Agent skill · research science · sickn33
pi-web-search
Give Pi Agents a safe web-search and fetch workflow using the installed pi-web-access package.
Why this skill is useful
Adds a specific web search and content fetching workflow using the pi-web-access package that the AI wouldn't reliably generate on its own.
What it needs
Requires ffmpeg, pi-web-access, yt-dlp installed locally. Requires deepapi account access. About 2k tokens when loaded. Last updated 2026-08-07. 44,571 stars on the source repository.
What this skill does
Web Search When to Use Use when a Pi Agent task needs current web information, page fetches, PDFs, YouTube, or GitHub content. Use when Pi should use its own web-access package instead of another agent browser tool. The pi-web-access package is installed globally. Zero-config via Exa MCP (no API key), with fallback Exa → Perplexity → Gemini. CRITICAL: always pass workflow: "none" Every websearch call MUST include workflow: "none". This skips the interactive browser curator popup (the user does not want it opening). No exceptions — single query or batched queries, always set workflow: "none". Tools websearch — search the web; returns synthesized answers with citations. Can be called many times per turn. Always pass workflow: "none". codesearch — zero-key Exa code-context. Use for library/API/code lookups instead of generic websearch. fetchcontent — fetch URL(s) → markdown; handles PDFs, YouTube, GitHub. getsearchcontent — big pages (>30k chars) are truncated in responses but stored in full; call this to pull the rest on demand so they don't blow context. fetchcontent specifics GitHub URLs are cloned, not scraped — you get real files + a local path to explore with read/bash (private repos need the gh CLI). Use this for dev work. PDFs → auto-extracted to markdown in ~/Downloads/, readable in sections (text-only, no OCR). YouTube/video → full raw transcripts + frame extraction. Needs a GEMINIAPIKEY (not zero-config); frame extraction also needs ffmpeg/yt-dlp. Routing — match the user's phrasing Always use the websearch tool. These counts are HARD MINIMUMS — count your queries before answering and do not stop short: "web search" → at least 2 queries, varied keywords/angles, then synthesize. "extensive web research" → at least 4 queries, totally different keywords and angles. "deep research" → at least 8 queries, totally different keywords and angles, run across 2–3 successive batches (refine angles after each batch), to learn as much as possible about the topic. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sickn33/pi-web-search--9b575b