SkillAgentSearch skills...

lab:autoresearch

Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.

Install / Use

npx skills add oliver-kriska/claude-elixir-phoenix --skill autoresearch

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Category

Marketing

Supported Platforms

Universal

Our assessment of lab:autoresearch

lab:autoresearch scores 87/100 on our quality scale, 347th of 652 Marketing skills we index.

Its SKILL.md is 4.5 KB long, well organised into 18 sections with 5 code examples: a solid amount of guidance for an agent.

It has 574 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 12 days ago, so lab:autoresearch is actively maintained.
  • Our last check on 2026-11-01 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

lab:autoresearch compared with similar skills

All 4 of these similar skills score higher than lab:autoresearch; compare them before choosing.

SkillScoreStarsUpdatedFormat
lab:autoresearch (this skill)by oliver-kriska8757412d agoSKILL.md
Agent-Reachby Panniantong100113.0k10d agoCLAUDE.md
algorithmic-artby anthropics100177.9k57d agoSKILL.md
pptxby anthropics100177.9k57d agoSKILL.md
prospectingby coreyhaines3110060.1k7d agoSKILL.md

Frequently asked questions

How do I install lab:autoresearch?
Run npx skills add oliver-kriska/claude-elixir-phoenix --skill "lab:autoresearch". The install tabs above show the steps for each supported agent.
Which AI agents does lab:autoresearch work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is lab:autoresearch safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is lab:autoresearch still maintained?
The repository was last updated 12 days ago, so lab:autoresearch is actively maintained.

name: lab:autoresearch description: > Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs. effort: high argument-hint: "[--skill NAME] [--strategy targeted|sweep|random] [--dry-run] [--max-iterations N]" disable-model-invocation: true

Autoresearch — Plugin Skill Self-Improvement

Iteratively improve plugin skills via the autoresearch pattern: propose one mutation -> eval -> keep/revert -> repeat.

Usage

/lab:autoresearch                           # Targeted: attack weakest skill+dimension
/lab:autoresearch --skill review            # Focus on one skill
/lab:autoresearch --strategy sweep          # Process all skills alphabetically
/lab:autoresearch --dry-run                 # Show what would change, don't commit

For overnight runs:

/loop 5m /lab:autoresearch --strategy sweep --max-iterations 200

Iron Laws

  1. ONE mutation per iteration — if description needs "and", split into two
  2. NEVER mutate read-only files — check program.md before every write
  3. EVAL is deterministic — always use the wrapper script, never LLM-judge
  4. REVERT on regression OR checks failure — no exceptions
  5. LOG every iteration — use keep or revert command (never skip)
  6. CHECK ideas.md before proposing — don't rediscover known optimizations

Wrapper Script Commands

All eval/git/journal operations go through ONE script. Do NOT run these manually.

# Find the weakest skill+dimension
python3 lab/autoresearch/scripts/run-iteration.py target --strategy targeted

# Score a skill (before mutation, to get baseline)
python3 lab/autoresearch/scripts/run-iteration.py score <skill-name>

# After mutation: score + checks + compare → verdict (KEEP or REVERT)
python3 lab/autoresearch/scripts/run-iteration.py eval <skill-name>

# Act on verdict:
python3 lab/autoresearch/scripts/run-iteration.py keep <skill> <dim> <old> <new> \
  --desc "what changed" --asi '{"hypothesis": "why", "mechanism": "how"}'

python3 lab/autoresearch/scripts/run-iteration.py revert <skill> <dim> <old> <new> \
  --desc "what was attempted" --asi '{"hypothesis": "why", "regression": "what broke", "avoid": "do not retry this"}'

# Check overall progress
python3 lab/autoresearch/scripts/run-iteration.py status

Core Loop (ONE iteration)

Step 1: Read State

  1. Read lab/autoresearch/program.md (goals, mutable surface, rules)
  2. Read lab/autoresearch/ideas.md if it exists (deferred optimizations)
  3. Run: python3 lab/autoresearch/scripts/run-iteration.py status

Step 2: Select Target

Run: python3 lab/autoresearch/scripts/run-iteration.py target --strategy targeted

Parse the JSON: skill, dimension, failing_checks. If all_perfect → STOP.

Step 3: Read + Propose

  1. Read target SKILL.md and its references/ listing
  2. Read eval definition from lab/eval/evals/{skill}.json
  3. Check ideas.md for deferred ideas about this skill
  4. Check recent journal entries for prior failures on this skill (avoid repeats)
  5. Consult ${CLAUDE_SKILL_DIR}/references/mutation-strategies.md
  6. Propose exactly ONE change targeting the failing checks

Step 4: Apply + Evaluate

  1. Apply the mutation via Edit tool
  2. Run: python3 lab/autoresearch/scripts/run-iteration.py eval <skill-name>
  3. Parse JSON → check verdict field

Step 5: Keep or Revert

If verdict is KEEP:

python3 lab/autoresearch/scripts/run-iteration.py keep <skill> <dim> <old> <new> \
  --desc "..." --asi '{"hypothesis": "...", "mechanism": "..."}'

If verdict is REVERT:

python3 lab/autoresearch/scripts/run-iteration.py revert <skill> <dim> <old> <new> \
  --desc "..." --asi '{"hypothesis": "...", "regression": "...", "avoid": "..."}'

Step 6: Ideas Backlog

If during analysis you discovered a promising optimization you can't act on now:

  • Append it to lab/autoresearch/ideas.md as a bullet
  • On next resume: prune stale/tried ideas, experiment with the rest

Step 7: Continue or Stop

  • All targets >= 0.95? Print "AUTORESEARCH_COMPLETE"
  • Max iterations reached? Print "AUTORESEARCH_COMPLETE"
  • 50 consecutive discards? Print "AUTORESEARCH_STUCK"
  • Otherwise: immediately start Step 1 again

References

  • ${CLAUDE_SKILL_DIR}/references/mutation-strategies.md — mutation type catalog
  • ${CLAUDE_SKILL_DIR}/references/state-management.md — git protocol, journaling
  • lab/autoresearch/program.md — research agenda (read every iteration)

Related Skills

View on GitHub
GitHub Stars574
CategoryMarketing
Updated12d ago
Forks45

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions