[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7859HJCG7ZSWDXGBDFBSTH6":3,"skill-same:01M7859HJCG7ZSWDXGBDFBSTH6":65},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7859HJCG7ZSWDXGBDFBSTH6","darwinian-evolver",null,"Evolve prompts\u002Fregex\u002FSQL\u002Fcode with Imbue's evolution loop.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Foptional-skills\u002Fdarwinian-evolver\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: darwinian-evolver\ndescription: \"Evolve prompts\u002Fregex\u002FSQL\u002Fcode with Imbue's evolution loop.\"\nversion: 0.1.0\nauthor: Bihruze (Asahi0x), Hermes Agent\nlicense: MIT\nplatforms: [linux, macos]\ncategory: research\ntags: [evolution, optimization, prompt-engineering, research]\ncompatible: [claude-code, openai-agents, hermes-agent, autogen, langchain, any-llm]\nsource: optional\n---\n\n# Darwinian Evolver\n\nRun Imbue's [darwinian_evolver](https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver) — an\nLLM-driven evolutionary search loop — to optimize a **prompt, regex, SQL query,\nor small code snippet** against a fitness function.\n\nStatus: thin wrapper around the upstream tool. The skill installs it, walks the\nagent through writing a `Problem` definition (organism + evaluator + mutator),\nand drives the loop via the upstream CLI or a small custom Python driver.\n\n**License:** the upstream tool is **AGPL-3.0**. The skill ONLY ever invokes it\nvia the upstream CLI or a `subprocess`\u002F`uv run` call (mere aggregation). Do NOT\nimport upstream classes into Hermes itself.\n\n## When to Use\n\n- User says \"optimize this prompt\", \"evolve a regex for X\", \"auto-improve this\n  code\u002FSQL\", \"search for a better instruction\".\n- You have a scorer (exact match, regex pass-rate, unit test, LLM-judge, runtime\n  metric) AND a starting candidate (organism). If you don't have a scorer, stop\n  and define one first — that's the hard part.\n- Cost is OK: a typical run is 50–500 LLM calls. On gpt-4o-mini that's pennies;\n  on Claude Sonnet it can be a few dollars.\n\nDo **not** use this when:\n- The optimization target is differentiable (use gradient descent \u002F DSPy).\n- You only need to try 2–3 variants — just write them by hand.\n- The fitness signal is purely subjective with no measurable criterion.\n\n## Prerequisites\n\n- Python ≥3.11\n- `git`, `uv` (or `pip`)\n- One of: `OPENROUTER_API_KEY`, `ANTHROPIC_API_KEY`, or `OPENAI_API_KEY`\n\nThe skill ships a small `parrot_openrouter.py` driver that uses `OPENROUTER_API_KEY`\nvia the OpenAI SDK, so any model on OpenRouter works. The upstream CLI itself\nhardcodes Anthropic and needs `ANTHROPIC_API_KEY`.\n\n## Install (One-Time)\n\nRun via the `terminal` tool:\n\n```bash\nmkdir -p ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver && cd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\n[ -d darwinian_evolver ] || git clone --depth 1 https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver.git\ncd darwinian_evolver && uv sync\n```\n\nVerify:\n\n```bash\ncd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver \\\n  && uv run darwinian_evolver --help | head -5\n```\n\n## Quick Start — The Built-In Parrot Example\n\nTiny smoke test (requires `ANTHROPIC_API_KEY`):\n\n```bash\ncd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\nuv run darwinian_evolver parrot \\\n  --num_iterations 2 \\\n  --num_parents_per_iteration 2 \\\n  --mutator_concurrency 2 --evaluator_concurrency 2 \\\n  --output_dir \u002Ftmp\u002Fparrot_demo\n```\n\nOutputs:\n- `\u002Ftmp\u002Fparrot_demo\u002Fsnapshots\u002Fiteration_N.pkl` — pickled population per iteration\n- `\u002Ftmp\u002Fparrot_demo\u002F\u003Cjsonl>` — per-iteration JSON log (path printed at end)\n\nOpen `~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\u002Fdarwinian_evolver\u002Flineage_visualizer.html`\nin a browser and load the JSON log to see the evolutionary tree.