[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758W2MZYBVRHT74V0SW4NX3":3,"skill-same:01M758W2MZYBVRHT74V0SW4NX3":53},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M758W2MZYBVRHT74V0SW4NX3","engram",null,"Engram — memoria persistente para agentes. CLI y MCP son COMPLEMENTARIOS con routing dinámico: CLI cubre 80% (search\u002Fsave\u002Fcontext\u002Fstats\u002Ftimeline\u002Fexport\u002Fsync), MCP cubre 20% exclusivo (save_prompt, session lifecycle, suggest_topic_key, capture_passive). Skill con routing dinámico CLI→MCP según capacidad. Trigger: When saving\u002Frecalling memories, session lifecycle, or using engram from terminal vs agent.","davidcoachdev\u002Fdcfiles","davidcoachdev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69812733?v=4","01M758C4BR16TAV1N47W319E9V","David H. Caycedo Blum.","01M758C4CCZA2ZYGA0BGMXCDRH",1,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fengram\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: engram\ndescription: >\n  Engram — memoria persistente para agentes. CLI y MCP son COMPLEMENTARIOS con routing dinámico:\n  CLI cubre 80% (search\u002Fsave\u002Fcontext\u002Fstats\u002Ftimeline\u002Fexport\u002Fsync), MCP cubre 20% exclusivo\n  (save_prompt, session lifecycle, suggest_topic_key, capture_passive). Skill con routing dinámico\n  CLI→MCP según capacidad. Trigger: When saving\u002Frecalling memories, session lifecycle, or using engram from terminal vs agent.\nlicense: MIT\nmetadata:\n  author: dc-dev\n  version: \"1.0\"\n  cli_version: \"1.10.0\"\n  mcp_command: \"engram mcp --tools=agent\"\n  mcp_profiles: \"agent=11, all=14, admin=3\"\n---\n\n## What is Engram?\n\nMemoria persistente que sobrevive a sessions y compactions — 660 sessions \u002F 1217 obs en este host:\n\n- **SQLite local** — `~\u002F.engram\u002Fengram.db` + sync a `.engram\u002F` chunks para git\n- **Projects** — dcfiles, tts-control, wsl-bridge, etc. (filtro por `--project`)\n- **No es grep** — FTS5 + topic_keys para decisiones evolutivas\n\n## CLI vs MCP — Routing Dinámico (NO 1:1)\n\n**Engram es dinámico: CLI hace 80%, MCP hace 20% exclusivo. No elijas uno — rutea según la operación.**\n\n| Operación | CLI (`engram \u003Ccmd>`) | MCP (`mem_*`) | Ruta recomendada |\n|---|---|---|---|\n| **Buscar** | `engram search \"query\" --project X --limit 10` | `mem_search` | ✅ **CLI** — más rápido en terminal, mismo FTS5 |\n| **Guardar** | `engram save \"Título\" \"What:...\" --type bugfix` | `mem_save` | ✅ **CLI** en terminal, MCP `mem_save` dentro de agente |\n| **Contexto** | `engram context [project]` | `mem_context` | ✅ CLI |\n| **Timeline** | `engram timeline \u003Cobs_id>` | `mem_timeline` (solo `--tools=all`) | ✅ CLI (MCP agent NO lo tiene) |\n| **Stats** | `engram stats` | `mem_stats` (solo `--tools=all`) | ✅ CLI (MCP agent NO lo tiene) |\n| **Export\u002FImport\u002FSync** | `engram export\u002Fsync --status` | ❌ | **CLI only** |\n| **TUI** | `engram tui` | ❌ | CLI only |\n| **Save prompt** | ❌ | `mem_save_prompt` | **MCP only** — no hay `engram save-prompt` |\n| **Session start\u002Fend** | ❌ | `mem_session_start`, `mem_session_end` | MCP only |\n| **Session summary** | ❌ | `mem_session_summary` | MCP only — el que usas al cerrar sesión |\n| **Suggest topic_key** | ❌ | `mem_suggest_topic_key` | MCP only |\n| **Capture passive** | ❌ | `mem_capture_passive` | MCP only — auto-extrae `## Key Learnings` |\n| **Get observation** | ❌ (usa `search` + lee) | `mem_get_observation` | MCP