[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KPC5APBJYPF3J238T8VG5Z":3,"skill-same:01M6KPC5APBJYPF3J238T8VG5Z":147},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6KPC5APBJYPF3J238T8VG5Z","autoresearch-agent",null,"Autonomous 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\u002Fimage 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.","Boboegg\u002Fai-resources","Boboegg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F171472260?v=4","01M6KMJYEA4SVHDTXRTH3HZANA","曾柏儒","01M6KMJYJ4231XB9W048VZ8RBB",1,"MIT","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"autoresearch","autoresearch agent","command","rate","reduce","improvement loop","loops","ctr","reset","optimize","karpathy","autonomous","image","loop","improve","Evaluation","git","code","run","commit","2026-11-10 10:12:30",false,"---\nname: \"autoresearch-agent\"\ndescription: \"Autonomous 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\u002Fimage 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.\"\nlicense: MIT\nmetadata:\n  version: 2.0.0\n  author: Alireza Rezvani\n  category: engineering\n  updated: 2026-03-13\n---\n\n# Autoresearch Agent\n\n> You sleep. The agent experiments. You wake up to results.\n\nAutonomous experiment loop inspired by [Karpathy's autoresearch](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fautoresearch). The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely.\n\nNot one guess — fifty measured attempts, compounding.\n\n---\n\n## Slash Commands\n\n| Command | What it does |\n|---------|-------------|\n| `\u002Far:setup` | Set up a new experiment interactively |\n| `\u002Far:run` | Run a single experiment iteration |\n| `\u002Far:loop` | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) |\n| `\u002Far:status` | Show dashboard and results |\n| `\u002Far:resume` | Resume a paused experiment |\n\n---\n\n## When This Skill Activates\n\nRecognize these patterns from the user:\n\n- \"Make this faster \u002F smaller \u002F better\"\n- \"Optimize [file] for [metric]\"\n- \"Improve my [headlines \u002F copy \u002F prompts]\"\n- \"Run experiments overnight\"\n- \"I want to get [metric] from X to Y\"\n- Any request involving: optimize, benchmark, improve, experiment loop, autoresearch\n\nIf the user describes a target file + a way to measure success → this skill applies.\n\n---\n\n## Setup\n\n### First Time — Create the Experiment\n\nRun the setup script. The user decides where experiments live:\n\n**Project-level** (inside repo, git-tracked, shareable with team):\n```bash\npython scripts\u002Fsetup_experiment.py \\\n  --domain engineering \\\n  --name api-speed \\\n  --target src\u002Fapi\u002Fsearch.py \\\n  --eval \"pytest bench.py --tb=no -q\" \\\n  --metric p50_ms \\\n  --direction lower \\\n  --scope project\n```\n\n**User-level** (personal, in `~\u002F.autoresearch\u002F`):\n```bash\npython scripts\u002Fsetup_experiment.py \\\n  --domain marketing \\\n  --name medium-ctr \\\n  --target content\u002Ftitles.md \\\n  --eval \"python evaluate.py\" \\\n  --metric ctr_score \\\n  --direction higher \\\n  --evaluator llm_judge_content \\\n  --scope user\n```\n\nThe `--scope` flag determines where `.autoresearch\u002F` lives:\n- `project` (default) → `.autoresearch\u002F` in the repo root. Experiment definitions are git-tracked. Results are gitignored.\n- `user` → `~\u002F.autoresearch\u002F` in the home directory. Everything is personal.\n\n### What Setup Creates\n\n```\n.autoresearch\u002F\n├── config.yaml                        ← Global settings\n├── .gitignore                         ← Ignores results.tsv, *.log\n└── {domain}\u002F{experiment-name}\u002F\n    ├── program.md                     ← Objectives, constraints, strategy\n    ├── config.cfg                     ← Target, eval cmd, metric, direction\n    ├── results.tsv                    ← Experiment log (gitignored)\n    └── evaluate.py                    ← Evaluation script (if --evaluator used)\n```\n\n**results.tsv columns:** `commit | metric | status | description`\n- `commit` — short git hash\n- `metric` — float value or \"N\u002FA\" for crashes\n- `status` — keep | discard | crash\n- `description` — what changed or why it crashed\n\n### Domains\n\n| Domain | Use Cases |\n|--------|-----------|\n| `engineering` | Code speed, memory, bundle size, test pass rate, build time |\n| `marketing` | Headlines, social copy, email subjects, ad copy, engagement |\n| `content` | Article structure, SEO descriptions, readability, CTR |\n| `prompts` | System prompts, chatbot tone, agent instructions |\n| `custom` | Anything else with a measurable metric |\n\n### If `program.md` Already Exists\n\nThe 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.