\n\n## Quick Start — OpenRouter Driver (No Anthropic Key)\n\nThe skill ships `scripts\u002Fparrot_openrouter.py` — same parrot problem, but the\nLLM call goes through OpenRouter so any provider works.\n\n```bash\n# From wherever the skill is installed:\nSKILL_DIR=~\u002F.hermes\u002Fskills\u002Fresearch\u002Fdarwinian-evolver\nDE_DIR=~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\n\ncd \"$DE_DIR\" && \\\n  EVOLVER_MODEL='openai\u002Fgpt-4o-mini' \\\n  uv run --with openai python \"$SKILL_DIR\u002Fscripts\u002Fparrot_openrouter.py\" \\\n    --num_iterations 3 --num_parents_per_iteration 2 \\\n    --output_dir \u002Ftmp\u002Fparrot_or\n```\n\nInspect the result with `scripts\u002Fshow_snapshot.py`:\n\n```bash\nuv run --with openai python \"$SKILL_DIR\u002Fscripts\u002Fshow_snapshot.py\" \\\n  \u002Ftmp\u002Fparrot_or\u002Fsnapshots\u002Fiteration_3.pkl\n```\n\nExpected output: 7 evolved prompt templates ranked by score, with the best\nlanding around 0.6–0.8 (the seed `Say {{ phrase }}` scored 0.000).\n\n## Defining a Custom Problem\n\nThe skill ships `templates\u002Fcustom_problem_template.py` — copy, edit, run.\nThree things you must define:\n\n1. **`Organism`** — a Pydantic `BaseModel` subclass holding the artifact being\n   evolved (`prompt_template: str`, `regex_pattern: str`, `sql_query: str`,\n   `code_block: str`, etc.). Add a `run(*args)` method that exercises it.\n\n2. **`Evaluator`** — `.evaluate(organism) -> EvaluationResult(score=..., trainable_failure_cases=[...], holdout_failure_cases=[...], is_viable=True)`.\n   - **`score`** is in `[0, 1]`. Higher is better.\n   - **`trainable_failure_cases`** — what the mutator sees. Include enough\n     context (input, expected, actual) for the LLM to diagnose.\n   - **`holdout_failure_cases`** — kept out of the mutator's view. Use these\n     to detect overfitting.\n   - **`is_viable=True`** unless the organism is completely broken (raises,\n     returns None, etc.). A 0-score viable organism is fine — it just gets\n     down-weighted in parent selection.\n\n3. **`Mutator`** — `.mutate(organism, failure_cases, learning_log_entries) -> list[Organism]`.\n   Typically: build an LLM prompt that includes the current organism + a\n   failure case + an ask to propose a fix; parse the LLM's response; return\n   a new `Organism`. Return `[]` on parse failure — the loop handles it.\n\nThen write a driver script that wires `Problem(initial_organism, evaluator, [mutators])`\ninto `EvolveProblemLoop` and iterates over `loop.run(num_iterations=N)` — the\nshipped `scripts\u002Fparrot_openrouter.py` is the reference.\n\n## Hyperparameters That Actually Matter\n\n| flag | default | when to change |\n|---|---|---|\n| `--num_iterations` | 5 | bump to 10–20 once you trust the evaluator |\n| `--num_parents_per_iteration` | 4 | drop to 2 for cheap exploration |\n| `--mutator_concurrency` | 10 | drop to 2–4 to avoid rate limits |\n| `--evaluator_concurrency` | 10 | same; evaluator hits the LLM too |\n| `--batch_size` | 1 | raise to 3–5 once your mutator handles multiple failures |\n| `--verify_mutations` | off | turn on once mutator is wasteful (>10× cost saving on later runs per Imbue) |\n| `--midpoint_score` | `p75` | leave alone unless scores cluster |\n| `--sharpness` | 10 | leave alone |\n\n## Pitfalls\n\n1. **`Initial organism must be viable`** — set `is_viable=True` in your\n   `EvaluationResult` even on a 0-score seed. The loop refuses non-viable\n   organisms because they imply the loop has nothing to evolve from.\n2. **Provider content filters kill runs.** Azure-backed OpenRouter models\n   reject phrases like \"ignore previous instructions\" with HTTP 400. Wrap\n   the LLM call in `try\u002Fexcept` and return `f\"\u003CLLM_ERROR: {e}>\"` — the\n   evolver will just score that organism 0 and move on.\n3. **`loop.run()` is a generator** — calling it doesn't run anything until\n   you iterate. Use `for snap in loop.run(num_iterations=N):`.\n4. **Snapshots are nested pickles.** `iteration_N.pkl` contains a dict with\n   `population_snapshot` (more pickled bytes). To unpickle you must have the\n   `Organism` class importable under the same dotted path it was pickled at.\n5. **Concurrency defaults are aggressive.** 10\u002F10 will hit rate limits on\n   most providers. Start with 2\u002F2.\n6. **CLI is hardcoded to Anthropic.** `uv run darwinian_evolver \u003Cproblem>`\n   reaches for `ANTHROPIC_API_KEY` and uses Claude Sonnet. To use any other\n   provider, write a driver like `parrot_openrouter.py`.\n7. **AGPL.** Never `from darwinian_evolver import ...` inside Hermes core.\n   Custom driver scripts under `~\u002F.hermes\u002Fskills\u002F...` are user-side and fine.\n8. **No PyPI package.** `pip install darwinian-evolver` will pull the wrong\n   thing. Always install from the GitHub repo.\n\n## Verification\n\nAfter install + a parrot run, exit code 0 from this is sufficient:\n\n```bash\nDE_DIR=~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\nls \"$DE_DIR\u002Fdarwinian_evolver\u002Flineage_visualizer.html\" >\u002Fdev\u002Fnull && \\\ncd \"$DE_DIR\" && uv run darwinian_evolver --help >\u002Fdev\u002Fnull && \\\necho \"darwinian-evolver: OK\"\n```\n\n## References\n\n- [Imbue research post](https:\u002F\u002Fimbue.com\u002Fresearch\u002F2026-02-27-darwinian-evolver\u002F)\n- [ARC-AGI-2 results](https:\u002F\u002Fimbue.com\u002Fresearch\u002F2026-02-27-arc-agi-2-evolution\u002F)\n- [imbue-ai\u002Fdarwinian_evolver](https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver) (AGPL-3.0)\n- [Darwin Gödel Machines](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22954)\n- [PromptBreeder](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.16797)\n","# Darwinian Evolver\n\nRun Imbue's [darwinian_evolver](https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver) — an\nLLM-driven evolutionary search loop — to optimize a **prompt, regex, SQL query,\nor small code snippet** against a fitness function.\n\nStatus: thin wrapper around the upstream tool. The skill installs it, walks the\nagent through writing a `Problem` definition (organism + evaluator + mutator),\nand drives the loop via the upstream CLI or a small custom Python driver.\n\n**License:** the upstream tool is **AGPL-3.0**. The skill ONLY ever invokes it\nvia the upstream CLI or a `subprocess`\u002F`uv run` call (mere aggregation). Do NOT\nimport upstream classes into Hermes itself.\n\n## When to Use\n\n- User says \"optimize this prompt\", \"evolve a regex for X\", \"auto-improve this\n  code\u002FSQL\", \"search for a better instruction\".\n- You have a scorer (exact match, regex pass-rate, unit test, LLM-judge, runtime\n  metric) AND a starting candidate (organism). If you don't have a scorer, stop\n  and define one first — that's the hard part.\n- Cost is OK: a typical run is 50–500 LLM calls. On gpt-4o-mini that's pennies;\n  on Claude Sonnet it can be a few dollars.\n\nDo **not** use this when:\n- The optimization target is differentiable (use gradient descent \u002F DSPy).\n- You only need to try 2–3 variants — just write them by hand.\n- The fitness signal is purely subjective with no measurable criterion.\n\n## Prerequisites\n\n- Python ≥3.11\n- `git`, `uv` (or `pip`)\n- One of: `OPENROUTER_API_KEY`, `ANTHROPIC_API_KEY`, or `OPENAI_API_KEY`\n\nThe skill ships a small `parrot_openrouter.py` driver that uses `OPENROUTER_API_KEY`\nvia the OpenAI SDK, so any model on OpenRouter works. The upstream CLI itself\nhardcodes Anthropic and needs `ANTHROPIC_API_KEY`.