only para ID puntual |\n| **Update\u002FDelete** | ❌ | `mem_update`, `mem_delete` (all) | MCP only |\n\n**Regla de routing:**\n```bash\nif operacion in [search, save, context, timeline, stats, export, sync, tui]:\n  → usa CLI directo: engram \u003Ccmd>\nelse if operacion in [save_prompt, session_start\u002Fend\u002Fsummary, suggest_topic_key, capture_passive, get_observation]:\n  → usa MCP: mem_*\nelse:\n  → CLI no puede, MCP sí → usa MCP\n```\n\n> Verificado `engram mcp --tools=agent` → 11 tools, `--tools=all` → 14 tools. `agent` NO incluye `mem_timeline`\u002F`mem_stats`\u002F`mem_delete` — para esos usa CLI o `--tools=all`.\n\n## CLI Workflow (terminal — 80%)\n\n```bash\n# Buscar y contexto (lo que más usarás en terminal)\nengram search \"lightpanda\" --project tts-control --limit 10\nengram search \"codegraph\" --type architecture\nengram context tts-control        # últimas 20 obs\nengram context --limit 30         # global\n\n# Guardar (formato What\u002FWhy\u002FWhere\u002FLearned obligatorio)\nengram save \"Fixed N+1 in user list\" \"**What**: ... **Why**: ... **Where**: src\u002F...\" --type bugfix --project tts-control\n\n# Timeline y stats (solo CLI en perfil agent)\nengram timeline 695 --before 5 --after 5  # contexto alrededor de obs 695\nengram stats                              # 660 sessions, 1217 obs\n\n# Sync \u002F export (solo CLI)\nengram sync --status\nengram sync              # exporta chunk a .engram\u002F\nengram export backup.json\nengram import backup.json\n\n# TUI\nengram tui\n\n# HTTP API (alternativa a CLI)\nengram serve 7437  # http:\u002F\u002F127.0.0.1:7437\n```\n\n## MCP Workflow (agente — 20% exclusivo)\n\n**Config en opencode.json:**\n```json\n{\n  \"mcp\": {\n    \"engram\": {\n      \"command\": [\"engram\", \"mcp\", \"--tools=agent\"],\n      \"type\": \"local\"\n    }\n  }\n}\n```\n\n**Usa MCP solo para lo que CLI no puede:**\n\n```javascript\n\u002F\u002F 1. Save prompt (registrar lo que pidió el usuario)\nmem_save_prompt({ content: \"haz un TTS bridge\", project: \"tts-control\" })\n\n\u002F\u002F 2. Session lifecycle (obligatorio al iniciar\u002Fcerrar)\nmem_session_start({ id: \"sess-123\", project: \"tts-control\", directory: \"\u002Fhome\u002F...\" })\nmem_session_end({ id: \"sess-123\", summary: \"hecho X\" })\nmem_session_summary({ project: \"tts-control\", content: \"## Goal\\n...\\n## Accomplished\\n...\" })\n\n\u002F\u002F 3. Topic keys (decisiones evolutivas)\nmem_suggest_topic_key({ title: \"Auth model\", type: \"architecture\" })\n\u002F\u002F → architecture\u002Fauth-model\nmem_save({ title: \"Auth model\", content: \"...\", topic_key: \"architecture\u002Fauth-model\" })\n\n\u002F\u002F 4. Capture passive (auto-extrae Key Learnings)\nmem_capture_passive({ content: \"## Key Learnings:\\n- item 1\\n- item 2\", project: \"tts-control\" })\n\n\u002F\u002F 5. Get\u002FUpdate\u002FDelete por ID\nmem_get_observation({ id: 695 })\nmem_update({ id: 695, title: \"nuevo título\" })\n```\n\n**No uses MCP para lo que CLI ya hace:** `mem_search`\u002F`mem_save`\u002F`mem_context` en agente sí están bien, pero en terminal es más rápido `engram search\u002Fsave\u002Fcontext`.\n\n## Comparativa Final — Por qué Engram es dinámico\n\n```bash\n# TERMINAL — rápido, sin JSON-RPC\nengram search \"serena\" --limit 5\nengram save \"Decision X\" \"What: ...\" --project dcfiles\n\n# AGENTE — para lo exclusivo de MCP\nmem_save_prompt({ content: userPrompt })\nmem_session_summary({ content: \"## Goal\\n...