// Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.
Guide for extending Pi — decide between skills, extensions, prompt templates, themes, context files, or custom models, then create and package them. Use when someone wants to extend Pi, add capabilities, create a skill, build an extension, or make a Pi package.
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
Generate flat favicons from image prompts, then key out a magenta background and build PNG/ICO/WebP outputs with ImageMagick. Use when you need a reliable favicon workflow.
| name | brave-search |
| description | Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required. |
Headless web search and content extraction using Brave Search API. No browser or setup required.
BRAVE_API_KEY environment variable{baseDir}/search.py "query" # Basic search (5 results)
{baseDir}/search.py "query" -n 10 # More results
{baseDir}/search.py "query" --content # Include page content as markdown
{baseDir}/search.py "query" -n 3 --content # Combined
{baseDir}/content.py https://example.com/article
Fetches a URL and extracts readable content as markdown.
--- Result 1 ---
Title: Page Title
Link: https://example.com/page
Snippet: Description from search results
Content: (if --content flag used)
Markdown content extracted from the page...
--- Result 2 ---
...
DO NOT use Brave Search for these URLs. Use the correct tool instead:
gh CLI instead (e.g., gh api, gh repo view, gh issue view, etc.).md file URLs: ALWAYS use curl to fetch the raw file content directly (e.g., curl -sL https://example.com/docs/guide.md).md files — see above)