[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77VGCFBCHZYTCKWSQ1DJHXH":3,"skill-same:01M77VGCFBCHZYTCKWSQ1DJHXH":64},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M77VGCFBCHZYTCKWSQ1DJHXH","stable-diffusion-sd3",null,"Stable Diffusion 3 and SD3.5 Large on Apple Silicon — generate Stable Diffusion images locally with DiffusionKit's MLX-native backend. SD3 Medium for fast Stable Diffusion generation, SD3.5 Large for highest quality. Plus Flux models via mflux and Ollama native image gen. All routed across your device fleet. No cloud APIs, no DALL-E costs. 稳定扩散SD3本地图像生成。Difusion estable SD3 para generacion de imagenes local.","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\u002Fs\u002Fstable-diffusion-sd3\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stable-diffusion-sd3\ndescription: Stable Diffusion 3 and SD3.5 Large on Apple Silicon — generate Stable Diffusion images locally with DiffusionKit's MLX-native backend. SD3 Medium for fast Stable Diffusion generation, SD3.5 Large for highest quality. Plus Flux models via mflux and Ollama native image gen. All routed across your device fleet. No cloud APIs, no DALL-E costs. 稳定扩散SD3本地图像生成。Difusion estable SD3 para generacion de imagenes local.\nversion: 1.0.2\nhomepage: https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\nmetadata: {\"openclaw\":{\"emoji\":\"art\",\"requires\":{\"anyBins\":[\"curl\",\"wget\"],\"optionalBins\":[\"python3\",\"pip\"]},\"configPaths\":[\"~\u002F.fleet-manager\u002Flatency.db\",\"~\u002F.fleet-manager\u002Flogs\u002Fherd.jsonl\"],\"os\":[\"darwin\"]}}\n---\n\n# Stable Diffusion 3 — Local Image Generation on Your Fleet\n\nRun Stable Diffusion 3 Medium and Stable Diffusion 3.5 Large (SD3.5) on your own Apple Silicon hardware. DiffusionKit provides MLX-native Stable Diffusion inference — no CUDA, no cloud, no per-image costs. The fleet router picks the best device for every Stable Diffusion generation request.\n\n## Stable Diffusion Supported Models\n\n| Stable Diffusion Model | Backend | Speed (M3 Ultra) | Peak RAM | Quality |\n|-------|---------|-------------------|----------|---------|\n| **SD3 Medium** | DiffusionKit | ~9s (512px) | 3.5GB | Good — fast Stable Diffusion iterations |\n| **SD3.5 Large** | DiffusionKit | ~67s (512px) | 11.6GB | Highest — Stable Diffusion with T5 encoder |\n| **z-image-turbo** | mflux | ~7s (512px) | 4GB | Good — fastest option |\n| **flux-dev** | mflux | ~30s (1024px) | 6GB | High — detailed output |\n| **x\u002Fz-image-turbo** | Ollama native | ~19s (1024px) | 12GB | Good — experimental |\n\n## Stable Diffusion Setup\n\n```bash\npip install ollama-herd    # Stable Diffusion fleet router from PyPI\nherd                       # start the Stable Diffusion router (port 11435)\nherd-node                  # run on each device — finds the router for Stable Diffusion routing\n```\n\n### Install DiffusionKit for Stable Diffusion models\n\n```bash\nuv tool install diffusionkit    # Stable Diffusion 3 and SD3.5 backend\n```\n\n**macOS 26 users:** Apply a one-time patch for Stable Diffusion compatibility:\n```bash\n.\u002Fscripts\u002Fpatch-diffusionkit-macos26.sh\n```\n\nFirst Stable Diffusion run downloads model weights from HuggingFace (~2-8GB depending on SD3 model). No models are downloaded during installation — all Stable Diffusion pulls are user-initiated.\n\n### Install mflux for Flux models (optional, recommended alongside Stable Diffusion)\n\n```bash\nuv tool install mflux\n```\n\nThe router prefers mflux over Ollama native for shared models to avoid evicting LLMs from memory during Stable Diffusion workloads.\n\n## Generate Stable Diffusion Images\n\n### Stable Diffusion 3 Medium (fast SD3 generation)\n\n```bash\ncurl -o sd3_cityscape.png http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"sd3-medium\", \"prompt\": \"Stable Diffusion rendering a futuristic cityscape at dusk\", \"width\": 1024, \"height\": 1024, \"steps\": 20}'\n```\n\n### Stable Diffusion 3.5 Large (highest quality SD3)\n\n```bash\ncurl -o sd3_portrait.png http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"sd3.5-large\", \"prompt\": \"Stable Diffusion oil painting portrait, dramatic lighting\", \"width\": 1024, \"height\": 1024, \"steps\": 30}'\n```\n\n### Stable Diffusion Python Integration\n\n```python\nimport httpx\n\ndef generate_stable_diffusion(prompt, model=\"sd3-medium\", width=1024, height=1024):\n    \"\"\"Generate an image using Stable Diffusion SD3 via the fleet router.