[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBGPYKNP6QZDGQTPBYA9PG":3,"skill-same:01M6DBGPYKNP6QZDGQTPBYA9PG":73},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6DBGPYKNP6QZDGQTPBYA9PG","knowledge-ops",null,"Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fknowledge-ops\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"ops","knowledge","knowledge ops","vector stores","local","across","knowledge base","organize","files","knowledge systems","ingestion","MCP","save","vector","search","git","repos","sync","storage","memory","2026-11-10 10:12:30",false,"---\nname: knowledge-ops\ndescription: Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.\norigin: ECC\n---\n\n# Knowledge Operations\n\nManage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across multiple stores.\n\nPrefer the live workspace model:\n- code work lives in the real cloned repos\n- active execution context lives in GitHub, Linear, and repo-local working-context files\n- broader human-facing notes can live in a non-repo context\u002Farchive folder\n- durable cross-machine memory belongs in the knowledge base, not in a shadow repo workspace\n\n## When to Activate\n\n- User wants to save information to their knowledge base\n- Ingesting documents, conversations, or data into structured storage\n- Syncing knowledge across systems (local files, MCP memory, Supabase, Git repos)\n- Deduplicating or organizing existing knowledge\n- User says \"save this to KB\", \"sync knowledge\", \"what do I know about X\", \"ingest this\", \"update the knowledge base\"\n- Any knowledge management task beyond simple memory recall\n\n## Knowledge Architecture\n\n### Layer 1: Active execution truth\n- **Sources:** GitHub issues, PRs, discussions, release notes, Linear issues\u002Fprojects\u002Fdocs\n- **Use for:** the current operational state of the work\n- **Rule:** if something affects an active engineering plan, roadmap, rollout, or release, prefer putting it here first\n\n### Layer 2: Claude Code Memory (Quick Access)\n- **Path:** `~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F`\n- **Format:** Markdown files with frontmatter\n- **Types:** user preferences, feedback, project context, reference\n- **Use for:** quick-access context that persists across conversations\n- **Automatically loaded at session start**\n\n### Layer 3: MCP Memory Server (Structured Knowledge Graph)\n- **Access:** MCP memory tools (create_entities, create_relations, add_observations, search_nodes)\n- **Use for:** Semantic search across all stored memories, relationship mapping\n- **Cross-session persistence with queryable graph structure**\n\n### Layer 4: Knowledge base repo \u002F durable document store\n- **Use for:** curated durable notes, session exports, synthesized research, operator memory, long-form docs\n- **Rule:** this is the preferred durable store for cross-machine context when the content is not repo-owned code\n\n### Layer 5: External Data Store (Supabase, PostgreSQL, etc.)\n- **Use for:** Structured data, large document storage, full-text search\n- **Good for:** Documents too large for memory files, data needing SQL queries\n\n### Layer 6: Local context\u002Farchive folder\n- **Use for:** human-facing notes, archived gameplans, local media organization, temporary non-code docs\n- **Rule:** writable for information storage, but not a shadow code workspace\n- **Do not use for:** active code changes or repo truth that should live upstream\n\n## Ingestion Workflow\n\nWhen new knowledge needs to be captured:\n\n### 1. Classify\nWhat type of knowledge is it?\n- Business decision -> memory file (project type) + MCP memory\n- Active roadmap \u002F release \u002F implementation state -> GitHub + Linear first\n- Personal preference -> memory file (user\u002Ffeedback type)\n- Reference info -> memory file (reference type) + MCP memory\n- Large document -> external data store + summary in memory\n- Conversation\u002Fsession -> knowledge base repo + short summary in memory\n\n### 2. Deduplicate\nCheck if this knowledge already exists:\n- Search memory files for existing entries\n- Query MCP memory with relevant terms\n- Check whether the information already exists in GitHub or Linear before creating another local note\n- Do not create duplicates. Update existing entries instead.\n\n### 3. Store\nWrite to appropriate layer(s):\n- Always update Claude Code memory for quick access\n- Use MCP memory for semantic searchability and relationship mapping\n- Update GitHub \u002F Linear first when the information changes live project truth\n- Commit to the knowledge base repo for durable long-form additions\n\n### 4. Index\nUpdate any relevant indexes or summary files.