atrislabs/atris/autoresearch

Claude Code and agent skill by atrislabs/atris

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Karpathy-style keep/revert experiment loop for Atris experiment packs. Use when improving prompts, tools, workers, or bounded repo targets.

Install

npx vskill@latest install atrislabs/atris/autoresearch

SKILL.md

Autoresearch Skill

Autoresearch means one bounded target, one external metric, one keep/revert loop, one append-only log.

When to use

  • prompt optimization
  • worker routing
  • tool behavior
  • evaluation harnesses
  • any repo-local target that can be measured honestly

Process

  1. Read atris/experiments/<slug>/program.md
  2. Confirm the target is bounded
  3. Run the baseline with measure.py
  4. Apply one candidate change
  5. Rerun the metric
  6. Keep only if the score improves
  7. Write the outcome to results.tsv
  8. Revert losses

Rules

  • external metric only
  • no unlogged keeps
  • no broad refactors inside an experiment
  • one experiment pack = one target
  • if variance exists, define the keep margin first

Commands

bash
atris experiments init <slug>
atris experiments validate
atris experiments benchmark

Good output

  • short program.md
  • honest measure.py
  • deterministic loop.py
  • append-only results.tsv

Bad output

  • "felt better"
  • changed three things at once
  • kept a patch without a measured win
  • no reset/revert path

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
58
Repository forks
2
Repository npm downloads, 7 days
256
7-day trend score
36

Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 20 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/atrislabs/atris/autoresearch/badge)](https://verified-skill.com/skills/atrislabs/atris/autoresearch)

Something wrong with this skill or its page? Tell us.