\n\n---\n\n## Agent Protocol\n\nYou are the loop. The scripts handle setup and evaluation — you handle the creative work.\n\n### Before Starting\n1. Read `.autoresearch\u002F{domain}\u002F{name}\u002Fconfig.cfg` to get:\n   - `target` — the file you edit\n   - `evaluate_cmd` — the command that measures your changes\n   - `metric` — the metric name to look for in eval output\n   - `metric_direction` — \"lower\" or \"higher\" is better\n   - `time_budget_minutes` — max time per evaluation\n2. Read `program.md` for strategy, constraints, and what you can\u002Fcannot change\n3. Read `results.tsv` for experiment history (columns: commit, metric, status, description)\n4. Checkout the experiment branch: `git checkout autoresearch\u002F{domain}\u002F{name}`\n\n### Each Iteration\n1. Review results.tsv — what worked? What failed? What hasn't been tried?\n2. Decide ONE change to the target file. One variable per experiment.\n3. Edit the target file\n4. Commit: `git add {target} && git commit -m \"experiment: {description}\"`\n5. Evaluate: `python scripts\u002Frun_experiment.py --experiment {domain}\u002F{name} --single`\n6. Read the output — it prints KEEP, DISCARD, or CRASH with the metric value\n7. Go to step 1\n\n### What the Script Handles (you don't)\n- Running the eval command with timeout\n- Parsing the metric from eval output\n- Comparing to previous best\n- Reverting the commit on failure (`git reset --hard HEAD~1`)\n- Logging the result to results.tsv\n\n### Starting an Experiment\n\n```bash\n# Single iteration (the agent calls this repeatedly)\npython scripts\u002Frun_experiment.py --experiment engineering\u002Fapi-speed --single\n\n# Dry run (test setup before starting)\npython scripts\u002Frun_experiment.py --experiment engineering\u002Fapi-speed --dry-run\n```\n\n### Strategy Escalation\n- Runs 1-5: Low-hanging fruit (obvious improvements, simple optimizations)\n- Runs 6-15: Systematic exploration (vary one parameter at a time)\n- Runs 16-30: Structural changes (algorithm swaps, architecture shifts)\n- Runs 30+: Radical experiments (completely different approaches)\n- If no improvement in 20+ runs: update program.md Strategy section\n\n### Self-Improvement\nAfter every 10 experiments, review results.tsv for patterns. Update the\nStrategy section of program.md with what you learned (e.g., \"caching changes\nconsistently improve by 5-10%\", \"refactoring attempts never improve the metric\").\nFuture iterations benefit from this accumulated knowledge.\n\n### Stopping\n- Run until interrupted by the user, context limit reached, or goal in program.md is met\n- Before stopping: ensure results.tsv is up to date\n- On context limit: the next session can resume — results.tsv and git log persist\n\n### Rules\n\n- **One change per experiment.** Don't change 5 things at once. You won't know what worked.\n- **Simplicity criterion.** A small improvement that adds ugly complexity is not worth it. Equal performance with simpler code is a win. Removing code that gets same results is the best outcome.\n- **Never modify the evaluator.** `evaluate.py` is the ground truth. Modifying it invalidates all comparisons. Hard stop if you catch yourself doing this.\n- **Timeout.** If a run exceeds 2.5× the time budget, kill it and treat as crash.\n- **Crash handling.** If it's a typo or missing import, fix and re-run. If the idea is fundamentally broken, revert, log \"crash\", move on. 5 consecutive crashes → pause and alert.\n- **No new dependencies.** Only use what's already available in the project.\n\n---\n\n## Evaluators\n\nReady-to-use evaluation scripts. Copied into the experiment directory during setup with `--evaluator`.\n\n### Free Evaluators (no API cost)\n\n| Evaluator | Metric | Use Case |\n|-----------|--------|----------|\n| `benchmark_speed` | `p50_ms` (lower) | Function\u002FAPI execution time |\n| `benchmark_size` | `size_bytes` (lower) | File, bundle, Docker image size |\n| `test_pass_rate` | `pass_rate` (higher) | Test suite pass percentage |\n| `build_speed` | `build_seconds` (lower) | Build\u002Fcompile\u002FDocker build time |\n| `memory_usage` | `peak_mb` (lower) | Peak memory during execution |\n\n### LLM Judge Evaluators (uses your subscription)\n\n| Evaluator | Metric | Use Case |\n|-----------|--------|----------|\n| `llm_judge_content` | `ctr_score` 0-10 (higher) | Headlines, titles, descriptions |\n| `llm_judge_prompt` | `quality_score` 0-100 (higher) | System prompts, agent instructions |\n| `llm_judge_copy` | `engagement_score` 0-10 (higher) | Social posts, ad copy, emails |\n\nLLM judges call the CLI tool the user is already running (Claude, Codex, Gemini). The evaluation prompt is locked inside `evaluate.py` — the agent cannot modify it. This prevents the agent from gaming its own evaluator.\n\nThe user's existing subscription covers the cost:\n- Claude Code Max → unlimited Claude calls for evaluation\n- Codex CLI (ChatGPT Pro) → unlimited Codex calls\n- Gemini CLI (free tier) → free evaluation calls\n\n### Custom Evaluators\n\nIf no built-in evaluator fits, the user writes their own `evaluate.py`. Only requirement: it must print `metric_name: value` to stdout.\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# My custom evaluator — DO NOT MODIFY after experiment starts\nimport subprocess\nresult = subprocess.run([\"my-benchmark\", \"--json\"], capture_output=True, text=True)\n# Parse and output\nprint(f\"my_metric: {parse_score(result.stdout)}\")\n```\n\n---\n\n## Viewing Results\n\n```bash\n# Single experiment\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed\n\n# All experiments in a domain\npython scripts\u002Flog_results.py --domain engineering\n\n# Cross-experiment dashboard\npython scripts\u002Flog_results.py --dashboard\n\n# Export formats\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed --format csv --output results.csv\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed --format markdown --output results.md\npython scripts\u002Flog_results.py --dashboard --format markdown --output dashboard.md\n```\n\n### Dashboard Output\n\n```\nDOMAIN          EXPERIMENT          RUNS  KEPT  BEST         Δ FROM START  STATUS\nengineering     api-speed            47    14   185ms        -76.9%        active\nengineering     bundle-size          23     8   412KB        -58.3%        paused\nmarketing       medium-ctr           31    11   8.4\u002F10       +68.0%        active\nprompts         support-tone         15     6   82\u002F100       +46.4%        done\n```\n\n### Export Formats\n\n- **TSV** — default, tab-separated (compatible with spreadsheets)\n- **CSV** — comma-separated, with proper quoting\n- **Markdown** — formatted table, readable in GitHub\u002Fdocs\n\n---\n\n## Proactive Triggers\n\nFlag these without being asked:\n\n- **No evaluation command works** → Test it before starting the loop. Run once, verify output.\n- **Target file not in git** → `git init && git add . && git commit -m 'initial'` first.\n- **Metric direction unclear** → Ask: is lower or higher better? Must know before starting.\n- **Time budget too short** → If eval takes longer than budget, every run crashes.\n- **Agent modifying evaluate.py** → Hard stop. This invalidates all comparisons.\n- **5 consecutive crashes** → Pause the loop. Alert the user. Don't keep burning cycles.\n- **No improvement in 20+ runs** → Suggest changing strategy in program.md or trying a different approach.\n\n---\n\n## Installation\n\n### One-liner (any tool)\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills.git\ncp -r claude-skills\u002Fengineering\u002Fautoresearch-agent ~\u002F.claude\u002Fskills\u002F\n```\n\n### Multi-tool install\n```bash\n.\u002Fscripts\u002Fconvert.sh --skill autoresearch-agent --tool codex|gemini|cursor|windsurf|openclaw\n```\n\n### OpenClaw\n```bash\nclawhub install cs-autoresearch-agent\n```\n\n---\n\n## Related Skills\n\n- **self-improving-agent** — improves an agent's own memory\u002Frules over time. NOT for structured experiment loops.\n- **senior-ml-engineer** — ML architecture decisions. Complementary — use for initial design, then autoresearch for optimization.\n- **tdd-guide** — test-driven development. Complementary — tests can be the evaluation function.\n- **skill-security-auditor** — audit skills before publishing. NOT for optimization loops.\n","# Autoresearch Agent\n\n> You sleep. The agent experiments. You wake up to results.\n\nAutonomous experiment loop inspired by [Karpathy's autoresearch](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fautoresearch). The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely.\n\nNot one guess — fifty measured attempts, compounding.\n\n---\n\n## Slash Commands\n\n| Command | What it does |\n|---------|-------------|\n| `\u002Far:setup` | Set up a new experiment interactively |\n| `\u002Far:run` | Run a single experiment iteration |\n| `\u002Far:loop` | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) |\n| `\u002Far:status` | Show dashboard and results |\n| `\u002Far:resume` | Resume a paused experiment |\n\n---\n\n## When This Skill Activates\n\nRecognize these patterns from the user:\n\n- \"Make this faster \u002F smaller \u002F better\"\n- \"Optimize [file] for [metric]\"\n- \"Improve my [headlines \u002F copy \u002F prompts]\"\n- \"Run experiments overnight\"\n- \"I want to get [metric] from X to Y\"\n- Any request involving: optimize, benchmark, improve, experiment loop, autoresearch\n\nIf the user describes a target file + a way to measure success → this skill applies.\n\n---\n\n## Setup\n\n### First Time — Create the Experiment\n\nRun the setup script. The user decides where experiments live:\n\n**Project-level** (inside repo, git-tracked, shareable with team):\n```bash\npython scripts\u002Fsetup_experiment.py \\\n  --domain engineering \\\n  --name api-speed \\\n  --target src\u002Fapi\u002Fsearch.py \\\n  --eval \"pytest bench.py --tb=no -q\" \\\n  --metric p50_ms \\\n  --direction lower \\\n  --scope project\n```\n\n**User-level** (personal, in `~\u002F.autoresearch\u002F`):\n```bash\npython scripts\u002Fsetup_experiment.py \\\n  --domain marketing \\\n  --name medium-ctr \\\n  --target content\u002Ftitles.md \\\n  --eval \"python evaluate.py\" \\\n  --metric ctr_score \\\n  --direction higher \\\n  --evaluator llm_judge_content \\\n  --scope user\n```\n\nThe `--scope` flag determines where `.autoresearch\u002F` lives:\n- `project` (default) → `.autoresearch\u002F` in the repo root. Experiment definitions are git-tracked. Results are gitignored.\n- `user` → `~\u002F.autoresearch\u002F` in the home directory. Everything is personal.\n\n### What Setup Creates\n\n```\n.autoresearch\u002F\n├── config.yaml                        ← Global settings\n├── .gitignore                         ← Ignores results.tsv, *.log\n└── {domain}\u002F{experiment-name}\u002F\n    ├── program.md                     ← Objectives, constraints, strategy\n    ├── config.cfg                     ← Target, eval cmd, metric, direction\n    ├── results.tsv                    ← Experiment log (gitignored)\n    └── evaluate.py                    ← Evaluation script (if --evaluator used)\n```\n\n**results.tsv columns:** `commit | metric | status | description`\n- `commit` — short git hash\n- `metric` — float value or \"N\u002FA\" for crashes\n- `status` — keep | discard | crash\n- `description` — what changed or why it crashed\n\n### Domains\n\n| Domain | Use Cases |\n|--------|-----------|\n| `engineering` | Code speed, memory, bundle size, test pass rate, build time |\n| `marketing` | Headlines, social copy, email subjects, ad copy, engagement |\n| `content` | Article structure, SEO descriptions, readability, CTR |\n| `prompts` | System prompts, chatbot tone, agent instructions |\n| `custom` | Anything else with a measurable metric |\n\n### If `program.md` Already Exists\n\nThe 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.\n\n---\n\n## Agent Protocol\n\nYou are the loop. The scripts handle setup and evaluation — you handle the creative work.\n\n### Before Starting\n1. Read `.autoresearch\u002F{domain}\u002F{name}\u002Fconfig.cfg` to get:\n   - `target` — the file you edit\n   - `evaluate_cmd` — the command that measures your changes\n   - `metric` — the metric name to look for in eval output\n   - `metric_direction` — \"lower\" or \"higher\" is better\n   - `time_budget_minutes` — max time per evaluation\n2. Read `program.md` for strategy, constraints, and what you can\u002Fcannot change\n3. Read `results.tsv` for experiment history (columns: commit, metric, status, description)\n4. Checkout the experiment branch: `git checkout autoresearch\u002F{domain}\u002F{name}`\n\n### Each Iteration\n1. Review results.tsv — what worked? What failed? What hasn't been tried?\n2. Decide ONE change to the target file. One variable per experiment.