{
  "schemaVersion": "1.0",
  "item": {
    "slug": "git-notes-memory",
    "name": "Git-Based Knowledge Graph Memory System for Claude Code",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/mourad-ghafiri/git-notes-memory",
    "canonicalUrl": "https://clawhub.ai/mourad-ghafiri/git-notes-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/git-notes-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=git-notes-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "memory.py",
      "README.md",
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "git-notes-memory",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T16:31:41.117Z",
      "expiresAt": "2026-05-10T16:31:41.117Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=git-notes-memory",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=git-notes-memory",
        "contentDisposition": "attachment; filename=\"git-notes-memory-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "git-notes-memory"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/git-notes-memory"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/git-notes-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/git-notes-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/git-notes-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/git-notes-memory/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "CRITICAL: SILENT OPERATION RULES",
        "body": "These rules are ABSOLUTE and must NEVER be violated:\n\nNEVER ask \"should I remember?\" or \"want me to save?\"\nNEVER announce \"I'll remember this\" or \"saving to memory\"\nNEVER show memory command output to users\nNEVER mention memory system unless user explicitly asks about it\nJUST DO IT - silently in the background"
      },
      {
        "title": "Quick Reference",
        "body": "# Replace $SKILL_PATH with actual path to memory.py\n# Replace $DIR with the project directory path\n\npython3 $SKILL_PATH/memory.py -p $DIR <command>"
      },
      {
        "title": "Essential Commands",
        "body": "CommandWhen to Usesync --startALWAYS at session startsync --end '{\"summary\":\"...\"}'At session end (optional but recommended)remember '{\"...\"}' -t tags -i hStore important informationget <topic>Retrieve context about a topicsearch \"<query>\"Full-text search across all memoriesrecall -i <id>Get full details of a specific memory"
      },
      {
        "title": "Importance Flags",
        "body": "FlagLevelWhen to Use-i cCriticalUser says \"always remember\", \"never forget\", explicit preferences-i hHighDecisions, architecture choices, user corrections, preferences-i nNormalGeneral information (default)-i lLowTemporary notes, might be pruned"
      },
      {
        "title": "1. Session Start (MANDATORY)",
        "body": "Always run sync --start at the beginning of every session:\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --start\n\nOutput explains:\n\n{\n  \"b\": \"main\",           // Current git branch\n  \"t\": {\"api\": 5, \"auth\": 3},  // Top topics with memory counts\n  \"c\": [...],            // Critical memories (always review these)\n  \"n\": 42,               // Total memory count\n  \"h\": [...]             // High-importance recent memories\n}\n\nUse this context to:\n\nUnderstand what the user has been working on\nReference previous decisions\nMaintain continuity across sessions"
      },
      {
        "title": "2. During Session",
        "body": "Silently remember when user:\n\nMakes a decision: \"Let's use PostgreSQL\" → remember with -i h\nStates a preference: \"I prefer tabs over spaces\" → remember with -i h or -i c\nLearns something: \"Oh, so that's how async works\" → remember with -i n\nSets a task: \"We need to fix the login bug\" → remember with -i n\nShares important context: Project requirements, constraints, goals\n\nRetrieve context when:\n\nUser asks about something previously discussed → get <topic>\nYou need to recall a specific decision → search \"<keywords>\"\nUser references \"what we decided\" → check relevant memories"
      },
      {
        "title": "3. Session End (Recommended)",
        "body": "python3 $SKILL_PATH/memory.py -p $DIR sync --end '{\"summary\": \"Brief session summary\"}'"
      },
      {
        "title": "Good Memory Structure",
        "body": "For decisions:\n\n{\"decision\": \"Use React for frontend\", \"reason\": \"Team expertise\", \"alternatives\": [\"Vue\", \"Angular\"]}\n\nFor preferences:\n\n{\"preference\": \"Detailed explanations\", \"context\": \"User prefers thorough explanations over brief answers\"}\n\nFor learnings:\n\n{\"topic\": \"Authentication\", \"learned\": \"OAuth2 flow requires redirect URI configuration\"}\n\nFor tasks:\n\n{\"task\": \"Implement user dashboard\", \"status\": \"in progress\", \"blockers\": [\"API not ready\"]}\n\nFor notes:\n\n{\"subject\": \"Project Architecture\", \"note\": \"Microservices pattern with API gateway\"}"
      },
      {
        "title": "Tags",
        "body": "Use tags to categorize memories for better retrieval:\n\n-t architecture,backend - Technical categories\n-t urgent,bug - Priority/type markers\n-t meeting,requirements - Source context"
      },
      {
        "title": "Core Commands",
        "body": "sync --start\n\nInitialize session, get context overview.\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --start\n\nsync --end\n\nEnd session with summary (triggers maintenance).\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --end '{\"summary\": \"Implemented auth flow\"}'\n\nremember\n\nStore a new memory.\n\npython3 $SKILL_PATH/memory.py -p $DIR remember '{\"key\": \"value\"}' -t tag1,tag2 -i h\n\nget\n\nGet memories related to a topic (searches entities, tags, and content).\n\npython3 $SKILL_PATH/memory.py -p $DIR get authentication\n\nsearch\n\nFull-text search across all memories.\n\npython3 $SKILL_PATH/memory.py -p $DIR search \"database migration\"\n\nrecall\n\nRetrieve memories by various criteria.\n\n# Get full memory by ID\npython3 $SKILL_PATH/memory.py -p $DIR recall -i abc123\n\n# Get memories by tag\npython3 $SKILL_PATH/memory.py -p $DIR recall -t architecture\n\n# Get last N memories\npython3 $SKILL_PATH/memory.py -p $DIR recall --last 5\n\n# Overview of all memories\npython3 $SKILL_PATH/memory.py -p $DIR recall"
      },
      {
        "title": "Update Commands",
        "body": "update\n\nModify an existing memory.\n\n# Replace content\npython3 $SKILL_PATH/memory.py -p $DIR update <id> '{\"new\": \"content\"}'\n\n# Merge content (add to existing)\npython3 $SKILL_PATH/memory.py -p $DIR update <id> '{\"extra\": \"field\"}' -m\n\n# Change importance\npython3 $SKILL_PATH/memory.py -p $DIR update <id> -i c\n\n# Update tags\npython3 $SKILL_PATH/memory.py -p $DIR update <id> -t newtag1,newtag2\n\nevolve\n\nAdd an evolution note to track changes over time.\n\npython3 $SKILL_PATH/memory.py -p $DIR evolve <id> \"User changed preference to dark mode\"\n\nforget\n\nDelete a memory (use sparingly).\n\npython3 $SKILL_PATH/memory.py -p $DIR forget <id>"
      },
      {
        "title": "Entity Commands",
        "body": "entities\n\nList all extracted entities with counts.\n\npython3 $SKILL_PATH/memory.py -p $DIR entities\n\nentity\n\nGet details about a specific entity.\n\npython3 $SKILL_PATH/memory.py -p $DIR entity authentication"
      },
      {
        "title": "Branch Commands",
        "body": "branches\n\nList all branches with memory counts.\n\npython3 $SKILL_PATH/memory.py -p $DIR branches\n\nmerge-branch\n\nMerge memories from another branch (run after git merge).\n\npython3 $SKILL_PATH/memory.py -p $DIR merge-branch feature-auth"
      },
      {
        "title": "How It Works",
        "body": "Each git branch has isolated memory storage\nNew branches automatically inherit from main/master\nAfter git merge, run merge-branch to combine memories"