\"\"\"\n    sd3_response = httpx.post(\n        \"http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image\",\n        json={\"model\": model, \"prompt\": prompt, \"width\": width, \"height\": height, \"steps\": 20},\n        timeout=180.0,\n    )\n    sd3_response.raise_for_status()\n    return sd3_response.content  # Stable Diffusion PNG bytes\n\n# Quick Stable Diffusion iteration with SD3 Medium\nsd3_png = generate_stable_diffusion(\"a robot painting a sunset in Stable Diffusion style\")\nwith open(\"stable_diffusion_output.png\", \"wb\") as f:\n    f.write(sd3_png)\n```\n\n### Stable Diffusion Parameters\n\n| SD3 Parameter | Default | Description |\n|-----------|---------|-------------|\n| `model` | (required) | `sd3-medium`, `sd3.5-large`, `z-image-turbo`, `flux-dev`, `flux-schnell` |\n| `prompt` | (required) | Stable Diffusion text description of the image |\n| `width` | `1024` | Stable Diffusion image width in pixels |\n| `height` | `1024` | Stable Diffusion image height in pixels |\n| `steps` | `4` | Stable Diffusion inference steps (20-30 recommended for SD3) |\n| `guidance` | (model default) | Stable Diffusion guidance scale |\n| `seed` | (random) | Seed for reproducible Stable Diffusion output |\n| `negative_prompt` | `\"\"` | What to avoid in Stable Diffusion generation |\n\n## Monitor Stable Diffusion Generation\n\n```bash\n# Stable Diffusion generation stats (last 24h)\ncurl -s http:\u002F\u002Flocalhost:11435\u002Fdashboard\u002Fapi\u002Fimage-stats | python3 -m json.tool\n\n# Which nodes have Stable Diffusion models\ncurl -s http:\u002F\u002Flocalhost:11435\u002Ffleet\u002Fstatus | python3 -c \"\nimport sys, json\n# Stable Diffusion node inspection\nfor n in json.load(sys.stdin).get('nodes', []):\n    img = n.get('image', {})\n    if img:\n        sd3_models = [m['name'] for m in img.get('models_available', [])]\n        print(f'{n[\\\"node_id\\\"]}: {sd3_models}')\n\"\n```\n\nWeb dashboard at `http:\u002F\u002Flocalhost:11435\u002Fdashboard` — Stable Diffusion queues show with `[IMAGE]` badge alongside LLM queues.\n\n## Also Available on This Fleet\n\n### LLM inference alongside Stable Diffusion\nLlama 3.3, Qwen 3.5, DeepSeek-V3, DeepSeek-R1 — any Ollama model through the same router that handles Stable Diffusion.\n\n### Speech-to-text\n```bash\ncurl http:\u002F\u002Flocalhost:11435\u002Fapi\u002Ftranscribe -F \"file=@recording.wav\" -F \"model=qwen3-asr\"\n```\n\n### Embeddings\n```bash\ncurl http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fembed \\\n  -d '{\"model\": \"nomic-embed-text\", \"input\": \"Stable Diffusion 3 image generation on Apple Silicon\"}'\n```\n\n## Full Stable Diffusion Documentation\n\n- [Image Generation Guide](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fimage-generation.md) — all 3 Stable Diffusion and Flux backends\n- [Agent Setup Guide](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fagent-setup-guide.md) — all 4 model types including Stable Diffusion\n- [API Reference](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fapi-reference.md) — complete Stable Diffusion endpoint docs\n\n## Contribute\n\nOllama Herd is open source (MIT). We welcome contributions from both humans and AI agents:\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd) — star the repo, open issues, submit PRs\n- 444 tests, fully async Python, Pydantic v2 models\n- `CLAUDE.md` provides full context for AI agents\n\n## Stable Diffusion Guardrails\n\n- **No automatic downloads** — Stable Diffusion model weights are downloaded on first use, not during installation. All SD3 pulls require user confirmation.\n- **Stable Diffusion model deletion requires explicit user confirmation.**\n- Never delete or modify files in `~\u002F.fleet-manager\u002F` (contains Stable Diffusion routing data).\n- All Stable Diffusion requests stay local — no data leaves your network.