\" })\n```\n\n| Escenario | Ruta |\n|---|---|\n| Estoy en terminal y quiero buscar\u002Fguardar | `engram search\u002Fsave` (CLI) |\n| Estoy en terminal y quiero stats\u002Ftimeline\u002Fsync | `engram stats\u002Ftimeline\u002Fsync` (CLI only) |\n| Agente necesita registrar prompt del usuario | `mem_save_prompt` (MCP only) |\n| Agente inicia\u002Fcierra sesión | `mem_session_start\u002Fend\u002Fsummary` (MCP only) |\n| Necesito topic_key para decisión evolutiva | `mem_suggest_topic_key` (MCP only) |\n| Quiero ver memoria por ID | `mem_get_observation` (MCP) o `engram search` + filtrar |\n\n## Instalación\n\n```bash\nengram --version  # 1.10.0 (update a 1.20.0: brew upgrade engram)\nengram setup opencode --help\n# DB: ~\u002F.engram\u002Fengram.db — no requiere init por proyecto (a diferencia de CodeGraph)\n```\n\n## Resources\n\n- CLI help: `engram --help`, `engram \u003Ccmd> --help`\n- MCP: `engram mcp --tools=agent` (stdio), `engram mcp --tools=all` para mem_stats\u002Ftimeline\n- TUI: `engram tui`\n- HTTP: `engram serve`\n","## What is Engram?\n\nMemoria persistente que sobrevive a sessions y compactions — 660 sessions \u002F 1217 obs en este host:\n\n- **SQLite local** — `~\u002F.engram\u002Fengram.db` + sync a `.engram\u002F` chunks para git\n- **Projects** — dcfiles, tts-control, wsl-bridge, etc. (filtro por `--project`)\n- **No es grep** — FTS5 + topic_keys para decisiones evolutivas\n\n## CLI vs MCP — Routing Dinámico (NO 1:1)\n\n**Engram es dinámico: CLI hace 80%, MCP hace 20% exclusivo. No elijas uno — rutea según la operación.**\n\n| Operación | CLI (`engram \u003Ccmd>`) | MCP (`mem_*`) | Ruta recomendada |\n|---|---|---|---|\n| **Buscar** | `engram search \"query\" --project X --limit 10` | `mem_search` | ✅ **CLI** — más rápido en terminal, mismo FTS5 |\n| **Guardar** | `engram save \"Título\" \"What:...\" --type bugfix` | `mem_save` | ✅ **CLI** en terminal, MCP `mem_save` dentro de agente |\n| **Contexto** | `engram context [project]` | `mem_context` | ✅ CLI |\n| **Timeline** | `engram timeline \u003Cobs_id>` | `mem_timeline` (solo `--tools=all`) | ✅ CLI (MCP agent NO lo tiene) |\n| **Stats** | `engram stats` | `mem_stats` (solo `--tools=all`) | ✅ CLI (MCP agent NO lo tiene) |\n| **Export\u002FImport\u002FSync** | `engram export\u002Fsync --status` | ❌ | **CLI only** |\n| **TUI** | `engram tui` | ❌ | CLI only |\n| **Save prompt** | ❌ | `mem_save_prompt` | **MCP only** — no hay `engram save-prompt` |\n| **Session start\u002Fend** | ❌ | `mem_session_start`, `mem_session_end` | MCP only |\n| **Session summary** | ❌ | `mem_session_summary` | MCP only — el que usas al cerrar sesión |\n| **Suggest topic_key** | ❌ | `mem_suggest_topic_key` | MCP only |\n| **Capture passive** | ❌ | `mem_capture_passive` | MCP only — auto-extrae `## Key Learnings` |\n| **Get observation** | ❌ (usa `search` + lee) | `mem_get_observation` | MCP only para ID puntual |\n| **Update\u002FDelete** | ❌ | `mem_update`, `mem_delete` (all) | MCP only |\n\n**Regla de routing:**\n```bash\nif operacion in [search, save, context, timeline, stats, export, sync, tui]:\n  → usa CLI directo: engram \u003Ccmd>\nelse if operacion in [save_prompt, session_start\u002Fend\u002Fsummary, suggest_topic_key, capture_passive, get_observation]:\n  → usa MCP: mem_*\nelse:\n  → CLI no puede, MCP sí → usa MCP\n```\n\n> Verificado `engram mcp --tools=agent` → 11 tools, `--tools=all` → 14 tools. `agent` NO incluye `mem_timeline`\u002F`mem_stats`\u002F`mem_delete` — para esos usa CLI o `--tools=all`.