LeoYeAI/agent-master-skills / skills/autoresearch-agent
autoresearch-agent
VerifiedAutonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
| File | Kind | Size |
|---|---|---|
| CLAUDE.md | markdown | 1.8 KB |
| SKILL.md | skill md | 12.0 KB |
| _meta.json | config | 296 B |
| agents/experiment-runner.md | markdown | 3.2 KB |
| evaluators/benchmark_size.py | script | 1.9 KB |
| evaluators/benchmark_speed.py | script | 1.2 KB |
| evaluators/build_speed.py | script | 1.1 KB |
| evaluators/llm_judge_content.py | script | 2.7 KB |
| evaluators/llm_judge_copy.py | script | 4.4 KB |
| evaluators/llm_judge_prompt.py | script | 3.0 KB |
| evaluators/memory_usage.py | script | 1.6 KB |
| evaluators/test_pass_rate.py | script | 1.5 KB |
| references/experiment-domains.md | markdown | 6.5 KB |
| references/program-template.md | markdown | 4.7 KB |
| scripts/log_results.py | script | 15.0 KB |
| scripts/run_experiment.py | script | 9.6 KB |
| scripts/setup_experiment.py | script | 14.0 KB |
| settings.json | config | 672 B |
evaluators/benchmark_speed.py
View on GitHub#!/usr/bin/env python3
"""Measure execution speed of a target function or command.
DO NOT MODIFY after experiment starts — this is the fixed evaluator."""
import statistics
import subprocess
import sys
import time
# --- CONFIGURE THESE ---
COMMAND = "python src/module.py" # Command to benchmark
RUNS = 5 # Number of runs
WARMUP = 1 # Warmup runs (not counted)
# --- END CONFIG ---
times = []
# Warmup
for _ in range(WARMUP):
subprocess.run(COMMAND, shell=True, capture_output=True, timeout=120)
# Benchmark
for i in range(RUNS):
t0 = time.perf_counter()
result = subprocess.run(COMMAND, shell=True, capture_output=True, timeout=120)
elapsed = (time.perf_counter() - t0) * 1000 # ms
if result.returncode != 0:
print(f"Run {i+1} failed (exit {result.returncode})", file=sys.stderr)
print(f"stderr: {result.stderr.decode()[:200]}", file=sys.stderr)
sys.exit(1)
times.append(elapsed)
p50 = statistics.median(times)
p95 = sorted(times)[int(len(times) * 0.95)] if len(times) >= 5 else max(times)
print(f"p50_ms: {p50:.2f}")
print(f"p95_ms: {p95:.2f}")
print(f"runs: {RUNS}")
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |