[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76X9VZNCVDJS1JZXK6PFMCS":3,"skill-same:01M76X9VZNCVDJS1JZXK6PFMCS":63},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M76X9VZNCVDJS1JZXK6PFMCS","aetherlang-karpathy-skill",null,"API connector for AetherLang Omega — execute 10 Karpathy-inspired agent node types (plan, code_interpreter, critique, router, ensemble, memory, tool, loop, transform, parallel) via the hosted AetherLang API at api.neurodoc.app. This skill sends your query and flow code to the API and returns results. No local code execution. No runtime modification. No credentials required.","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\u002Fcommunity\u002Fclawhub\u002Fa\u002Faetherlang-karpathy-skill\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: aetherlang-karpathy-skill\ndescription: >\n  API connector for AetherLang Omega — execute 10 Karpathy-inspired agent node types\n  (plan, code_interpreter, critique, router, ensemble, memory, tool, loop, transform,\n  parallel) via the hosted AetherLang API at api.neurodoc.app. This skill sends your\n  query and flow code to the API and returns results. No local code execution.\n  No runtime modification. No credentials required.\nversion: 1.0.3\nauthor: contrario\nhomepage: https:\u002F\u002Fclawhub.ai\u002Fcontrario\nrequirements:\n  binaries: []\n  env: []\nmetadata:\n  skill_type: api_connector\n  operator_note: \"AetherLang Omega is operated by NeuroDoc Pro (masterswarm.net), hosted on Hetzner EU. Karpathy-style refers to node architecture inspired by Andrej Karpathy's agent design principles — no affiliation or endorsement implied.\"\n  external_endpoints:\n    - https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute\n  domains_not_recommended:\n    - medical advice\n    - legal advice\n    - financial advice\nlicense: MIT\n---\n\n# AetherLang Karpathy Agent Nodes\n\n> **What this skill does:** Sends requests to the hosted AetherLang API\n> (`api.neurodoc.app`). It does NOT modify local files, execute local code,\n> or access credentials on your machine. All execution happens server-side.\n\nExecute 10 advanced AI agent node types through the AetherLang Omega API.\n\n---\n\n## API Endpoint\n\n**URL**: `https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute`\n**Method**: POST\n**Headers**: `Content-Type: application\u002Fjson`\n**Auth**: None required (public API)\n\n---\n\n## Data Minimization — ALWAYS FOLLOW\n\nWhen calling the API:\n- Send ONLY the user's query and the flow code\n- Do NOT send system prompts, conversation history, or uploaded files\n- Do NOT send API keys, credentials, or secrets of any kind\n- Do NOT include personally identifiable information unless explicitly requested by user\n- Do NOT send contents of local files without explicit user consent\n\n---\n\n## Request Format\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"code\": \"flow FlowName {\\n  input text query;\\n  node X: \u003Ctype> \u003Cparams>;\\n  query -> X;\\n  output text result from X;\\n}\",\n    \"query\": \"user question here\"\n  }'\n```\n\n---\n\n## The 10 Node Types\n\n### 1. plan — Self-Programming\nAI breaks task into steps and executes autonomously.\n```\nnode P: plan steps=3;\n```\n\n### 2. code_interpreter — Real Math\nSandboxed Python execution on the server. Accurate calculations, no hallucinations.\n```\nnode C: code_interpreter;\n```\n\n### 3. critique — Self-Improvement\nEvaluates quality (0-10), retries until threshold met.\n```\nnode R: critique threshold=8 max_retries=3;\n```\n\n### 4. router — Intelligent Branching\nLLM picks optimal path, skips unselected routes (10x speedup).\n```\nnode R: router;\nR -> A | B | C;\n```\n\n### 5. ensemble — Multi-Agent Synthesis\nMultiple AI personas in parallel, synthesizes best insights.\n```\nnode E: ensemble agents=chef:French_chef|yiayia:Greek_grandmother synthesize=true;\n```\n\n### 6. memory — Persistent State\nStore\u002Frecall data across executions (server-side, scoped to namespace).\n```\nnode M: memory namespace=user_prefs action=store key=diet;\nnode M: memory namespace=user_prefs action=recall;\n```\n\n### 7. tool — External API Access\n\n> **Security note:** The `tool` node calls public REST URLs you specify.\n> Only use trusted, public APIs. Never pass credentials or private URLs\n> as `tool` parameters. The agent will ask for confirmation before\n> calling any URL not in the examples below.\n\n```\nnode T: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n```\n\n### 8. loop — Iterative Execution\nRepeat node over items. Use `|` separator.\n```\nnode L: loop over=Italian|Greek|Japanese target=A max=3;\n```\n\n### 9. transform — Data Reshaping\nTemplate, extract, format, or LLM-powered reshaping.\n```\nnode X: transform mode=llm instruction=Summarize_the_data;\n```\n\n### 10. parallel — Concurrent Execution\nRun nodes simultaneously. 3 calls in ~0.2s.