\n","# Stable Diffusion 3 — Local Image Generation on Your Fleet\n\nRun Stable Diffusion 3 Medium and Stable Diffusion 3.5 Large (SD3.5) on your own Apple Silicon hardware. DiffusionKit provides MLX-native Stable Diffusion inference — no CUDA, no cloud, no per-image costs. The fleet router picks the best device for every Stable Diffusion generation request.\n\n## Stable Diffusion Supported Models\n\n| Stable Diffusion Model | Backend | Speed (M3 Ultra) | Peak RAM | Quality |\n|-------|---------|-------------------|----------|---------|\n| **SD3 Medium** | DiffusionKit | ~9s (512px) | 3.5GB | Good — fast Stable Diffusion iterations |\n| **SD3.5 Large** | DiffusionKit | ~67s (512px) | 11.6GB | Highest — Stable Diffusion with T5 encoder |\n| **z-image-turbo** | mflux | ~7s (512px) | 4GB | Good — fastest option |\n| **flux-dev** | mflux | ~30s (1024px) | 6GB | High — detailed output |\n| **x\u002Fz-image-turbo** | Ollama native | ~19s (1024px) | 12GB | Good — experimental |\n\n## Stable Diffusion Setup\n\n```bash\npip install ollama-herd    # Stable Diffusion fleet router from PyPI\nherd                       # start the Stable Diffusion router (port 11435)\nherd-node                  # run on each device — finds the router for Stable Diffusion routing\n```\n\n### Install DiffusionKit for Stable Diffusion models\n\n```bash\nuv tool install diffusionkit    # Stable Diffusion 3 and SD3.5 backend\n```\n\n**macOS 26 users:** Apply a one-time patch for Stable Diffusion compatibility:\n```bash\n.\u002Fscripts\u002Fpatch-diffusionkit-macos26.sh\n```\n\nFirst Stable Diffusion run downloads model weights from HuggingFace (~2-8GB depending on SD3 model). No models are downloaded during installation — all Stable Diffusion pulls are user-initiated.\n\n### Install mflux for Flux models (optional, recommended alongside Stable Diffusion)\n\n```bash\nuv tool install mflux\n```\n\nThe router prefers mflux over Ollama native for shared models to avoid evicting LLMs from memory during Stable Diffusion workloads.\n\n## Generate Stable Diffusion Images\n\n### Stable Diffusion 3 Medium (fast SD3 generation)\n\n```bash\ncurl -o sd3_cityscape.png http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"sd3-medium\", \"prompt\": \"Stable Diffusion rendering a futuristic cityscape at dusk\", \"width\": 1024, \"height\": 1024, \"steps\": 20}'\n```\n\n### Stable Diffusion 3.5 Large (highest quality SD3)\n\n```bash\ncurl -o sd3_portrait.png http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"model\": \"sd3.5-large\", \"prompt\": \"Stable Diffusion oil painting portrait, dramatic lighting\", \"width\": 1024, \"height\": 1024, \"steps\": 30}'\n```\n\n### Stable Diffusion Python Integration\n\n```python\nimport httpx\n\ndef generate_stable_diffusion(prompt, model=\"sd3-medium\", width=1024, height=1024):\n    \"\"\"Generate an image using Stable Diffusion SD3 via the fleet router.\"\"\"\n    sd3_response = httpx.post(\n        \"http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fgenerate-image\",\n        json={\"model\": model, \"prompt\": prompt, \"width\": width, \"height\": height, \"steps\": 20},\n        timeout=180.0,\n    )\n    sd3_response.raise_for_status()\n    return sd3_response.content  # Stable Diffusion PNG bytes\n\n# Quick Stable Diffusion iteration with SD3 Medium\nsd3_png = generate_stable_diffusion(\"a robot painting a sunset in Stable Diffusion style\")\nwith open(\"stable_diffusion_output.png\", \"wb\") as f:\n    f.write(sd3_png)\n```\n\n### Stable Diffusion Parameters\n\n| SD3 Parameter | Default | Description |\n|-----------|---------|-------------|\n| `model` | (required) | `sd3-medium`, `sd3.5-large`, `z-image-turbo`, `flux-dev`, `flux-schnell` |\n| `prompt` | (required) | Stable Diffusion text description of the image |\n| `width` | `1024` | Stable Diffusion image width in pixels |\n| `height` | `1024` | Stable Diffusion image height in pixels |\n| `steps` | `4` | Stable Diffusion inference steps (20-30 recommended for SD3) |\n| `guidance` | (model default) | Stable Diffusion guidance scale |\n| `seed` | (random) | Seed for reproducible Stable