\n3. Edit the target file\n4. Commit: `git add {target} && git commit -m \"experiment: {description}\"`\n5. Evaluate: `python scripts\u002Frun_experiment.py --experiment {domain}\u002F{name} --single`\n6. Read the output — it prints KEEP, DISCARD, or CRASH with the metric value\n7. Go to step 1\n\n### What the Script Handles (you don't)\n- Running the eval command with timeout\n- Parsing the metric from eval output\n- Comparing to previous best\n- Reverting the commit on failure (`git reset --hard HEAD~1`)\n- Logging the result to results.tsv\n\n### Starting an Experiment\n\n```bash\n# Single iteration (the agent calls this repeatedly)\npython scripts\u002Frun_experiment.py --experiment engineering\u002Fapi-speed --single\n\n# Dry run (test setup before starting)\npython scripts\u002Frun_experiment.py --experiment engineering\u002Fapi-speed --dry-run\n```\n\n### Strategy Escalation\n- Runs 1-5: Low-hanging fruit (obvious improvements, simple optimizations)\n- Runs 6-15: Systematic exploration (vary one parameter at a time)\n- Runs 16-30: Structural changes (algorithm swaps, architecture shifts)\n- Runs 30+: Radical experiments (completely different approaches)\n- If no improvement in 20+ runs: update program.md Strategy section\n\n### Self-Improvement\nAfter every 10 experiments, review results.tsv for patterns. Update the\nStrategy section of program.md with what you learned (e.g., \"caching changes\nconsistently improve by 5-10%\", \"refactoring attempts never improve the metric\").\nFuture iterations benefit from this accumulated knowledge.\n\n### Stopping\n- Run until interrupted by the user, context limit reached, or goal in program.md is met\n- Before stopping: ensure results.tsv is up to date\n- On context limit: the next session can resume — results.tsv and git log persist\n\n### Rules\n\n- **One change per experiment.** Don't change 5 things at once. You won't know what worked.\n- **Simplicity criterion.** A small improvement that adds ugly complexity is not worth it. Equal performance with simpler code is a win. Removing code that gets same results is the best outcome.\n- **Never modify the evaluator.** `evaluate.py` is the ground truth. Modifying it invalidates all comparisons. Hard stop if you catch yourself doing this.\n- **Timeout.** If a run exceeds 2.5× the time budget, kill it and treat as crash.\n- **Crash handling.** If it's a typo or missing import, fix and re-run. If the idea is fundamentally broken, revert, log \"crash\", move on. 5 consecutive crashes → pause and alert.\n- **No new dependencies.** Only use what's already available in the project.\n\n---\n\n## Evaluators\n\nReady-to-use evaluation scripts. Copied into the experiment directory during setup with `--evaluator`.\n\n### Free Evaluators (no API cost)\n\n| Evaluator | Metric | Use Case |\n|-----------|--------|----------|\n| `benchmark_speed` | `p50_ms` (lower) | Function\u002FAPI execution time |\n| `benchmark_size` | `size_bytes` (lower) | File, bundle, Docker image size |\n| `test_pass_rate` | `pass_rate` (higher) | Test suite pass percentage |\n| `build_speed` | `build_seconds` (lower) | Build\u002Fcompile\u002FDocker build time |\n| `memory_usage` | `peak_mb` (lower) | Peak memory during execution |\n\n### LLM Judge Evaluators (uses your subscription)\n\n| Evaluator | Metric | Use Case |\n|-----------|--------|----------|\n| `llm_judge_content` | `ctr_score` 0-10 (higher) | Headlines, titles, descriptions |\n| `llm_judge_prompt` | `quality_score` 0-100 (higher) | System prompts, agent instructions |\n| `llm_judge_copy` | `engagement_score` 0-10 (higher) | Social posts, ad copy, emails |\n\nLLM judges call the CLI tool the user is already running (Claude, Codex, Gemini). The evaluation prompt is locked inside `evaluate.py` — the agent cannot modify it. This prevents the agent from gaming its own evaluator.\n\nThe user's existing subscription covers the cost:\n- Claude Code Max → unlimited Claude calls for evaluation\n- Codex CLI (ChatGPT Pro) → unlimited Codex calls\n- Gemini CLI (free tier) → free evaluation calls\n\n### Custom Evaluators\n\nIf no built-in evaluator fits, the user writes their own `evaluate.py`. Only requirement: it must print `metric_name: value` to stdout.