skill-mesh

Provider-neutral skill pipeline (Claude, GitHub Copilot/GPT, OpenAI Codex) for autonomous plan -> build -> review -> ship: 57 skills (54…

A new way for AI to search for data
View on GitHub
2GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 2e7f325096 (2026-09-23).

Selected work

aberson
@aberson

“Restore reviewed Codex deep route with bounded validation exception”. 7 files, 530 lines in tests, tools.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-21. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

agentic-workflowsclaudeclaude-codedeveloper-toolsllmpythonai-agentsgithub-copilot

Example questions

The prompt

Paste it into your AI agent. It clones aberson/skill-mesh at the pinned commit and indexes it on your machine.

Search the GitHub repository aberson/skill-mesh with XERJ (https://hub.xerj.org/corpus/aberson--skill-mesh).
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/aberson/skill-mesh skill-mesh && git -C skill-mesh checkout 2e7f3250965d9b7da04fa72edd72d587463f4a4d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./skill-mesh --url http://127.0.0.1:9200 --prefix skill-mesh --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

Selected work and consent: the XERJ registry.