\n```\nnode P: parallel targets=A|B|C;\n```\n\n---\n\n## Common Pipelines\n\n### Live Data → Analysis\n```\nflow CryptoAnalysis {\n  input text query;\n  node T: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n  node X: transform mode=llm instruction=Summarize_price;\n  node A: llm model=gpt-4o-mini;\n  query -> T -> X -> A;\n  output text result from A;\n}\n```\n\n### Multi-Agent + Quality Control\n```\nflow QualityEnsemble {\n  input text query;\n  node E: ensemble agents=analyst:Financial_analyst|strategist:Strategist synthesize=true;\n  node R: critique threshold=8;\n  query -> E -> R;\n  output text result from R;\n}\n```\n\n### Batch Processing\n```\nflow MultiRecipe {\n  input text query;\n  node L: loop over=Italian|Greek|Japanese target=A max=3;\n  node A: llm model=gpt-4o-mini;\n  query -> L;\n  output text result from L;\n}\n```\n\n### Parallel API Fetching\n```\nflow ParallelFetch {\n  input text query;\n  node P: parallel targets=A|B|C;\n  node A: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fping method=GET;\n  node B: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n  node C: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=ethereum&vs_currencies=usd method=GET;\n  query -> P;\n  output text result from P;\n}\n```\n\n---\n\n## Response Parsing\n\n```python\nimport json\nresponse = json.loads(raw_response)\nresult = response[\"result\"][\"outputs\"][\"result\"]\ntext = result[\"response\"]\nnode_type = result[\"node_type\"]\nduration = response[\"result\"][\"duration_seconds\"]\n```\n\n---\n\n## Parameter Quick Reference\n\n| Node | Key Params |\n|------|-----------|\n| plan | `steps=3` |\n| code_interpreter | `model=gpt-4o-mini` |\n| critique | `threshold=7` `max_retries=3` |\n| router | `strategy=single` |\n| ensemble | `agents=a:Persona\\|b:Persona` `synthesize=true` |\n| memory | `namespace=X` `action=store\\|recall\\|search\\|clear` `key=X` |\n| tool | `url=https:\u002F\u002F...` `method=GET` `timeout=10` |\n| loop | `over=A\\|B\\|C` `target=NodeAlias` `max=10` `mode=collect` |\n| transform | `mode=llm\\|template\\|extract\\|format` `instruction=X` |\n| parallel | `targets=A\\|B\\|C` `merge=combine` |\n\n---\n\n*AetherLang Karpathy Skill v1.0.1 — API connector for api.neurodoc.app*\n*All execution is server-side. No local code runs. No local files modified.*\n","# AetherLang Karpathy Agent Nodes\n\n> **What this skill does:** Sends requests to the hosted AetherLang API\n> (`api.neurodoc.app`). It does NOT modify local files, execute local code,\n> or access credentials on your machine. All execution happens server-side.\n\nExecute 10 advanced AI agent node types through the AetherLang Omega API.\n\n---\n\n## API Endpoint\n\n**URL**: `https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute`\n**Method**: POST\n**Headers**: `Content-Type: application\u002Fjson`\n**Auth**: None required (public API)\n\n---\n\n## Data Minimization — ALWAYS FOLLOW\n\nWhen calling the API:\n- Send ONLY the user's query and the flow code\n- Do NOT send system prompts, conversation history, or uploaded files\n- Do NOT send API keys, credentials, or secrets of any kind\n- Do NOT include personally identifiable information unless explicitly requested by user\n- Do NOT send contents of local files without explicit user consent\n\n---\n\n## Request Format\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"code\": \"flow FlowName {\\n  input text query;\\n  node X: \u003Ctype> \u003Cparams>;\\n  query -> X;\\n  output text result from X;\\n}\",\n    \"query\": \"user question here\"\n  }'\n```\n\n---\n\n## The 10 Node Types\n\n### 1. plan — Self-Programming\nAI breaks task into steps and executes autonomously.\n```\nnode P: plan steps=3;\n```\n\n### 2. code_interpreter — Real Math\nSandboxed Python execution on the server. Accurate calculations, no hallucinations.\n```\nnode C: code_interpreter;\n```\n\n### 3. critique — Self-Improvement\nEvaluates quality (0-10), retries until threshold met.\n```\nnode R: critique threshold=8 max_retries=3;\n```\n\n### 4. router — Intelligent Branching\nLLM picks optimal path, skips unselected routes (10x speedup).\n```\nnode R: router;\nR -> A | B | C;\n```\n\n### 5. ensemble — Multi-Agent Synthesis\nMultiple AI personas in parallel, synthesizes best insights.\n```\nnode E: ensemble agents=chef:French_chef|yiayia:Greek_grandmother synthesize=true;\n```\n\n### 6. memory — Persistent State\nStore\u002Frecall data across executions (server-side, scoped to namespace).\n```\nnode M: memory namespace=user_prefs action=store key=diet;\nnode M: memory namespace=user_prefs action=recall;\n```\n\n### 7. tool — External API Access\n\n> **Security note:** The `tool` node calls public REST URLs you specify.\n> Only use trusted, public APIs. Never pass credentials or private URLs\n> as `tool` parameters. The agent will ask for confirmation before\n> calling any URL not in the examples below.