0xmariowu/autosearch/package-search

Claude Code and agent skill by 0xmariowu/autosearch

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install 0xmariowu/autosearch/package-search

SKILL.md

Self-written for task F201


name: package_search description: Discover packages across PyPI (exact-name lookup) and npm (full-text search) registries. version: 1 languages: [en, mixed] methods:

  • id: api_search

impl: methods/api_search.py requires: [] rate_limit: {per_min: 20, per_hour: 300} fallback_chain: [api_search] when_to_use: query_languages: [en, mixed] query_types: [library, package, sdk, dependency, installation] domain_hints: [software, programming] quality_hint: typical_yield: medium chinese_native: false layer: leaf domains: [code-package] scenarios: [npm-pypi-discovery, dependency-check] model_tier: Fast experience_digest: experience.md


package_search helps discover software packages across two public registries: PyPI for Python packages and npm for JavaScript and Node.js packages. It combines exact-name PyPI lookups with npm full-text search so package-related queries can still return useful evidence even when one registry has limited recall.

Known Quirks

  • PyPI has no official JSON search API, so this channel only does exact-name lookups against /pypi/<name>/json; multi-word queries are split into tokens and only the first 5 tokens are tried.
  • npm supports real full-text search through the public registry search endpoint and is the broader-recall half of this channel.
  • Descriptions are truncated to 300 characters for snippets, and PyPI README-sized description content is intentionally excluded in favor of the shorter summary.

Quality Bar

  • Evidence items have non-empty title and url.
  • No crash on empty or malformed API response.
  • Source channel field matches the channel name.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
49
Repository forks
8
7-day trend score
25

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/0xmariowu/autosearch/package-search/badge)](https://verified-skill.com/skills/0xmariowu/autosearch/package-search)

Something wrong with this skill or its page? Tell us.