agentleFS
Sign inStart free
thistleknotthistleknot/skills/axiom-ladder-search/SKILL.md

axiom-ladder-search

Skill0 starsChanged 6 months agoNo licenceView on GitHub

Round-based parameter search for expensive, human-judged systems. Sample ONE axiom, rank the top 3, make those winners fixed BASES, then cross them against a DIFFERENT axiom -- expanding into new dimensions each round rather than drilling the winner's own axis. Carries winners forward re-run under identical conditions so "did we improve" is answerable. Use when each evaluation is slow or costly (image/video generation, model training, physical process tuning), the quality bar is a human eye rather than a metric, and a full cartesian grid is unaffordable. Covers proving an axis is live before sweeping it, ablation when parameters look inert, iso-cost banding to trade one resource against another fairly, and why an automated score is a second opinion. Trigger on "grid search", "sweep these settings", "top 3 then expand", "partition the variance", "which parameter matters", or a sweep whose cells come back identical.

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 16 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈16

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    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 350,495 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.

Check your setup, free