\n\n```\nnode T: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n```\n\n### 8. loop — Iterative Execution\nRepeat node over items. Use `|` separator.\n```\nnode L: loop over=Italian|Greek|Japanese target=A max=3;\n```\n\n### 9. transform — Data Reshaping\nTemplate, extract, format, or LLM-powered reshaping.\n```\nnode X: transform mode=llm instruction=Summarize_the_data;\n```\n\n### 10. parallel — Concurrent Execution\nRun nodes simultaneously. 3 calls in ~0.2s.\n```\nnode P: parallel targets=A|B|C;\n```\n\n---\n\n## Common Pipelines\n\n### Live Data → Analysis\n```\nflow CryptoAnalysis {\n  input text query;\n  node T: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n  node X: transform mode=llm instruction=Summarize_price;\n  node A: llm model=gpt-4o-mini;\n  query -> T -> X -> A;\n  output text result from A;\n}\n```\n\n### Multi-Agent + Quality Control\n```\nflow QualityEnsemble {\n  input text query;\n  node E: ensemble agents=analyst:Financial_analyst|strategist:Strategist synthesize=true;\n  node R: critique threshold=8;\n  query -> E -> R;\n  output text result from R;\n}\n```\n\n### Batch Processing\n```\nflow MultiRecipe {\n  input text query;\n  node L: loop over=Italian|Greek|Japanese target=A max=3;\n  node A: llm model=gpt-4o-mini;\n  query -> L;\n  output text result from L;\n}\n```\n\n### Parallel API Fetching\n```\nflow ParallelFetch {\n  input text query;\n  node P: parallel targets=A|B|C;\n  node A: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fping method=GET;\n  node B: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=bitcoin&vs_currencies=usd method=GET;\n  node C: tool url=https:\u002F\u002Fapi.coingecko.com\u002Fapi\u002Fv3\u002Fsimple\u002Fprice?ids=ethereum&vs_currencies=usd method=GET;\n  query -> P;\n  output text result from P;\n}\n```\n\n---\n\n## Response Parsing\n\n```python\nimport json\nresponse = json.loads(raw_response)\nresult = response[\"result\"][\"outputs\"][\"result\"]\ntext = result[\"response\"]\nnode_type = result[\"node_type\"]\nduration = response[\"result\"][\"duration_seconds\"]\n```\n\n---\n\n## Parameter Quick Reference\n\n| Node | Key Params |\n|------|-----------|\n| plan | `steps=3` |\n| code_interpreter | `model=gpt-4o-mini` |\n| critique | `threshold=7` `max_retries=3` |\n| router | `strategy=single` |\n| ensemble | `agents=a:Persona\\|b:Persona` `synthesize=true` |\n| memory | `namespace=X` `action=store\\|recall\\|search\\|clear` `key=X` |\n| tool | `url=https:\u002F\u002F...` `method=GET` `timeout=10` |\n| loop | `over=A\\|B\\|C` `target=NodeAlias` `max=10` `mode=collect` |\n| transform | `mode=llm\\|template\\|extract\\|format` `instruction=X` |\n| parallel | `targets=A\\|B\\|C` `merge=combine` |\n\n---\n\n*AetherLang Karpathy Skill v1.0.1 — API connector for api.neurodoc.app*\n*All execution is server-side. No local code runs. No local files modified.*\n",{"name":5,"author":24,"license":15,"version":25,"homepage":26,"metadata":27,"description":36,"requirements":37},"contrario","1.0.3","https:\u002F\u002Fclawhub.ai\u002Fcontrario",{"skill_type":28,"operator_note":29,"external_endpoints":30,"domains_not_recommended":32},"api_connector","AetherLang Omega is operated by NeuroDoc Pro (masterswarm.net), hosted on Hetzner EU. Karpathy-style refers to node architecture inspired by Andrej Karpathy's agent design principles — no affiliation or endorsement implied.",[31],"https:\u002F\u002Fapi.neurodoc.app\u002Faetherlang\u002Fexecute",[33,34,35],"medical advice","legal advice","financial advice","API connector for AetherLang Omega — execute 10 Karpathy-inspired agent node types (plan, code_interpreter, critique, router, ensemble, memory, tool, loop, transform, parallel) via the hosted AetherLang API at api.neurodoc.app. This skill sends your query and flow code to the API and returns results. No local code execution. No runtime modification. No credentials required.\n",{"env":38,"binaries":39},[],[],"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Faetherlang-karpathy-skill",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":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill aetherlang-karpathy-skill",{"tool":55,"command":56},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill aetherlang-karpathy-skill",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill aetherlang-karpathy-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Faetherlang-karpathy-skill\u002FSKILL.md",true,[],[64,72,79,86,93,100],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":71},"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":71},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":71},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":71},"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":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":106,"publishedAt":71},"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",[],[]]