\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n# My custom evaluator — DO NOT MODIFY after experiment starts\nimport subprocess\nresult = subprocess.run([\"my-benchmark\", \"--json\"], capture_output=True, text=True)\n# Parse and output\nprint(f\"my_metric: {parse_score(result.stdout)}\")\n```\n\n---\n\n## Viewing Results\n\n```bash\n# Single experiment\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed\n\n# All experiments in a domain\npython scripts\u002Flog_results.py --domain engineering\n\n# Cross-experiment dashboard\npython scripts\u002Flog_results.py --dashboard\n\n# Export formats\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed --format csv --output results.csv\npython scripts\u002Flog_results.py --experiment engineering\u002Fapi-speed --format markdown --output results.md\npython scripts\u002Flog_results.py --dashboard --format markdown --output dashboard.md\n```\n\n### Dashboard Output\n\n```\nDOMAIN          EXPERIMENT          RUNS  KEPT  BEST         Δ FROM START  STATUS\nengineering     api-speed            47    14   185ms        -76.9%        active\nengineering     bundle-size          23     8   412KB        -58.3%        paused\nmarketing       medium-ctr           31    11   8.4\u002F10       +68.0%        active\nprompts         support-tone         15     6   82\u002F100       +46.4%        done\n```\n\n### Export Formats\n\n- **TSV** — default, tab-separated (compatible with spreadsheets)\n- **CSV** — comma-separated, with proper quoting\n- **Markdown** — formatted table, readable in GitHub\u002Fdocs\n\n---\n\n## Proactive Triggers\n\nFlag these without being asked:\n\n- **No evaluation command works** → Test it before starting the loop. Run once, verify output.\n- **Target file not in git** → `git init && git add . && git commit -m 'initial'` first.\n- **Metric direction unclear** → Ask: is lower or higher better? Must know before starting.\n- **Time budget too short** → If eval takes longer than budget, every run crashes.\n- **Agent modifying evaluate.py** → Hard stop. This invalidates all comparisons.\n- **5 consecutive crashes** → Pause the loop. Alert the user. Don't keep burning cycles.\n- **No improvement in 20+ runs** → Suggest changing strategy in program.md or trying a different approach.\n\n---\n\n## Installation\n\n### One-liner (any tool)\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills.git\ncp -r claude-skills\u002Fengineering\u002Fautoresearch-agent ~\u002F.claude\u002Fskills\u002F\n```\n\n### Multi-tool install\n```bash\n.\u002Fscripts\u002Fconvert.sh --skill autoresearch-agent --tool codex|gemini|cursor|windsurf|openclaw\n```\n\n### OpenClaw\n```bash\nclawhub install cs-autoresearch-agent\n```\n\n---\n\n## Related Skills\n\n- **self-improving-agent** — improves an agent's own memory\u002Frules over time. NOT for structured experiment loops.\n- **senior-ml-engineer** — ML architecture decisions. Complementary — use for initial design, then autoresearch for optimization.\n- **tdd-guide** — test-driven development. Complementary — tests can be the evaluation function.\n- **skill-security-auditor** — audit skills before publishing. NOT for optimization loops.\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":50,"updated":51,"version":52,"category":53},"Alireza Rezvani",1773360000000,"2.0.0","engineering","main","cfe69e68b9b427ce0b098a2306c9898096ef0ac2","claude-skills\u002Fengineering\u002Fautoresearch-agent","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources","https:\u002F\u002Fgithub.com\u002FBoboegg","National Chung Cheng University Student","2026-04-03 12:18:40",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add Boboegg\u002Fai-resources --skill autoresearch-agent",{"tool":67,"command":68},"bunx","bunx skills add Boboegg\u002Fai-resources --skill autoresearch-agent",{"tool":70,"command":71},"pnpm","pnpm dlx skills add Boboegg\u002Fai-resources --skill autoresearch-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002FSKILL.md",true,[75,81,85,89,95,99,103,107,111,115,119,123,127,131,135,139,143],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},".claude-plugin\u002Fplugin.json","REFERENCE","参考文档",533,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002F.claude-plugin\u002Fplugin.json",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"agents\u002Fexperiment-runner.md",3266,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fagents\u002Fexperiment-runner.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"CLAUDE.md",1850,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002FCLAUDE.