agentleFS
Sign inStart free
xenodevexenodeve/xeno-skills/skills/ask-xeno/SKILL.md

ask-xeno

Skill2 starsChanged 20 days agoMITView on GitHub

The top of this library. Ask it which family your task belongs to, then take the family's own route from there. Reach for it when you are unsure which skill applies, when a task spans families, or when you suspect a skill exists for this and cannot name it. Deliberately thin — it names the family entries and nothing else, so it stays cheap enough to carry everywhere. Triggers include "is there a skill for X", "which skill should I use", "how do we do X here", and any moment you are about to improvise a process this library already encodes.

Create a free account to mount
Files
SKILL.md

Ask Xeno

The entries. Pick one and follow its route — the detail lives there, not here.

You are…Enter at
Working in a T4 repo — building a feature, filing an issue or PR, recording a decision, picking up where a session left off, running unattended, or writing anything the developer readsusing-t4
Handing work to another agent — executing a scoped subtask, convening a panel for judgment, or hunting a bug across agentsusing-clink
Designing a web UI — prototyping, micro-UI rules, auditing, layout reasoningusing-design; anti-slop using-anti-slop; 3D/motion using-web3d
Writing code, in any repokarpathy-guidelines — simplest thing that works, surgical diffs, verifiable success criteria
Auditing a codebase for vulnerabilities — a full security audit or pen-testusing-security-audit — Cloudflare's skill, installed on demand
Running as Qwen3.8 (27B or Flash-Next) — the session's model is the local Qwen, through Claude Codeusing-qwen38 — the map from task to skill to gate (qwen38-think first, qwen38-claude-code before the first tool call, then design-ship-gate or qwen38-code-gate), and the four rules that model needs written down
Writing a skill for Qwen3.8 — a skill a small, literal model will followqwen38-skill-style — enumerate, command + pass condition, fixed done-report, one with/without pair

This file stays thin on purpose. Each family entry already carries its own map and its own rules; restating them here would create a second copy that drifts from the first. If you find yourself wanting to add detail to this table, it belongs in the family entry instead.

When nothing here fits, say so and use the general skills directly. A skill invoked because it was the nearest one is worse than none — it makes the wrong process look chosen.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free