AI WorkflowĐộ khó: advanced

Autoresearch

Stateful single-mission improvement loop with strict evaluator contract — runs until a measurable goal is achieved or max runtime is reached.

Dùng được với:Claude

Khi nào dùng

Use for optimisation tasks with a measurable evaluator — e.g., improve Lighthouse score, reduce bundle size, increase test coverage, improve benchmark results.

Ví dụ sử dụng

Skill: autoresearch — define mission + evaluator command; it loops improve→evaluate→improve until the goal is met.

Select Model

<skill name="Autoresearch">
<purpose>
# Autoresearch Skill

## Overview
Autoresearch is a stateful improvement loop with a strict evaluator contract. You define a mission (what to improve) and an evaluator (a command that measures success). The skill loops until the evaluator passes or max runtime is reached.

## The Loop
```
Mission defined → Baseline evaluation
while (evaluator fails AND time remaining):
  1. Generate improvement hypothesis
  2. Implement change
  3. Run evaluator
  4. Record result in decision log
  5. If better: keep change; if worse: revert
  6. Repeat with new hypothesis
```

## How to Invoke
```
Skill: autoresearch
Mission: Improve Lighthouse performance score from 72 to 90+
Evaluator: npm run lighthouse
Max runtime: 2 hours
```

## Evaluator Requirements
The evaluator must:
- Be a runnable shell command
- Return exit code 0 on success, non-zero on failure
- Produce consistent, reproducible results

## Output Artifacts
- `.omc/autoresearch/decision-log.md`: Every hypothesis tried + result
- Final state of improved code
- Summary of changes made
</purpose>
</skill>

Tải .md

Khi nào dùng

Ví dụ sử dụng

Skill liên quan