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"evaluators\u002Fbenchmark_size.py","SCRIPT","脚本",1899,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fbenchmark_size.py",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"evaluators\u002Fbenchmark_speed.py",1179,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fbenchmark_speed.py",{"path":100,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":101,"sourceHtmlUrl":102},"evaluators\u002Fbuild_speed.py",1141,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fbuild_speed.py",{"path":104,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":105,"sourceHtmlUrl":106},"evaluators\u002Fllm_judge_content.py",2714,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fllm_judge_content.py",{"path":108,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":109,"sourceHtmlUrl":110},"evaluators\u002Fllm_judge_copy.py",4471,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fllm_judge_copy.py",{"path":112,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":113,"sourceHtmlUrl":114},"evaluators\u002Fllm_judge_prompt.py",3026,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fllm_judge_prompt.py",{"path":116,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":117,"sourceHtmlUrl":118},"evaluators\u002Fmemory_usage.py",1663,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Fmemory_usage.py",{"path":120,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":121,"sourceHtmlUrl":122},"evaluators\u002Ftest_pass_rate.py",1586,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fevaluators\u002Ftest_pass_rate.py",{"path":124,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fexperiment-domains.md",6672,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Freferences\u002Fexperiment-domains.md",{"path":128,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Fprogram-template.md",4819,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Freferences\u002Fprogram-template.md",{"path":132,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":133,"sourceHtmlUrl":134},"scripts\u002Flog_results.py",15327,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fscripts\u002Flog_results.py",{"path":136,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":137,"sourceHtmlUrl":138},"scripts\u002Frun_experiment.py",9821,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fscripts\u002Frun_experiment.py",{"path":140,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":141,"sourceHtmlUrl":142},"scripts\u002Fsetup_experiment.py",14341,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fscripts\u002Fsetup_experiment.py",{"path":144,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":145,"sourceHtmlUrl":146},"settings.json",672,"https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fengineering\u002Fautoresearch-agent\u002Fsettings.json",[148,179,206,227,251,284],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":159,"publishedAt":44},"01M6KQBV2F4EG8YV2KET152Y5C","ra-qm-skills","12 regulatory & QM agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. ISO 13485 QMS, MDR 2017\u002F745, FDA 510(k)\u002FPMA, ISO 27001 ISMS, GDPR\u002FDSGVO, risk management (ISO 14971), CAPA, document control, auditing. Python tools (stdlib-only).","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fra-qm-team\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[160,161,162,163,164,165,41,166,167,168,169,170,171,172,173,174,175,176,177,178],"ra qm skills","qm","cli","gemini","python","codex","gdpr","risk","quality","cursor","regulatory","only","document","control","iso","iso 14971","ISO 13485","codex-cli","for",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":44},"01M6KQB7AQ2V5E25R7MNWW8QEW","scrum-master","Advanced Scrum Master skill for data-driven agile team analysis and coaching. Use when the user asks about sprint planning, velocity tracking, retrospectives, standup facilitation, backlog grooming, story points, burndown charts, blocker resolution, or agile team health. Runs Python scripts to analyse sprint JSON exports from Jira or similar tools: velocity_analyzer.py for Monte Carlo sprint forecasting, sprint_health_scorer.py for multi-dimension health scoring, and retrospective_analyzer.py for action-item and theme tracking. Produces confidence-interval forecasts, health grade reports, and improvement-velocity trends for high-performing Scrum