\n\n## Install (One-Time)\n\nRun via the `terminal` tool:\n\n```bash\nmkdir -p ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver && cd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\n[ -d darwinian_evolver ] || git clone --depth 1 https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver.git\ncd darwinian_evolver && uv sync\n```\n\nVerify:\n\n```bash\ncd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver \\\n  && uv run darwinian_evolver --help | head -5\n```\n\n## Quick Start — The Built-In Parrot Example\n\nTiny smoke test (requires `ANTHROPIC_API_KEY`):\n\n```bash\ncd ~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\nuv run darwinian_evolver parrot \\\n  --num_iterations 2 \\\n  --num_parents_per_iteration 2 \\\n  --mutator_concurrency 2 --evaluator_concurrency 2 \\\n  --output_dir \u002Ftmp\u002Fparrot_demo\n```\n\nOutputs:\n- `\u002Ftmp\u002Fparrot_demo\u002Fsnapshots\u002Fiteration_N.pkl` — pickled population per iteration\n- `\u002Ftmp\u002Fparrot_demo\u002F\u003Cjsonl>` — per-iteration JSON log (path printed at end)\n\nOpen `~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\u002Fdarwinian_evolver\u002Flineage_visualizer.html`\nin a browser and load the JSON log to see the evolutionary tree.\n\n## Quick Start — OpenRouter Driver (No Anthropic Key)\n\nThe skill ships `scripts\u002Fparrot_openrouter.py` — same parrot problem, but the\nLLM call goes through OpenRouter so any provider works.\n\n```bash\n# From wherever the skill is installed:\nSKILL_DIR=~\u002F.hermes\u002Fskills\u002Fresearch\u002Fdarwinian-evolver\nDE_DIR=~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\n\ncd \"$DE_DIR\" && \\\n  EVOLVER_MODEL='openai\u002Fgpt-4o-mini' \\\n  uv run --with openai python \"$SKILL_DIR\u002Fscripts\u002Fparrot_openrouter.py\" \\\n    --num_iterations 3 --num_parents_per_iteration 2 \\\n    --output_dir \u002Ftmp\u002Fparrot_or\n```\n\nInspect the result with `scripts\u002Fshow_snapshot.py`:\n\n```bash\nuv run --with openai python \"$SKILL_DIR\u002Fscripts\u002Fshow_snapshot.py\" \\\n  \u002Ftmp\u002Fparrot_or\u002Fsnapshots\u002Fiteration_3.pkl\n```\n\nExpected output: 7 evolved prompt templates ranked by score, with the best\nlanding around 0.6–0.8 (the seed `Say {{ phrase }}` scored 0.000).\n\n## Defining a Custom Problem\n\nThe skill ships `templates\u002Fcustom_problem_template.py` — copy, edit, run.\nThree things you must define:\n\n1. **`Organism`** — a Pydantic `BaseModel` subclass holding the artifact being\n   evolved (`prompt_template: str`, `regex_pattern: str`, `sql_query: str`,\n   `code_block: str`, etc.). Add a `run(*args)` method that exercises it.\n\n2. **`Evaluator`** — `.evaluate(organism) -> EvaluationResult(score=..., trainable_failure_cases=[...], holdout_failure_cases=[...], is_viable=True)`.\n   - **`score`** is in `[0, 1]`. Higher is better.\n   - **`trainable_failure_cases`** — what the mutator sees. Include enough\n     context (input, expected, actual) for the LLM to diagnose.\n   - **`holdout_failure_cases`** — kept out of the mutator's view. Use these\n     to detect overfitting.\n   - **`is_viable=True`** unless the organism is completely broken (raises,\n     returns None, etc.). A 0-score viable organism is fine — it just gets\n     down-weighted in parent selection.\n\n3. **`Mutator`** — `.mutate(organism, failure_cases, learning_log_entries) -> list[Organism]`.\n   Typically: build an LLM prompt that includes the current organism + a\n   failure case + an ask to propose a fix; parse the LLM's response; return\n   a new `Organism`. Return `[]` on parse failure — the loop handles it.\n\nThen write a driver script that wires `Problem(initial_organism, evaluator, [mutators])`\ninto `EvolveProblemLoop` and iterates over `loop.run(num_iterations=N)` — the\nshipped `scripts\u002Fparrot_openrouter.py` is the reference.