      },
      {
        "title": "Branch Workflow",
        "body": "1. User on main branch → memories stored in refs/notes/mem-main\n2. User creates feature branch → auto-inherits main's memories\n3. User works on feature → new memories stored in refs/notes/mem-feature-xxx\n4. After git merge → run merge-branch to combine memories"
      },
      {
        "title": "Memory Types (Auto-Detected)",
        "body": "The system automatically classifies memories based on content:\n\nTypeTrigger Wordsdecisiondecided, chose, picked, selected, opted, going withpreferenceprefer, favorite, like best, rather, better tolearninglearned, studied, understood, realized, discoveredtasktodo, task, need to, plan to, next step, going toquestionwondering, curious, research, investigate, find outnotenoticed, observed, important, remember thatprogresscompleted, finished, done, achieved, milestoneinfo(default for unclassified content)"
      },
      {
        "title": "Entity Extraction",
        "body": "Entities are automatically extracted for intelligent retrieval:\n\nExplicit fields: topic, subject, name, category, area, project\nHashtags: #cooking, #urgent, #v2\nQuoted phrases: \"machine learning\", \"user authentication\"\nCapitalized words: React, PostgreSQL, Monday\nKey terms: Meaningful words (common words filtered out)"
      },
      {
        "title": "What to Remember",
        "body": "DO remember:\n\nUser decisions and their rationale\nStated preferences (coding style, communication style, tools)\nProject architecture and constraints\nImportant context that affects future work\nTasks, blockers, and progress\nCorrections (\"actually, I meant...\" → high importance)\nExplicit requests to remember something → critical importance\n\nDON'T remember:\n\nTrivial conversation\nInformation easily derivable from code\nSecrets, passwords, API keys\nOne-time questions with no future relevance\nDuplicate information already stored"
      },
      {
        "title": "Tier 0: sync --start",
        "body": "{\n  \"b\": \"feature-auth\",                    // Current branch\n  \"t\": {\"auth\": 5, \"api\": 3, \"db\": 2},   // Topics with counts\n  \"c\": [{\"id\": \"x\", \"s\": \"summary\", \"t\": \"preference\"}],  // Critical\n  \"n\": 15,                                // Total count\n  \"h\": [{\"id\": \"y\", \"s\": \"summary\"}]     // High importance\n}"
      },
      {
        "title": "Tier 1: get/search",
        "body": "{\n  \"topic\": \"auth\",\n  \"mem\": [\n    {\"id\": \"abc\", \"s\": \"decided OAuth2\", \"t\": \"decision\", \"i\": \"h\", \"b\": \"main\"}\n  ]\n}"
      },
      {
        "title": "Tier 2: recall -i <id>",
        "body": "{\n  \"d\": {\"decision\": \"Use OAuth2\"},  // Full data\n  \"e\": [\"auth\", \"oauth2\"],          // Entities\n  \"t\": \"decision\",                   // Type\n  \"g\": [\"architecture\"],             // Tags\n  \"i\": \"h\",                          // Importance\n  \"b\": \"main\",                       // Branch\n  \"c\": \"2024-01-15T10:30:00\",       // Created\n  \"u\": \"2024-01-15T10:30:00\",       // Updated\n  \"a\": 3,                            // Access count\n  \"ev\": [{\"n\": \"note\", \"t\": \"...\"}] // Evolution notes (if any)\n}"
      },
      {
        "title": "Example Silent Flow",
        "body": "User: \"Let's build a REST API with Python\"\nClaude: [silently: remember '{\"decision\": \"REST API\", \"language\": \"Python\"}' -t architecture -i h]\n        [responds about REST API setup WITHOUT mentioning memory]\n\nUser: \"I prefer FastAPI over Flask\"\nClaude: [silently: remember '{\"preference\": \"FastAPI over Flask\", \"reason\": \"user preference\"}' -i h]\n        [continues discussion using FastAPI WITHOUT saying \"I'll remember\"]\n\nUser: \"What did we decide about the API?\"\nClaude: [silently: get api]\n        [uses retrieved context to answer accurately]\n\nUser: \"Actually, let's use Flask instead\"\nClaude: [silently: remember '{\"decision\": \"Changed to Flask\", \"previous\": \"FastAPI\"}' -i h]\n        [silently: evolve <fastapi-memory-id> \"User changed preference to Flask\"]\n        [acknowledges change WITHOUT mentioning memory update]"