\n\n## Sync Operations\n\n### Conversation Sync\nPeriodically sync conversation history into the knowledge base:\n- Sources: Claude session files, Codex sessions, other agent sessions\n- Destination: knowledge base repo\n- Generate a session index for quick browsing\n- Commit and push\n\n### Workspace State Sync\nMirror important workspace configuration and scripts to the knowledge base:\n- Generate directory maps\n- Redact sensitive config before committing\n- Track changes over time\n- Do not treat the knowledge base or archive folder as the live code workspace\n\n### GitHub \u002F Linear Sync\nWhen the information affects active execution:\n- update the relevant GitHub issue, PR, discussion, release notes, or roadmap thread\n- attach supporting docs to Linear when the work needs durable planning context\n- only mirror a local note afterwards if it still adds value\n\n### Cross-Source Knowledge Sync\nPull knowledge from multiple sources into one place:\n- Claude\u002FChatGPT\u002FGrok conversation exports\n- Browser bookmarks\n- GitHub activity events\n- Write status summary, commit and push\n\n## Memory Patterns\n\n```\n# Short-term: current session context\nUse TodoWrite for in-session task tracking\n\n# Medium-term: project memory files\nWrite to ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F for cross-session recall\n\n# Long-term: GitHub \u002F Linear \u002F KB\nPut active execution truth in GitHub + Linear\nPut durable synthesized context in the knowledge base repo\n\n# Semantic layer: MCP knowledge graph\nUse mcp__memory__create_entities for permanent structured data\nUse mcp__memory__create_relations for relationship mapping\nUse mcp__memory__add_observations for new facts about known entities\nUse mcp__memory__search_nodes to find existing knowledge\n```\n\n## Best Practices\n\n- Keep memory files concise. Archive old data rather than letting files grow unbounded.\n- Use frontmatter (YAML) for metadata on all knowledge files.\n- Deduplicate before storing. Search first, then create or update.\n- Prefer one canonical home per fact set. Avoid parallel copies of the same plan across local notes, repo files, and tracker docs.\n- Redact sensitive information (API keys, passwords) before committing to Git.\n- Use consistent naming conventions for knowledge files (lowercase-kebab-case).\n- Tag entries with topics\u002Fcategories for easier retrieval.\n\n## Quality Gate\n\nBefore completing any knowledge operation:\n- no duplicate entries created\n- sensitive data redacted from any Git-tracked files\n- indexes and summaries updated\n- appropriate storage layer chosen for the data type\n- cross-references added where relevant\n","# Knowledge Operations\n\nManage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across multiple stores.\n\nPrefer the live workspace model:\n- code work lives in the real cloned repos\n- active execution context lives in GitHub, Linear, and repo-local working-context files\n- broader human-facing notes can live in a non-repo context\u002Farchive folder\n- durable cross-machine memory belongs in the knowledge base, not in a shadow repo workspace\n\n## When to Activate\n\n- User wants to save information to their knowledge base\n- Ingesting documents, conversations, or data into structured storage\n- Syncing knowledge across systems (local files, MCP memory, Supabase, Git repos)\n- Deduplicating or organizing existing knowledge\n- User says \"save this to KB\", \"sync knowledge\", \"what do I know about X\", \"ingest this\", \"update the knowledge base\"\n- Any knowledge management task beyond simple memory recall\n\n## Knowledge Architecture\n\n### Layer 1: Active execution truth\n- **Sources:** GitHub issues, PRs, discussions, release notes, Linear issues\u002Fprojects\u002Fdocs\n- **Use for:** the current operational state of the work\n- **Rule:** if something affects an active engineering plan, roadmap, rollout, or release, prefer putting it here first\n\n### Layer 2: Claude Code Memory (Quick Access)\n- **Path:** `~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F`\n- **Format:** Markdown files with frontmatter\n- **Types:** user preferences, feedback, project context, reference\n- **Use for:** quick-access context that persists across conversations\n- **Automatically loaded at session start**\n\n### Layer 3: MCP Memory Server (Structured Knowledge Graph)\n- **Access:** MCP memory tools (create_entities, create_relations, add_observations, search_nodes)\n- **Use for:** Semantic search across all stored memories, relationship mapping\n- **Cross-session persistence with queryable graph structure**\n\n### Layer 4: Knowledge base repo \u002F durable document store\n- **Use for:** curated durable notes, session exports, synthesized research, operator memory, long-form docs\n- **Rule:** this is the preferred durable store for cross-machine context when the content is not repo-owned code\n\n### Layer 5: External Data Store (Supabase, PostgreSQL, etc.)\n- **Use for:** Structured data, large document storage, full-text search\n- **Good for:** Documents too large for memory files, data needing SQL queries\n\n### Layer 6: Local context\u002Farchive folder\n- **Use for:** human-facing notes, archived gameplans, local media organization, temporary non-code docs\n- **Rule:** writable for information storage, but not a shadow code workspace\n- **Do not use for:** active code changes or repo truth that should live upstream\n\n## Ingestion Workflow\n\nWhen new knowledge needs to be captured:\n\n### 1. Classify\nWhat type of knowledge is it?