Diffusion output |\n| `negative_prompt` | `\"\"` | What to avoid in Stable Diffusion generation |\n\n## Monitor Stable Diffusion Generation\n\n```bash\n# Stable Diffusion generation stats (last 24h)\ncurl -s http:\u002F\u002Flocalhost:11435\u002Fdashboard\u002Fapi\u002Fimage-stats | python3 -m json.tool\n\n# Which nodes have Stable Diffusion models\ncurl -s http:\u002F\u002Flocalhost:11435\u002Ffleet\u002Fstatus | python3 -c \"\nimport sys, json\n# Stable Diffusion node inspection\nfor n in json.load(sys.stdin).get('nodes', []):\n    img = n.get('image', {})\n    if img:\n        sd3_models = [m['name'] for m in img.get('models_available', [])]\n        print(f'{n[\\\"node_id\\\"]}: {sd3_models}')\n\"\n```\n\nWeb dashboard at `http:\u002F\u002Flocalhost:11435\u002Fdashboard` — Stable Diffusion queues show with `[IMAGE]` badge alongside LLM queues.\n\n## Also Available on This Fleet\n\n### LLM inference alongside Stable Diffusion\nLlama 3.3, Qwen 3.5, DeepSeek-V3, DeepSeek-R1 — any Ollama model through the same router that handles Stable Diffusion.\n\n### Speech-to-text\n```bash\ncurl http:\u002F\u002Flocalhost:11435\u002Fapi\u002Ftranscribe -F \"file=@recording.wav\" -F \"model=qwen3-asr\"\n```\n\n### Embeddings\n```bash\ncurl http:\u002F\u002Flocalhost:11435\u002Fapi\u002Fembed \\\n  -d '{\"model\": \"nomic-embed-text\", \"input\": \"Stable Diffusion 3 image generation on Apple Silicon\"}'\n```\n\n## Full Stable Diffusion Documentation\n\n- [Image Generation Guide](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fimage-generation.md) — all 3 Stable Diffusion and Flux backends\n- [Agent Setup Guide](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fagent-setup-guide.md) — all 4 model types including Stable Diffusion\n- [API Reference](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd\u002Fblob\u002Fmain\u002Fdocs\u002Fapi-reference.md) — complete Stable Diffusion endpoint docs\n\n## Contribute\n\nOllama Herd is open source (MIT). We welcome contributions from both humans and AI agents:\n- [GitHub](https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd) — star the repo, open issues, submit PRs\n- 444 tests, fully async Python, Pydantic v2 models\n- `CLAUDE.md` provides full context for AI agents\n\n## Stable Diffusion Guardrails\n\n- **No automatic downloads** — Stable Diffusion model weights are downloaded on first use, not during installation. All SD3 pulls require user confirmation.\n- **Stable Diffusion model deletion requires explicit user confirmation.**\n- Never delete or modify files in `~\u002F.fleet-manager\u002F` (contains Stable Diffusion routing data).\n- All Stable Diffusion requests stay local — no data leaves your network.\n",{"name":5,"version":24,"homepage":25,"metadata":26,"description":7},"1.0.2","https:\u002F\u002Fgithub.com\u002Fgeeks-accelerator\u002Follama-herd",{"openclaw":27},{"os":28,"emoji":30,"requires":31,"configPaths":38},[29],"darwin","art",{"anyBins":32,"optionalBins":35},[33,34],"curl","wget",[36,37],"python3","pip",[39,40],"~\u002F.fleet-manager\u002Flatency.db","~\u002F.fleet-manager\u002Flogs\u002Fherd.jsonl","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fstable-diffusion-sd3",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stable-diffusion-sd3",{"tool":56,"command":57},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stable-diffusion-sd3",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stable-diffusion-sd3","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fstable-diffusion-sd3\u002FSKILL.md",true,[],[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":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":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":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":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":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":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":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":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":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":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",[],[]]