[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ECF2VHEJD8BA0VZFNTHVBV":3,"skill-same:01M6ECF2VHEJD8BA0VZFNTHVBV":77},{"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":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6ECF2VHEJD8BA0VZFNTHVBV","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.","levalencia\u002Fagent-god-mode","levalencia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6962857?v=4","01M6EB0FZZ4BPQPC4HET4QY6NM","Luis Valencia ","01M6EB0G4HWHPWW0H9X7QKSAHP",3,"MIT","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\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","repo","ctr","reset","speed","optimize","experiment","karpathy","autonomous","command","image","loop","improve","Evaluation","git","code","run","git commit","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","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fautoresearch-agent",1,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode","https:\u002F\u002Fgithub.com\u002Flevalencia","https:\u002F\u002Fmedium.com\u002F@luisevalencia","Microsoft MVP - Artificial Intelligence\r\nMachine Learning Enthusiast\r\n","2026-05-02 06:55:36",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add levalencia\u002Fagent-god-mode --skill autoresearch-agent",{"tool":69,"command":70},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill autoresearch-agent",{"tool":72,"command":73},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill autoresearch-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fautoresearch-agent\u002FSKILL.md",true,[],[78,100,134,160,186,213],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":44},"01M6EM8ES5M9J4S8N78NJST0YC","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzarr-python\u002FSKILL.md",[],[85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":115,"publishedAt":44},"01M6EM8AR6ZFKZ9YVW8TTG850Z","zabbix","Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper\u002Fsender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User\u002Fpermission management","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzabbix-api-skill\u002FSKILL.md",[106,109,110],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[102,85,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":44},"01M6EM6Q9JG846ECQY9A210A26","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fx-twitter-growth\u002FSKILL.md",[],[141,142,143,144,145,146,147,148,149,150,151,152,30,153,154,155,156,157,158,159],"twitter","x twitter growth","growth","competitive intelligence","search","analyzing","plan","marketing","web search","competitors","analyze","write","social","intelligence","viral","growth engine","mechanics","grow","competitive",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":44},"01M6EM3FQNPYNKPC4CV9TCVNGD","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fwhat-if-oracle\u002FSKILL.md",[],[167,168,169,170,171,172,173,174,175,176,177,178,124,179,180,181,182,183,184,185],"oracle","what if oracle","test","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":195,"publishedAt":44},"01M6EM08C06RGDYCJ86HAPK0FF","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvercel-react-best-practices\u002FSKILL.md",[192],{"categoryNo":193,"categoryName":194,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[196,197,198,199,200,201,202,203,204,205,206,40,207,119,208,209,210,211,212,129],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":229,"publishedAt":44},"01M6EM00S13326QM08DTM94J6Z","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvenue-templates\u002FSKILL.md",[219,222,225,226],{"categoryNo":220,"categoryName":221,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":223,"categoryName":224,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":227,"categoryName":228,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000036","内容创作者",[120,230,231,205,232,233,234,235,236,237,238,152,239,240,241,242,243,244,99,245],"venue templates","research","NeurIPS","ICML","LaTeX","science","Bash","access","read","edit","proposals","Academic","requirements","formatting","journal","chi"]