\n- Business decision -> memory file (project type) + MCP memory\n- Active roadmap \u002F release \u002F implementation state -> GitHub + Linear first\n- Personal preference -> memory file (user\u002Ffeedback type)\n- Reference info -> memory file (reference type) + MCP memory\n- Large document -> external data store + summary in memory\n- Conversation\u002Fsession -> knowledge base repo + short summary in memory\n\n### 2. Deduplicate\nCheck if this knowledge already exists:\n- Search memory files for existing entries\n- Query MCP memory with relevant terms\n- Check whether the information already exists in GitHub or Linear before creating another local note\n- Do not create duplicates. Update existing entries instead.\n\n### 3. Store\nWrite to appropriate layer(s):\n- Always update Claude Code memory for quick access\n- Use MCP memory for semantic searchability and relationship mapping\n- Update GitHub \u002F Linear first when the information changes live project truth\n- Commit to the knowledge base repo for durable long-form additions\n\n### 4. Index\nUpdate any relevant indexes or summary files.\n\n## Sync Operations\n\n### Conversation Sync\nPeriodically sync conversation history into the knowledge base:\n- Sources: Claude session files, Codex sessions, other agent sessions\n- Destination: knowledge base repo\n- Generate a session index for quick browsing\n- Commit and push\n\n### Workspace State Sync\nMirror important workspace configuration and scripts to the knowledge base:\n- Generate directory maps\n- Redact sensitive config before committing\n- Track changes over time\n- Do not treat the knowledge base or archive folder as the live code workspace\n\n### GitHub \u002F Linear Sync\nWhen the information affects active execution:\n- update the relevant GitHub issue, PR, discussion, release notes, or roadmap thread\n- attach supporting docs to Linear when the work needs durable planning context\n- only mirror a local note afterwards if it still adds value\n\n### Cross-Source Knowledge Sync\nPull knowledge from multiple sources into one place:\n- Claude\u002FChatGPT\u002FGrok conversation exports\n- Browser bookmarks\n- GitHub activity events\n- Write status summary, commit and push\n\n## Memory Patterns\n\n```\n# Short-term: current session context\nUse TodoWrite for in-session task tracking\n\n# Medium-term: project memory files\nWrite to ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F for cross-session recall\n\n# Long-term: GitHub \u002F Linear \u002F KB\nPut active execution truth in GitHub + Linear\nPut durable synthesized context in the knowledge base repo\n\n# Semantic layer: MCP knowledge graph\nUse mcp__memory__create_entities for permanent structured data\nUse mcp__memory__create_relations for relationship mapping\nUse mcp__memory__add_observations for new facts about known entities\nUse mcp__memory__search_nodes to find existing knowledge\n```\n\n## Best Practices\n\n- Keep memory files concise. Archive old data rather than letting files grow unbounded.\n- Use frontmatter (YAML) for metadata on all knowledge files.\n- Deduplicate before storing. Search first, then create or update.\n- Prefer one canonical home per fact set. Avoid parallel copies of the same plan across local notes, repo files, and tracker docs.\n- Redact sensitive information (API keys, passwords) before committing to Git.\n- Use consistent naming conventions for knowledge files (lowercase-kebab-case).\n- Tag entries with topics\u002Fcategories for easier retrieval.\n\n## Quality Gate\n\nBefore completing any knowledge operation:\n- no duplicate entries created\n- sensitive data redacted from any Git-tracked files\n- indexes and summaries updated\n- appropriate storage layer chosen for the data type\n- cross-references added where relevant\n",{"name":5,"origin":52,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fknowledge-ops","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill knowledge-ops",{"tool":65,"command":66},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill knowledge-ops",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill knowledge-ops","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fknowledge-ops\u002FSKILL.md",true,[],[74,96,121,148,162,178],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":47},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":47},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[102],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[104,105,106,107,108,109,110,111,112,113,114,115,116,117,90,118,119,31,120,38],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","do",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":133,"publishedAt":47},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[127,130],{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[134,135,136,137,138,139,140,141,142,143,105,144,145,146,147],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":47},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[150,155,156,157,158,159,160,161],"setup","report","project","installation","project setup","issues","state",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":47},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[168],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[164,170,86,171,172,173,90,174,175,176,177],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":179,"name":155,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":47},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[155,157,31,35,159,184],"interactive"]