agentleFS
Sign inStart free
EskyeeEskyee/agentbot-opensource/skills/aeon-autoresearch/SKILL.md

aeon-autoresearch

Skill17 starsChanged 5 months agoMITView on GitHub

Evolve any installed skill by generating four variations along separate theses (better inputs / sharper output / more robust / rethink), scoring them on a weighted rubric, and applying the winner. Never downgrades a working skill — aborts cleanly if no variation improves the original. Use when an installed skill is producing low-signal output, hitting deprecated APIs, or feels stale. Triggers: "improve this skill", "evolve $skill", "auto-research my X", "regenerate variations".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If every variation scores ≤ original on Improvement, the skill aborts with AUTORESEARCH_NO_IMPROVEMENT.

    line 47

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

aeon-autoresearch

Self-improvement loop. Given a target SKILL.md, generates four parallel improved variations, scores each, applies the winner.

Inputs

ParamDescription
targetSkill name or path to SKILL.md. Required.
modeevolve (default) writes the diff. dry-run scores and prints, writes nothing.

The four variations

  • A — Better inputs: replace deprecated APIs, add fallbacks, fix broken endpoints.
  • B — Sharper output: tighter format, signal over noise, explicit verdicts, banned filler.
  • C — More robust: empty-data handling, retries, dedup state, rate-limit awareness.
  • D — Rethink: fundamentally different methodology for the same goal.

Each is a complete runnable SKILL.md. Frontmatter shape preserved.

Scoring

1-5 per axis, weighted total max 50:

AxisWeight
Improvement vs original3×
Output value2×
Clarity, data quality, robustness1.5× each
Conventions1×

Tie-break (within 2 points): prefer the variation making the biggest single improvement over many small ones.

Safety guarantee

If every variation scores ≤ original on Improvement, the skill aborts with AUTORESEARCH_NO_IMPROVEMENT. No file written. Working skills are never downgraded.

Preserves the original's core purpose, frontmatter shape, and declared env vars.

Versioning

Inside a git repo, changes land in a branch (autoresearch/${target}) — operator reviews the diff before merging. Outside a repo, the original is preserved at ${target}/SKILL.md.before-autoresearch for rollback.

Output

The diff, plus a report with the scoring table for all four variations and a one-paragraph rationale for the winner.

Pairs with aeon-skill-evals (surfaces what's underperforming) and aeon-skill-repair (deterministic bugs; autoresearch handles quality lifts).

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