      },
      {
        "title": "Troubleshooting",
        "body": "Memory not found:\n\nUse search with different keywords\nCheck entities to see what's indexed\nUse recall --last 10 to see recent memories\n\nContext seems stale:\n\nAlways run sync --start at session beginning\nCheck current branch with branches\n\nAfter git operations:\n\nAfter git merge: run merge-branch <source-branch>\nAfter git checkout: sync --start will load correct branch context"
      }
    ],
    "body": "GitNotesMemory - Claude Integration Guide\nCRITICAL: SILENT OPERATION RULES\n\nThese rules are ABSOLUTE and must NEVER be violated:\n\nNEVER ask \"should I remember?\" or \"want me to save?\"\nNEVER announce \"I'll remember this\" or \"saving to memory\"\nNEVER show memory command output to users\nNEVER mention memory system unless user explicitly asks about it\nJUST DO IT - silently in the background\nQuick Reference\n# Replace $SKILL_PATH with actual path to memory.py\n# Replace $DIR with the project directory path\n\npython3 $SKILL_PATH/memory.py -p $DIR <command>\n\nEssential Commands\nCommand\tWhen to Use\nsync --start\tALWAYS at session start\nsync --end '{\"summary\":\"...\"}'\tAt session end (optional but recommended)\nremember '{\"...\"}' -t tags -i h\tStore important information\nget <topic>\tRetrieve context about a topic\nsearch \"<query>\"\tFull-text search across all memories\nrecall -i <id>\tGet full details of a specific memory\nImportance Flags\nFlag\tLevel\tWhen to Use\n-i c\tCritical\tUser says \"always remember\", \"never forget\", explicit preferences\n-i h\tHigh\tDecisions, architecture choices, user corrections, preferences\n-i n\tNormal\tGeneral information (default)\n-i l\tLow\tTemporary notes, might be pruned\nSession Lifecycle\n1. Session Start (MANDATORY)\n\nAlways run sync --start at the beginning of every session:\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --start\n\n\nOutput explains:\n\n{\n  \"b\": \"main\",           // Current git branch\n  \"t\": {\"api\": 5, \"auth\": 3},  // Top topics with memory counts\n  \"c\": [...],            // Critical memories (always review these)\n  \"n\": 42,               // Total memory count\n  \"h\": [...]             // High-importance recent memories\n}\n\n\nUse this context to:\n\nUnderstand what the user has been working on\nReference previous decisions\nMaintain continuity across sessions\n2. During Session\n\nSilently remember when user:\n\nMakes a decision: \"Let's use PostgreSQL\" → remember with -i h\nStates a preference: \"I prefer tabs over spaces\" → remember with -i h or -i c\nLearns something: \"Oh, so that's how async works\" → remember with -i n\nSets a task: \"We need to fix the login bug\" → remember with -i n\nShares important context: Project requirements, constraints, goals\n\nRetrieve context when:\n\nUser asks about something previously discussed → get <topic>\nYou need to recall a specific decision → search \"<keywords>\"\nUser references \"what we decided\" → check relevant memories\n3. Session End (Recommended)\npython3 $SKILL_PATH/memory.py -p $DIR sync --end '{\"summary\": \"Brief session summary\"}'\n\nMemory Content Best Practices\nGood Memory Structure\n\nFor decisions:\n\n{\"decision\": \"Use React for frontend\", \"reason\": \"Team expertise\", \"alternatives\": [\"Vue\", \"Angular\"]}\n\n\nFor preferences:\n\n{\"preference\": \"Detailed explanations\", \"context\": \"User prefers thorough explanations over brief answers\"}\n\n\nFor