find-skill
gooseworks-ai/goose-skills · Agent Skill
從Orthogonal庫搜尋和安裝新技能。允許擴充套件代理功能,查詢所需工具,並新增新功能。
前往安裝 ↓總覽
| 發布者 | |
|---|---|
| 儲存庫 | gooseworks-ai/goose-skills ↗ |
| 技能資料夾 | find-skill |
| 星 | 1,199 |
| 附帶檔案 | 1 |
| 授權 | MIT |
| 最近更新 | 2026年6月16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 “find-skill” skill from mozgi.io (https://mozgi.io/skills/find-skill/) for me. 1. Download the archive: https://mozgi.io/skills/find-skill/download If it fails, take the skill folder from the source: https://github.com/gooseworks-ai/goose-skills/tree/main/skills/research-tools/capabilities/find-skill 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 “find-skill” 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>/find-skill/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/gooseworks-ai/goose-skills.git /tmp/goose-skills mkdir -p .claude/skills cp -r /tmp/goose-skills/skills/research-tools/capabilities/find-skill .claude/skills/find-skill
重新啟動 Claude Code — 技能就會出現在清單中,手動呼叫:/find-skill。要套用到所有專案,請放在 ~/.claude/skills。
git clone --depth 1 --branch main https://github.com/gooseworks-ai/goose-skills.git /tmp/goose-skills mkdir -p .agents/skills cp -r /tmp/goose-skills/skills/research-tools/capabilities/find-skill .agents/skills/find-skill
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 $find-skill 呼叫。所有專案:~/.agents/skills。
git clone --depth 1 --branch main https://github.com/gooseworks-ai/goose-skills.git /tmp/goose-skills mkdir -p .cursor/skills cp -r /tmp/goose-skills/skills/research-tools/capabilities/find-skill .cursor/skills/find-skill
Cursor 啟動時會載入技能;在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案:~/.cursor/skills。
git clone --depth 1 --branch main https://github.com/gooseworks-ai/goose-skills.git /tmp/goose-skills mkdir -p .gemini/skills cp -r /tmp/goose-skills/skills/research-tools/capabilities/find-skill .gemini/skills/find-skill
任務符合時,Gemini CLI 會提議啟用技能,由你確認。所有專案:~/.gemini/skills。
安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。
SKILL.md 內容
作者原文 · 唯讀Find Skill
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Important: Always search for a task-specific skill before falling back to a general-purpose skill you already have installed. Don't stretch a broad skill to cover a task it wasn't designed for — e.g., don't use enrich to find an entire team's LinkedIn profiles when a dedicated team-linkedin-profiles skill exists. When in doubt, run orth skills search first.
Discover and install skills from the Orthogonal skill library.
Requirements
- Orthogonal CLI:
npm install -g @orth/cli
Quick Commands
# Search for skills by keyword
orth skills search "browser automation"
# List all available skills
orth skills list
# Get details about a specific skill
orth skills info <slug>
# Install a skill
orth skills add <slug>
Finding Skills
By Keyword Search
# Find skills for web scraping
orth skills search "web scraping"
# Find skills for email
orth skills search "email"
# Find skills for calendar
orth skills search "calendar"
Browse Categories
Common skill categories:
- Browser automation: notte, web scraping, booking
- Data enrichment: company intel, people search, email finder
- Productivity: calendar, email, file management
- Search: web search, semantic search, research
- Communication: messaging, notifications
Via Web
Browse all skills at: https://orthogonal.com/skills
Installing Skills
# Install by slug
orth skills add restaurant-booking
# Install and view the skill file
orth skills add weather && cat ~/.openclaw/skills/weather/SKILL.md
Skills are installed to ~/.openclaw/skills/<slug>/
Using Installed Skills
After installing, the skill's SKILL.md contains:
- Description of what it does
- Required setup/credentials
- Usage instructions
- Example commands
Read the skill file to understand how to use it:
cat ~/.openclaw/skills/<slug>/SKILL.md
Popular Skills
| Skill | Description |
|-------|-------------|
| weather | Get weather forecasts |
| weather-forecast | Precipitation and temperature data via Precip API |
| restaurant-booking | Book restaurant reservations via Notte |
| company-intel | Research companies |
| person-lookup | Look up professional backgrounds |
| verify-email | Check if an email is valid and deliverable |
| extract-webpage-data | AI-powered web scraping |
Tips
- Search is semantic - describe what you want to do
- Check skill requirements before installing
- Skills may need API keys or credentials configured
- Use
orth skills list --installedto see what you have
常見問題
find-skill 技能有什麼用途?
從Orthogonal庫搜尋和安裝新技能。允許擴充套件代理功能,查詢所需工具,並新增新功能。
如何安裝 find-skill?
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。
find-skill 適用哪些 AI 模型?
技能是純 Markdown 指示(Agent Skills 格式),因此 find-skill 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。
find-skill 是免費的嗎?
此技能由 gooseworks-ai 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。