\n\n## CLI Workflow (terminal — 80%)\n\n```bash\n# Buscar y contexto (lo que más usarás en terminal)\nengram search \"lightpanda\" --project tts-control --limit 10\nengram search \"codegraph\" --type architecture\nengram context tts-control        # últimas 20 obs\nengram context --limit 30         # global\n\n# Guardar (formato What\u002FWhy\u002FWhere\u002FLearned obligatorio)\nengram save \"Fixed N+1 in user list\" \"**What**: ... **Why**: ... **Where**: src\u002F...\" --type bugfix --project tts-control\n\n# Timeline y stats (solo CLI en perfil agent)\nengram timeline 695 --before 5 --after 5  # contexto alrededor de obs 695\nengram stats                              # 660 sessions, 1217 obs\n\n# Sync \u002F export (solo CLI)\nengram sync --status\nengram sync              # exporta chunk a .engram\u002F\nengram export backup.json\nengram import backup.json\n\n# TUI\nengram tui\n\n# HTTP API (alternativa a CLI)\nengram serve 7437  # http:\u002F\u002F127.0.0.1:7437\n```\n\n## MCP Workflow (agente — 20% exclusivo)\n\n**Config en opencode.json:**\n```json\n{\n  \"mcp\": {\n    \"engram\": {\n      \"command\": [\"engram\", \"mcp\", \"--tools=agent\"],\n      \"type\": \"local\"\n    }\n  }\n}\n```\n\n**Usa MCP solo para lo que CLI no puede:**\n\n```javascript\n\u002F\u002F 1. Save prompt (registrar lo que pidió el usuario)\nmem_save_prompt({ content: \"haz un TTS bridge\", project: \"tts-control\" })\n\n\u002F\u002F 2. Session lifecycle (obligatorio al iniciar\u002Fcerrar)\nmem_session_start({ id: \"sess-123\", project: \"tts-control\", directory: \"\u002Fhome\u002F...\" })\nmem_session_end({ id: \"sess-123\", summary: \"hecho X\" })\nmem_session_summary({ project: \"tts-control\", content: \"## Goal\\n...\\n## Accomplished\\n...\" })\n\n\u002F\u002F 3. Topic keys (decisiones evolutivas)\nmem_suggest_topic_key({ title: \"Auth model\", type: \"architecture\" })\n\u002F\u002F → architecture\u002Fauth-model\nmem_save({ title: \"Auth model\", content: \"...\", topic_key: \"architecture\u002Fauth-model\" })\n\n\u002F\u002F 4. Capture passive (auto-extrae Key Learnings)\nmem_capture_passive({ content: \"## Key Learnings:\\n- item 1\\n- item 2\", project: \"tts-control\" })\n\n\u002F\u002F 5. Get\u002FUpdate\u002FDelete por ID\nmem_get_observation({ id: 695 })\nmem_update({ id: 695, title: \"nuevo título\" })\n```\n\n**No uses MCP para lo que CLI ya hace:** `mem_search`\u002F`mem_save`\u002F`mem_context` en agente sí están bien, pero en terminal es más rápido `engram search\u002Fsave\u002Fcontext`.\n\n## Comparativa Final — Por qué Engram es dinámico\n\n```bash\n# TERMINAL — rápido, sin JSON-RPC\nengram search \"serena\" --limit 5\nengram save \"Decision X\" \"What: ...\" --project dcfiles\n\n# AGENTE — para lo exclusivo de MCP\nmem_save_prompt({ content: userPrompt })\nmem_session_summary({ content: \"## Goal\\n...\" })\n```\n\n| Escenario | Ruta |\n|---|---|\n| Estoy en terminal y quiero buscar\u002Fguardar | `engram search\u002Fsave` (CLI) |\n| Estoy en terminal y quiero stats\u002Ftimeline\u002Fsync | `engram stats\u002Ftimeline\u002Fsync` (CLI only) |\n| Agente necesita registrar prompt del usuario | `mem_save_prompt` (MCP only) |\n| Agente inicia\u002Fcierra sesión | `mem_session_start\u002Fend\u002Fsummary` (MCP only) |\n| Necesito topic_key para decisión evolutiva | `mem_suggest_topic_key` (MCP only) |\n| Quiero ver memoria por ID | `mem_get_observation` (MCP) o `engram search` + filtrar |\n\n## Instalación\n\n```bash\nengram --version  # 1.10.0 (update a 1.20.0: brew upgrade engram)\nengram setup opencode --help\n# DB: ~\u002F.engram\u002Fengram.db — no requiere init por proyecto (a diferencia de CodeGraph)\n```\n\n## Resources\n\n- CLI help: `engram --help`, `engram \u003Ccmd> --help`\n- MCP: `engram mcp --tools=agent` (stdio), `engram mcp --tools=all` para mem_stats\u002Ftimeline\n- TUI: `engram tui`\n- HTTP: `engram serve`\n",{"name":5,"license":15,"metadata":24,"description":30},{"author":25,"version":26,"cli_version":27,"mcp_command":28,"mcp_profiles":29},"dc-dev","1.0","1.10.0","engram mcp --tools=agent","agent=11, all=14, admin=3","Engram — memoria persistente para agentes. CLI y MCP son COMPLEMENTARIOS con routing dinámico: CLI cubre 80% (search\u002Fsave\u002Fcontext\u002Fstats\u002Ftimeline\u002Fexport\u002Fsync), MCP cubre 20% exclusivo (save_prompt, session lifecycle, suggest_topic_key, capture_passive). Skill con routing dinámico CLI→MCP según capacidad. Trigger: When saving\u002Frecalling memories, session lifecycle, or using engram from terminal vs agent.\n","main","5dc86f90a5cbe45db3acd917825461b3ed6937fb","config\u002F.config\u002Fopencode\u002Fskills\u002Fengram",0,"https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev","🌐 Apasionado por crear soluciones web escalables y eficientes. \r\n🧑‍🏫 Coach Dev.\r\n💻 Frontend Dev. \r\n🎚️Backend Dev.\r\n📊 Agile\u002FScrum.\r\n🚀100% remoto.","2026-08-26 07:28:05",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add davidcoachdev\u002Fdcfiles --skill engram",{"tool":45,"command":46},"bunx","bunx skills add davidcoachdev\u002Fdcfiles --skill engram",{"tool":48,"command":49},"pnpm","pnpm dlx skills add davidcoachdev\u002Fdcfiles --skill engram","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fengram\u002FSKILL.md",true,[],[54,62,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7740FETMZY1VTYAEFY1TWY7","zustand-5","Zustand 5 state management patterns. Trigger: When managing React state with Zustand.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fzustand-5\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M773ZZM9V68SA1AKP4WF4J29","zod-4","Zod 4 schema validation patterns. Trigger: When using Zod for validation - breaking changes from v3.","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fzod-4\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M773ZJFR90CQAY0N9QR40QVP","x-bookmark-quote-posts","Workflow para revisar bookmarks de X\u002FTwitter y convertirlos en drafts de quote posts. Accede a la sección de bookmarks vía browser headless, extrae posts recientes, y genera drafts con voz personal del usuario. No publica ni muta X — solo genera contenido para revisión. Trigger: X bookmarks, Twitter bookmarks, quote posts, bookmark automation, crear quote posts, revisar bookmarks, growth content X.","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fx-bookmark-quote-posts\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M773Z2RGV3786FV310SDB0YD","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M773YJH3KDSW467CSS63CSRJ","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M773Y3S3H2CPRK5S8YFHWB5C","work-unit-commits","Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.","https:\u002F\u002Fgithub.com\u002Fdavidcoachdev\u002Fdcfiles\u002Fblob\u002Fmain\u002Fconfig\u002F.config\u002Fopencode\u002Fskills\u002Fwork-unit-commits\u002FSKILL.md",[],[]]