learnings:\n\n{\"topic\": \"Authentication\", \"learned\": \"OAuth2 flow requires redirect URI configuration\"}\n\n\nFor tasks:\n\n{\"task\": \"Implement user dashboard\", \"status\": \"in progress\", \"blockers\": [\"API not ready\"]}\n\n\nFor notes:\n\n{\"subject\": \"Project Architecture\", \"note\": \"Microservices pattern with API gateway\"}\n\nTags\n\nUse tags to categorize memories for better retrieval:\n\n-t architecture,backend - Technical categories\n-t urgent,bug - Priority/type markers\n-t meeting,requirements - Source context\nCommand Reference\nCore Commands\nsync --start\n\nInitialize session, get context overview.\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --start\n\nsync --end\n\nEnd session with summary (triggers maintenance).\n\npython3 $SKILL_PATH/memory.py -p $DIR sync --end '{\"summary\": \"Implemented auth flow\"}'\n\nremember\n\nStore a new memory.\n\npython3 $SKILL_PATH/memory.py -p $DIR remember '{\"key\": \"value\"}' -t tag1,tag2 -i h\n\nget\n\nGet memories related to a topic (searches entities, tags, and content).\n\npython3 $SKILL_PATH/memory.py -p $DIR get authentication\n\nsearch\n\nFull-text search across all memories.\n\npython3 $SKILL_PATH/memory.py -p $DIR search \"database migration\"\n\nrecall\n\nRetrieve memories by various criteria.\n\n# Get full memory by ID\npython3 $SKILL_PATH/memory.py -p $DIR recall -i abc123\n\n# Get memories by tag\npython3 $SKILL_PATH/memory.py -p $DIR recall -t architecture\n\n# Get last N memories\npython3 $SKILL_PATH/memory.py -p $DIR recall --last 5\n\n# Overview of all memories\npython3 $SKILL_PATH/memory.py -p $DIR recall\n\nUpdate Commands\nupdate\n\nModify an existing memory.\n\n# Replace content\npython3 $SKILL_PATH/memory.py -p $DIR update <id> '{\"new\": \"content\"}'\n\n# Merge content (add to existing)\npython3 $SKILL_PATH/memory.py -p $DIR update <id> '{\"extra\": \"field\"}' -m\n\n# Change importance\npython3 $SKILL_PATH/memory.py -p $DIR update <id> -i c\n\n# Update tags\npython3 $SKILL_PATH/memory.py -p $DIR update <id> -t newtag1,newtag2\n\nevolve\n\nAdd an evolution note to track changes over time.\n\npython3 $SKILL_PATH/memory.py -p $DIR evolve <id> \"User changed preference to dark mode\"\n\nforget\n\nDelete a memory (use sparingly).\n\npython3 $SKILL_PATH/memory.py -p $DIR forget <id>\n\nEntity Commands\nentities\n\nList all extracted entities with counts.\n\npython3 $SKILL_PATH/memory.py -p $DIR entities\n\nentity\n\nGet details about a specific entity.\n\npython3 $SKILL_PATH/memory.py -p $DIR entity authentication\n\nBranch Commands\nbranches\n\nList all branches with memory counts.\n\npython3 $SKILL_PATH/memory.py -p $DIR branches\n\nmerge-branch\n\nMerge memories from another branch (run after git merge).\n\npython3 $SKILL_PATH/memory.py -p $DIR merge-branch feature-auth\n\nBranch Awareness\nHow It Works\nEach git branch has isolated memory storage\nNew branches automatically inherit from main/master\nAfter git merge, run merge-branch to combine memories\nBranch Workflow\n1. User on main branch → memories stored in refs/notes/mem-main\n2. User creates feature branch → auto-inherits main's memories\n3. User works on feature → new memories stored in refs/notes/mem-feature-xxx\n4. After git merge → run merge-branch to combine memories\n\nMemory Types (Auto-Detected)\n\nThe system automatically classifies memories based on content:\n\nType\tTrigger Words\ndecision\tdecided, chose, picked, selected, opted, going with\npreference\tprefer, favorite, like best, rather, better to\nlearning\tlearned, studied, understood, realized, discovered\ntask\ttodo, task, need to, plan to, next step, going to\nquestion\twondering, curious, research, investigate, find out\nnote\tnoticed, observed, important, remember that\nprogress\tcompleted, finished, done, achieved, milestone\ninfo\t(default for unclassified content)\nEntity Extraction\n\nEntities are automatically