只靠通用对话时，用于列出日历、查看/创建/更新事件以及检查可用性的Google日历命令行界面。 --- VS C…这件事容易做得散，结果也不稳定。
gccli把这件事收成可复用的技能。Agent 被点到时按这个目标组织步骤，输入侧常见的是文本，交付侧常见的是文本。它不替代你读仓库里的 SKILL.md，只帮你在安装前判断这件事值不值得交给 Agent。
当用户的说法接近这项技能的名称或任务时会匹配。用户用名称或接近的说法点名这项技能，或描述与它相同的任务。
若用户只是随口提到相关词、并不要求现在就做，未必应该触发。具体匹配句子以 GitHub 上的 SKILL.md 为准。
安装前先看它会动哪些材料：当前能确定的输入是文本，输出是文本。是否会改文件、跑命令或访问网络，仓库说明里没有写死，不能从名称推断。
权限、副作用和适用范围都以该仓库的 SKILL.md 为准。涉及生产数据、账号或对外发布时，先在小范围试一次，再决定是否常用。
重要提示：本站仅作 Skill 资源导航与收录，正文以 GitHub 原仓库为准，版权归原项目所有。
Web search and content extraction using the official Brave Search API. No browser required.
Requires a Brave Search API account with a free subscription. A credit card is required to create the free subscription (you won't be charged).
~/.profile or ~/.zprofile for zsh):
export BRAVE_API_KEY="your-api-key-here"
cd {baseDir}
npm install
{baseDir}/search.js "query" # Basic search (5 results)
{baseDir}/search.js "query" -n 10 # More results (max 20)
{baseDir}/search.js "query" --content # Include page content as markdown
{baseDir}/search.js "query" --freshness pw # Results from last week
{baseDir}/search.js "query" --freshness 2024-01-01to2024-06-30 # Date range
{baseDir}/search.js "query" --country DE # Results from Germany
{baseDir}/search.js "query" -n 3 --content # Combined options
-n <num> - Number of results (default: 5, max: 20)--content - Fetch and include page content as markdown--country <code> - Two-letter country code (default: US)--freshness <period> - Filter by time:
pd - Past day (24 hours)pw - Past weekpm - Past monthpy - Past yearYYYY-MM-DDtoYYYY-MM-DD - Custom date range{baseDir}/content.js https://example.com/article
Fetches a URL and extracts readable content as markdown.
--- Result 1 ---
Title: Page Title
Link: https://example.com/page
Age: 2 days ago
Snippet: Description from search results
Content: (if --content flag used)
Markdown content extracted from the page...
--- Result 2 ---
...
重要提示：本站仅作 Skill 资源导航与收录，正文以 GitHub 原仓库为准，版权归原项目所有。
A collection of skills for pi-coding-agent, compatible with Claude Code, Codex CLI, Amp, and Droid.
# User-level (available in all projects)
git clone https://github.com/badlogic/pi-skills ~/.pi/agent/skills/pi-skills
# Or project-level
git clone https://github.com/badlogic/pi-skills .pi/skills/pi-skills
git clone https://github.com/badlogic/pi-skills ~/.codex/skills/pi-skills
Amp finds skills recursively in toolboxes:
git clone https://github.com/badlogic/pi-skills ~/.config/amp/tools/pi-skills
# User-level
git clone https://github.com/badlogic/pi-skills ~/.factory/skills/pi-skills
# Or project-level
git clone https://github.com/badlogic/pi-skills .factory/skills/pi-skills
Claude Code only looks one level deep for SKILL.md files, so each skill folder must be directly under the skills directory. Clone the repo somewhere, then symlink individual skills:
# Clone to a convenient location
git clone https://github.com/badlogic/pi-skills ~/pi-skills
# Symlink individual skills (user-level)
mkdir -p ~/.claude/skills
ln -s ~/pi-skills/brave-search ~/.claude/skills/brave-search
ln -s ~/pi-skills/browser-tools ~/.claude/skills/browser-tools
ln -s ~/pi-skills/gccli ~/.claude/skills/gccli
ln -s ~/pi-skills/gdcli ~/.claude/skills/gdcli
ln -s ~/pi-skills/gmcli ~/.claude/skills/gmcli
ln -s ~/pi-skills/transcribe ~/.claude/skills/transcribe
ln -s ~/pi-skills/vscode ~/.claude/skills/vscode
ln -s ~/pi-skills/youtube-transcript ~/.claude/skills/youtube-transcript
# Or project-level
mkdir -p .claude/skills
ln -s ~/pi-skills/brave-search .claude/skills/brave-search
ln -s ~/pi-skills/browser-tools .claude/skills/browser-tools
ln -s ~/pi-skills/gccli .claude/skills/gccli
ln -s ~/pi-skills/gdcli .claude/skills/gdcli
ln -s ~/pi-skills/gmcli .claude/skills/gmcli
ln -s ~/pi-skills/transcribe .claude/skills/transcribe
ln -s ~/pi-skills/vscode .claude/skills/vscode
ln -s ~/pi-skills/youtube-transcript .claude/skills/youtube-transcript
| Skill | Description |
|---|---|
| brave-search | Web search and content extraction via Brave Search |
| browser-tools | Interactive browser automation via Chrome DevTools Protocol |
| gccli | Google Calendar CLI for events and availability |
| gdcli | Google Drive CLI for file management and sharing |
| gmcli | Gmail CLI for email, drafts, and labels |
| transcribe | Speech-to-text transcription via Groq Whisper API |
| vscode | VS Code integration for diffs and file comparison |
| youtube-transcript | Fetch YouTube video transcripts |
Each skill follows the pi/Claude Code format:
---
name: skill-name
description: Short description shown to agent
---
# Instructions
Detailed instructions here...
Helper files available at: {baseDir}/
The {baseDir} placeholder is replaced with the skill's directory path at runtime.
Some skills require additional setup. Generally, the agent will walk you through that. But if not, here you go:
npm install in the skill directory.npm install in the skill directory.npm install -g @mariozechner/gccli.npm install -g @mariozechner/gdcli.npm install -g @mariozechner/gmcli.npm install -g @mariozechner/pi-coding-agent.code CLI in PATH.npm install in the skill directory.MIT
Skill 就是一个装着 SKILL.md 的文件夹：头信息写 name 和 description，正文写具体指令；Agent 平时只记描述，匹配请求后再读全文。
在技能库挑一条接近任务的 Skill，按详情里的安装说明放到 Agent 目录，用点名或自然语言触发一次并核对结果。
只复制一段指令就用 Prompt；要让 Agent 按固定步骤、检查清单或脚本反复完成同一类任务，再用 Skill。
Skill 教 Agent 一套做法；MCP 把外部数据和工具接进 Agent。很多工作流两样都要。
先写清要完成的事，再在技能库里对 description；再看安装成本、维护状态和权限范围。