autoresearch-agent

Files (28)

• CLAUDE.md
• LICENSE
• SKILL.md
• _meta.json
• experiment-runner.md · agents/
• benchmark_size.py · evaluators/
• benchmark_speed.py · evaluators/
• build_speed.py · evaluators/
• llm_judge_content.py · evaluators/
• llm_judge_copy.py · evaluators/
• llm_judge_prompt.py · evaluators/
• memory_usage.py · evaluators/
• test_pass_rate.py · evaluators/
• experiment-domains.md · references/
• program-template.md · references/
• log_results.py · scripts/
• run_experiment.py · scripts/
• setup_experiment.py · scripts/
• settings.json
• LICENSE · skills/loop/
• SKILL.md · skills/loop/
• LICENSE · skills/resume/
• SKILL.md · skills/resume/
• LICENSE · skills/run/
• SKILL.md · skills/run/
• LICENSE · skills/setup/
• SKILL.md · skills/setup/
• SKILL.md · skills/status/

SKILL.md (first lines)

> **Attribution:** Sourced from [alirezarezvani/claude-skills](https://github.com/alirezarezvani/claude-skills) by [Alireza Rezvani](https://github.com/alirezarezvani).

# Autoresearch Agent

> You sleep. The agent experiments. You wake up to results.

Autonomous experiment loop inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely.

Not one guess — fifty measured attempts, compounding.

---

## Slash Commands

| Command | What it does |
|---------|-------------|
| `/ar:setup` | Set up a new experiment interactively |
| `/ar:run` | Run a single experiment iteration |
| `/ar:loop` | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) |
| `/ar:status` | Show dashboard and results |
| `/ar:resume` | Resume a paused experiment |

---

## When This Skill Activates

Recognize these patterns from the user:

- "Make this faster / smaller / better"
- "Optimize [file] for [metric]"
- "Improve my [headlines / copy / prompts]"
- "Run experiments overnight"
- "I want to get [metric] from X to Y"
- Any request involving: optimize, benchmark, improve, experiment loop, autoresearch

If the user describes a target file + a way to measure success → this skill applies.

---

## Setup

### First Time — Create the Experiment

Run the setup script. The user decides where experiments live:

**Project-level** (inside repo, git-tracked, shareable with team):
```bash
python scripts/setup_experiment.py \
  --domain engineering \
  --name api-speed \
  --target src/api/search.py \
  --eval "pytest bench.py --tb=no -q" \
  --metric p50_ms \
  --direction lower \
  --scope project
```

**User-level** (personal, in `~/.autoresearch/`):
```bash
python scripts/setup_experiment.py \
  --domain marketing \
  --name medium-ctr \
  --target content/titles.md \
  --eval "python evaluate.py" \
  --metric ctr_score \
  --direction higher \
  --evaluator llm_judge_content \
  --scope user
```

The `--scope` flag determines where `.autoresearch/` lives:
- `project` (default) → `.autoresearch/` in the repo root. Experiment definitions are git-tracked. Results are gitignored.
- `user` → `~/.autoresearch/` in the home directory. Everything is personal.

### What Setup Creates

```
.autoresearch/
├── config.yaml                        ← Global settings
├── .gitignore                         ← Ignores results.tsv, *.log
└── {domain}/{experiment-name}/
    ├── program.md                     ← Objectives, constraints, strategy
    ├── config.cfg                     ← Target, eval cmd, metric, direction
    ├── results.tsv                    ← Experiment log (gitignored)
    └── evaluate.py                    ← Evaluation script (if --evaluator used)
```

**results.tsv columns:** `commit | metric | status | description`
- `commit` — short git hash
- `metric` — float value or "N/A" for crashes
- `status` — keep | discard | crash
- `description` — what changed or why it crashed

### Domains

| Domain | Use Cases |
|--------|-----------|
| `engineering` | Code speed, memory, bundle size, test pass rate, build time |
| `marketing` | Headlines, social copy, email subjects, ad copy, engagement |
| `content` | Article structure, SEO descriptions, readability, CTR |
| `prompts` | System prompts, chatbot tone, agent instructions |
| `custom` | Anything else with a measurable metric |

### If `program.md` Already Exists

The user may have written their own `program.md`. If found in the experiment directory, read it. It overrides the template. Only ask for what's missing.

---

## Agent Protocol

You are the loop. The scripts handle setup and evaluation — you handle the creative work.

### Before Starting
1. Read `.autoresearch/{domain}/{name}/config.cfg` to get:
   - `target` — the file you edit
   - `evaluate_cmd` — the command that measures your changes
   - `metric` — the metric name to look for in eval output
   - `metric_direction` — "lower" or "higher" is better

From mouadja02/skills, MIT.

More from mouadja02/skills