agent-skills
48 Agent Skills: roast your GitHub, bisect bugs, record demo GIFs, write Playwright e2e tests, grill specs, catch AI slop and risky CI. Tested, one-line install. Claude Code, Cline, Cursor, Codex
What XERJ indexed
Snapshot
The whole repository at commit 7c7d700359 (2026-10-25). main is 24 commits ahead.
Selected work
“all 51 skills in one repo (skills/), Claude Code plugin marketp…”. 15 files, 922 lines in skills, scripts, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
agent-skillsai-agentsclaude-codeclaude-skillsclinecursorskill-mdinstagram
Example questions
- How does agent-skills implement ai-agents?
- What does skills do in agent-skills?
- Show the claude-code code in agent-skills.
Inside the indexed corpus
- Languages by size: Python 97%, Shell 1.8%, TypeScript 0.6%, Tape 0.1%, JavaScript 0.1%.
- On GitHub since 2026-10-25, last push 2026-10-29, 30 commits on main.
- The pin is 24 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for milad-ahmd/agent-skills on 2026-10-29, and the LICENSE file at commit 7c7d700359 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Milad (@milad-ahmd) has 1 selected repository on the hub.
Using XERJ with agent-skills
- A local search tool for Codex and Cursor agent-skills is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones milad-ahmd/agent-skills at the pinned commit and indexes it on your machine.
Search the GitHub repository milad-ahmd/agent-skills with XERJ (https://hub.xerj.org/corpus/milad-ahmd--agent-skills). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/milad-ahmd/agent-skills agent-skills && git -C agent-skills checkout 7c7d700359e1d04d01ef82db3b3617710c2a4a25 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./agent-skills --url http://127.0.0.1:9200 --prefix agent-skills --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
MiladAI, prompts and agents corporaxerj-blogpostsvanguard-context-burnfaahcalven-ai/marketing-as-codeGrit-77/done-is-a-claimtomtom87/latest
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.