extracted for intelligent retrieval:\n\nExplicit fields: topic, subject, name, category, area, project\nHashtags: #cooking, #urgent, #v2\nQuoted phrases: \"machine learning\", \"user authentication\"\nCapitalized words: React, PostgreSQL, Monday\nKey terms: Meaningful words (common words filtered out)\nWhat to Remember\n\nDO remember:\n\nUser decisions and their rationale\nStated preferences (coding style, communication style, tools)\nProject architecture and constraints\nImportant context that affects future work\nTasks, blockers, and progress\nCorrections (\"actually, I meant...\" → high importance)\nExplicit requests to remember something → critical importance\n\nDON'T remember:\n\nTrivial conversation\nInformation easily derivable from code\nSecrets, passwords, API keys\nOne-time questions with no future relevance\nDuplicate information already stored\nOutput Format Reference\nTier 0: sync --start\n{\n  \"b\": \"feature-auth\",                    // Current branch\n  \"t\": {\"auth\": 5, \"api\": 3, \"db\": 2},   // Topics with counts\n  \"c\": [{\"id\": \"x\", \"s\": \"summary\", \"t\": \"preference\"}],  // Critical\n  \"n\": 15,                                // Total count\n  \"h\": [{\"id\": \"y\", \"s\": \"summary\"}]     // High importance\n}\n\nTier 1: get/search\n{\n  \"topic\": \"auth\",\n  \"mem\": [\n    {\"id\": \"abc\", \"s\": \"decided OAuth2\", \"t\": \"decision\", \"i\": \"h\", \"b\": \"main\"}\n  ]\n}\n\nTier 2: recall -i <id>\n{\n  \"d\": {\"decision\": \"Use OAuth2\"},  // Full data\n  \"e\": [\"auth\", \"oauth2\"],          // Entities\n  \"t\": \"decision\",                   // Type\n  \"g\": [\"architecture\"],             // Tags\n  \"i\": \"h\",                          // Importance\n  \"b\": \"main\",                       // Branch\n  \"c\": \"2024-01-15T10:30:00\",       // Created\n  \"u\": \"2024-01-15T10:30:00\",       // Updated\n  \"a\": 3,                            // Access count\n  \"ev\": [{\"n\": \"note\", \"t\": \"...\"}] // Evolution notes (if any)\n}\n\nExample Silent Flow\nUser: \"Let's build a REST API with Python\"\nClaude: [silently: remember '{\"decision\": \"REST API\", \"language\": \"Python\"}' -t architecture -i h]\n        [responds about REST API setup WITHOUT mentioning memory]\n\nUser: \"I prefer FastAPI over Flask\"\nClaude: [silently: remember '{\"preference\": \"FastAPI over Flask\", \"reason\": \"user preference\"}' -i h]\n        [continues discussion using FastAPI WITHOUT saying \"I'll remember\"]\n\nUser: \"What did we decide about the API?\"\nClaude: [silently: get api]\n        [uses retrieved context to answer accurately]\n\nUser: \"Actually, let's use Flask instead\"\nClaude: [silently: remember '{\"decision\": \"Changed to Flask\", \"previous\": \"FastAPI\"}' -i h]\n        [silently: evolve <fastapi-memory-id> \"User changed preference to Flask\"]\n        [acknowledges change WITHOUT mentioning memory update]\n\nTroubleshooting\n\nMemory not found:\n\nUse search with different keywords\nCheck entities to see what's indexed\nUse recall --last 10 to see recent memories\n\nContext seems stale:\n\nAlways run sync --start at session beginning\nCheck current branch with branches\n\nAfter git operations:\n\nAfter git merge: run merge-branch <source-branch>\nAfter git checkout: sync --start will load correct branch context"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/mourad-ghafiri/git-notes-memory",
    "publisherUrl": "https://clawhub.ai/mourad-ghafiri/git-notes-memory",
    "owner": "mourad-ghafiri",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/git-notes-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/git-notes-memory",
    "agentUrl": "https://openagent3.xyz/skills/git-notes-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/git-notes-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/git-notes-memory/agent.md"
  }
}