Skip to content
mcp/skillhub

Agent Skill

Search skill

searchtaishi-i/awesome-ChatGPT-repositoriesplugins/awesome-chatgpt-search/skills/search/SKILL.md

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

3.3kCC0-1.0

always on

59 tokname + description

once used

3,941 tokSKILL.md body

bundled files

11 KB

repo stars

3.3kGitHub

Install the Search skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/taishi-i/awesome-ChatGPT-repositories --skill search

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/taishi-i/awesome-ChatGPT-repositories.git /tmp/awesome-ChatGPT-repositories
mkdir -p ~/.claude/skills
cp -R /tmp/awesome-ChatGPT-repositories/plugins/awesome-chatgpt-search/skills/search ~/.claude/skills/search

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description59 tok
When the agent uses itThe SKILL.md instructions3,941 tok
Only if opened1 bundled files (1 KB)varies

Until it is used, search costs about 23× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 3 skills from taishi-i/awesome-ChatGPT-repositories would load 201 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Instructions
  • Step 1 — Interpret the query
  • Step 2 — Search the data files with grep
  • Step 3 — Filter by language (if language:<lang> was given)
  • Step 4 — Score candidates
  • Step 5a — Re-rank with your judgment
  • Step 5b — List categories (only if query was list categories / categories)
  • Step 6 — Format the output
  • Step 7 — Output use-case selection guide

More skills from taishi-i/awesome-ChatGPT-repositories

All skills in this repo
  1. awesome-chatgpttaishi-i/awesome-ChatGPT-repositories

    Search this repository's awesome-ChatGPT-repositories list for open-source ChatGPT and LLM projects such as RAG frameworks, agents, chatbots, CLIs, prompts, and browser extensions. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, or AI development; not for editing or adding list entries.

    3.3k79 tok idle · 120 in use
  2. awesome-chatgpt-searchtaishi-i/awesome-ChatGPT-repositories

    Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

    3.3k63 tok idle · 3,958 in use