代理會遵循的指示，安裝前請閱讀 SKILL.md 及相關檔案。技能資料夾中的腳本只有在代理執行時才會運行 — 留意它的動作，不要授予多餘權限。

技能和 MCP 伺服器或外掛有何不同？

MCP 伺服器或外掛為模型提供新工具 — 會執行並回傳結果的程式碼。技能提供的是知識與流程：如何處理任務、要遵循哪些步驟、好的成果長什麼樣子。它不需要伺服器或 API 金鑰。

總覽