teams.","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fproject-management\u002Fscrum-master\u002FSKILL.md",[],[186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205],"Scrum Master","scrum","master","jira","agile","data","analysis","Charts","team","project-management","reports","scoring","velocity","project","data-analysis","scripts","sprint","advanced","action","data-driven",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":214,"publishedAt":44},"01M6KQA3FMM7WRABSEDFVTFV1G","pm-skills","6 project management agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Senior PM, scrum master, Jira expert (JQL), Confluence expert, Atlassian admin, template creator. MCP integration for live Jira\u002FConfluence automation.","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fproject-management\u002FSKILL.md",[212,213],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},[215,216,217,218,162,219,220,189,41,190,221,222,195,223,187,188,224,199,225,226],"pm skills","pm","MCP","openclaw","gemini cli","template creator","project management","template","atlassian","expert","live","jql",{"skillNo":228,"name":229,"nameZh":6,"description":230,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":231,"categories":232,"keywords":237,"publishedAt":44},"01M6KQ95X5FVDMW0CS2CDC9Y8S","research-summarizer","Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fproduct-team\u002Fresearch-summarizer\u002FSKILL.md",[233,236],{"categoryNo":234,"categoryName":235,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[238,239,240,218,162,163,219,241,242,243,41,244,245,246,196,247,248,249,250,178],"research","research summarizer","summarizer","documentation","documents","create","dev","product","Citations","agent skill","sources","papers","briefs",{"skillNo":252,"name":253,"nameZh":6,"description":254,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":255,"categories":256,"keywords":267,"publishedAt":44},"01M6KQ7P10V92ZA3WAP0KMG5ZW","code-to-prd","Reverse-engineer any codebase into a complete Product Requirements Document (PRD).\nAnalyzes routes, components, state management, API integrations, and user interactions to produce\nbusiness-readable documentation detailed enough for engineers or AI agents to fully reconstruct\nevery page and endpoint. Works with frontend frameworks (React, Vue, Angular, Svelte, Next.js, Nuxt),\nbackend frameworks (NestJS, Django, Express, FastAPI), and fullstack applications.\n\nTrigger when users mention: generate PRD, reverse-engineer requirements, code to documentation,\nextract product specs from code, document page logic, analyze page fields and interactions,\ncreate a functional inventory, write requirements from an existing codebase, document API endpoints,\nor analyze backend routes.","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fproduct-team\u002Fcode-to-prd\u002FSKILL.md",[257,260,263,264],{"categoryNo":258,"categoryName":259,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":261,"categoryName":262,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},{"categoryNo":265,"categoryName":266,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000031","产品经理",[268,41,269,270,271,272,273,243,274,275,276,277,278,279,172,280,281,282,178,283],"to prd","prd","code to prd","frontend","components","react","generate","vue","applications","analyze","write","engineer","frameworks","express","functional","Existing",{"skillNo":285,"name":286,"nameZh":6,"description":287,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":288,"categories":289,"keywords":295,"publishedAt":44},"01M6KQ7A5WBZMQAM7Z37F77B4X","product-skills","10 product agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. PM toolkit (RICE), agile PO, product strategist (OKR), UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, research summarizer. Python tools (stdlib-only).","https:\u002F\u002Fgithub.com\u002FBoboegg\u002Fai-resources\u002Fblob\u002Fmain\u002Fclaude-skills\u002Fproduct-team\u002FSKILL.md",[290,291,292],{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},{"categoryNo":265,"categoryName":266,"taxonomyType":157,"taxonomyTypeDesc":158},{"categoryNo":293,"categoryName":294,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000032","设计师",[245,296,297,218,162,219,298,41,190,299,300,301,302,239,303,171,216,304,240,305],"product skills","design","design system","ux","ui","product strategist","Tools","rice","teardown","competitive"]