\n\n## Hyperparameters That Actually Matter\n\n| flag | default | when to change |\n|---|---|---|\n| `--num_iterations` | 5 | bump to 10–20 once you trust the evaluator |\n| `--num_parents_per_iteration` | 4 | drop to 2 for cheap exploration |\n| `--mutator_concurrency` | 10 | drop to 2–4 to avoid rate limits |\n| `--evaluator_concurrency` | 10 | same; evaluator hits the LLM too |\n| `--batch_size` | 1 | raise to 3–5 once your mutator handles multiple failures |\n| `--verify_mutations` | off | turn on once mutator is wasteful (>10× cost saving on later runs per Imbue) |\n| `--midpoint_score` | `p75` | leave alone unless scores cluster |\n| `--sharpness` | 10 | leave alone |\n\n## Pitfalls\n\n1. **`Initial organism must be viable`** — set `is_viable=True` in your\n   `EvaluationResult` even on a 0-score seed. The loop refuses non-viable\n   organisms because they imply the loop has nothing to evolve from.\n2. **Provider content filters kill runs.** Azure-backed OpenRouter models\n   reject phrases like \"ignore previous instructions\" with HTTP 400. Wrap\n   the LLM call in `try\u002Fexcept` and return `f\"\u003CLLM_ERROR: {e}>\"` — the\n   evolver will just score that organism 0 and move on.\n3. **`loop.run()` is a generator** — calling it doesn't run anything until\n   you iterate. Use `for snap in loop.run(num_iterations=N):`.\n4. **Snapshots are nested pickles.** `iteration_N.pkl` contains a dict with\n   `population_snapshot` (more pickled bytes). To unpickle you must have the\n   `Organism` class importable under the same dotted path it was pickled at.\n5. **Concurrency defaults are aggressive.** 10\u002F10 will hit rate limits on\n   most providers. Start with 2\u002F2.\n6. **CLI is hardcoded to Anthropic.** `uv run darwinian_evolver \u003Cproblem>`\n   reaches for `ANTHROPIC_API_KEY` and uses Claude Sonnet. To use any other\n   provider, write a driver like `parrot_openrouter.py`.\n7. **AGPL.** Never `from darwinian_evolver import ...` inside Hermes core.\n   Custom driver scripts under `~\u002F.hermes\u002Fskills\u002F...` are user-side and fine.\n8. **No PyPI package.** `pip install darwinian-evolver` will pull the wrong\n   thing. Always install from the GitHub repo.\n\n## Verification\n\nAfter install + a parrot run, exit code 0 from this is sufficient:\n\n```bash\nDE_DIR=~\u002F.hermes\u002Fcache\u002Fdarwinian-evolver\u002Fdarwinian_evolver\nls \"$DE_DIR\u002Fdarwinian_evolver\u002Flineage_visualizer.html\" >\u002Fdev\u002Fnull && \\\ncd \"$DE_DIR\" && uv run darwinian_evolver --help >\u002Fdev\u002Fnull && \\\necho \"darwinian-evolver: OK\"\n```\n\n## References\n\n- [Imbue research post](https:\u002F\u002Fimbue.com\u002Fresearch\u002F2026-02-27-darwinian-evolver\u002F)\n- [ARC-AGI-2 results](https:\u002F\u002Fimbue.com\u002Fresearch\u002F2026-02-27-arc-agi-2-evolution\u002F)\n- [imbue-ai\u002Fdarwinian_evolver](https:\u002F\u002Fgithub.com\u002Fimbue-ai\u002Fdarwinian_evolver) (AGPL-3.0)\n- [Darwin Gödel Machines](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22954)\n- [PromptBreeder](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.16797)\n",{"name":5,"tags":24,"author":29,"source":30,"license":15,"version":31,"category":28,"platforms":32,"compatible":35,"description":7},[25,26,27,28],"evolution","optimization","prompt-engineering","research","Bihruze (Asahi0x), Hermes Agent","optional","0.1.0",[33,34],"linux","macos",[36,37,38,39,40,41],"claude-code","openai-agents","hermes-agent","autogen","langchain","any-llm","master","4aa004da461d820f4ea5499e58eb8d196cf99016","optional-skills\u002Fdarwinian-evolver",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill darwinian-evolver",{"tool":57,"command":58},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill darwinian-evolver",{"tool":60,"command":61},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill darwinian-evolver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Foptional-skills\u002Fdarwinian-evolver\u002FSKILL.md",true,[],[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]