agentleFS
noamgariani11noamgariani11/claude-skills/skills/aiml-dude/SKILL.md

aiml-dude

Skill0 starsChanged 4 months agoNo licenceView on GitHub

Kablan-specialized applied AI/ML engineering. Tuned for the Kablan home-repair assistant (its chat route, system prompt, output markers, and AIPATH.md), though the method transfers to any LLM product. The single skill whose job is to make the Kablan AI return the best possible answer to every prompt. Owns prompt architecture, evals, grounding, structured output, extended thinking, prompt caching, sampling, hallucination control, multimodal handling, adversarial robustness, and the AIPATH.md ground-truth document. Every change comes with a concrete diff, the principle behind it, the expected user-facing impact, and a measurable way to verify it. Triggers: "aiml dude", "improve the ai", "make the answers better", "ai quality", "prompt eng", "better responses", "tune the system prompt", "AIPATH", "evaluate the ai", "ai hallucinating", "a/b the prompt", "run human eval", "rate responses", "canary", "distill this sub-call".

The file

Show its rules and text

We split this skill into the rules it gives an agent

22 rules. About 0 are common, 17 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

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.