OpenSkillIndex← back to search
claude-code

Autosearch valid_channel

<!-- Self-written, plan autosearch-0418-channels-and-skills.md § F001 -->

install
source · Clone the upstream repo
git clone https://github.com/0xmariowu/Autosearch
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/0xmariowu/Autosearch "$T" && mkdir -p ~/.claude/skills && cp -r "$T/tests/fixtures/skills/valid_channel" ~/.claude/skills/0xmariowu-autosearch-valid-channel && rm -rf "$T"
manifest: tests/fixtures/skills/valid_channel/SKILL.md
source content
<!-- Self-written, plan autosearch-0418-channels-and-skills.md § F001 -->

name: valid_channel description: Use for bilingual paper-style searches that may need a detail lookup. version: 1 languages: [zh, en] methods:

  • id: api_search impl: methods/api_search.py requires: [env:ARXIV_TOKEN] rate_limit: per_min: 30 per_hour: 500
  • id: api_detail impl: methods/api_detail.py requires: [cookie:arxiv_session] rate_limit: per_min: 10 fallback_chain: [api_search, api_detail] when_to_use: query_languages: [zh, en] query_types: [academic-papers, literature-review] domain_hints: [citations, scholarly-search] avoid_for: [real-time-news] quality_hint: typical_yield: medium-high chinese_native: false layer: leaf domains: [academic] scenarios: [paper-search, detail-hydration] model_tier: Standard tier: 1 fix_hint: "autosearch configure ARXIV_TOKEN <value>"

Prefer the search endpoint first, then hydrate selected records with the detail method. Keep body prose descriptive only.