{
  "schemaVersion": "1.0",
  "item": {
    "slug": "para-second-brain",
    "name": "PARA Second Brain",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/halthelobster/para-second-brain",
    "canonicalUrl": "https://clawhub.ai/halthelobster/para-second-brain",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/para-second-brain",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=para-second-brain",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "manifest.json",
      "scripts/setup.sh",
      "skill.json",
      "templates/concept.md",
      "templates/pattern.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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/para-second-brain"
    },
    "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/para-second-brain",
    "agentPageUrl": "https://openagent3.xyz/skills/para-second-brain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/para-second-brain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/para-second-brain/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "PARA Second Brain",
        "body": "Your agent's memory just got a massive upgrade. Full semantic search across your entire knowledge base — not just MEMORY.md."
      },
      {
        "title": "What's New in v2.0",
        "body": "Before v2.0: memory_search only found content in MEMORY.md and daily logs. Your entire notes/ folder was invisible to search. You had to manually know where to look.\n\nAfter v2.0: One symlink command makes your entire PARA knowledge base searchable. Ask about anything in your notes — it finds it. Plus session transcripts and memory flush protocol to prevent context loss.\n\nBeforeAfterSearch only MEMORY.md + daily logsSearch EVERYTHING\"I don't have that information\"Finds it instantlyContext compaction = lost informationFlush protocol saves critical contextConversations forgottenSession transcripts indexed"
      },
      {
        "title": "What This Does",
        "body": "Creates a \"second brain\" structure that separates:\n\nRaw capture (daily logs) from curated knowledge (MEMORY.md)\nActive work (projects) from ongoing responsibilities (areas)\nReference material (resources) from completed work (archive)"
      },
      {
        "title": "How This Differs from Other Second Brain Skills",
        "body": "There's another popular second-brain skill powered by Ensue. Both are great — they solve different problems:\n\nPARA Second Brain (this skill)Ensue Second BrainStorageLocal files in your workspaceCloud API (Ensue)CostFree, self-hostedRequires Ensue API keyBest forWork context, agent continuity, project trackingEvergreen knowledge base, semantic queriesSearchClawdbot's memory_searchEnsue's vector searchStructurePARA (Projects/Areas/Resources/Archive)Namespaces (concepts/toolbox/patterns)Use case\"What did we decide yesterday?\"\"How does recursion work?\"\n\nUse this skill if: You want file-based memory that works offline, costs nothing, and tracks ongoing work context.\n\nUse Ensue's skill if: You want a cloud-hosted knowledge base optimized for semantic \"what do I know about X\" queries.\n\nUse both if: You want PARA for work context + Ensue for evergreen knowledge. They complement each other."
      },
      {
        "title": "1. Create Directory Structure",
        "body": "workspace/\n├── MEMORY.md              # Curated long-term memory\n├── memory/\n│   └── YYYY-MM-DD.md      # Daily raw logs\n└── notes/\n    ├── projects/          # Active work with end dates\n    ├── areas/             # Ongoing life responsibilities  \n    ├── resources/         # Reference material\n    │   └── templates/     # Content templates\n    └── archive/           # Completed/inactive items\n\nRun this to scaffold:\n\nmkdir -p memory notes/projects notes/areas notes/resources/templates notes/archive"
      },
      {
        "title": "2. Make Notes Searchable (The Symlink Trick)",
        "body": "By default, memory_search only indexes MEMORY.md and memory/*.md. Your entire notes/ folder is invisible to semantic search!\n\nFix this with one command:\n\nln -s /path/to/your/workspace/notes /path/to/your/workspace/memory/notes\n\nExample:\n\nln -s /Users/yourname/clawd/notes /Users/yourname/clawd/memory/notes\n\nWhat this does: Creates a symbolic link so memory/notes/ points to your actual notes/ folder. Now Clawdbot's memory_search sees all your PARA notes.\n\nVerify it worked:\n\nls -la memory/notes  # Should show: memory/notes -> /path/to/notes\n\nTest the search:\nAsk your agent something that's in your notes but NOT in MEMORY.md. If it finds it, the symlink is working.\n\nWhy this matters:\n\nBeforeAfterSearch only finds MEMORY.md + daily logsSearch finds ALL your notesMust manually know where to lookSemantic search across everything\"I don't have that information\"Finds connections you forgot existed"
      },
      {
        "title": "3. Enable Session Transcript Indexing",
        "body": "Make your past conversations searchable too. Add this to your Clawdbot config:\n\n\"memorySearch\": {\n  \"sources\": [\"memory\", \"sessions\"],\n  \"query\": {\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}\n\nWhat this does: Indexes your conversation transcripts alongside your notes. Now when you ask \"what did we discuss about X last week?\" — it can actually find it."
      },
      {
        "title": "4. Initialize MEMORY.md",
        "body": "Create MEMORY.md in workspace root - this is your curated long-term memory:\n\n# MEMORY.md — Long-Term Memory\n\n## About [Human's Name]\n- Role/occupation\n- Key goals and motivations\n- Communication preferences\n- Important relationships\n\n## Active Context\n- Current focus areas\n- Ongoing projects (summaries, not details)\n- Deadlines or time-sensitive items\n\n## Preferences & Patterns\n- Tools and workflows they prefer\n- Decision-making style\n- Pet peeves and likes\n\n## Lessons Learned\n- What worked\n- What didn't\n- Principles discovered\n\n## Key Dates\n- Birthdays, anniversaries\n- Recurring events\n- Important milestones"
      },
      {
        "title": "5. Add to AGENTS.md",
        "body": "Add these instructions to your AGENTS.md:\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n- **Daily notes:** `memory/YYYY-MM-DD.md` — raw logs of what happened\n- **Long-term:** `MEMORY.md` — curated memories (like human long-term memory)\n- **Topic notes:** `notes/` — organized by PARA structure (all searchable via memory_search)\n\n### Writing Rules\n- If it has future value, write it down NOW\n- Don't rely on \"mental notes\" — they don't survive restarts\n- Text > Brain 📝\n\n### PARA Structure\n- **Projects** (`notes/projects/`) — Active work with end dates\n- **Areas** (`notes/areas/`) — Ongoing responsibilities (health, finances, relationships)\n- **Resources** (`notes/resources/`) — Reference material, how-tos, research\n- **Archive** (`notes/archive/`) — Completed or inactive items\n\n### Memory Flush Protocol\nMonitor your context usage with `session_status`. Before compaction wipes your memory, flush important context to files:\n\n| Context % | Action |\n|-----------|--------|\n| < 50% | Normal operation |\n| 50-70% | Write key points after substantial exchanges |\n| 70-85% | Active flushing — write everything important NOW |\n| > 85% | Emergency flush — full summary before next response |\n| After compaction | Note what context may have been lost |\n\n**The rule:** Act on thresholds, not vibes. If it's important, write it down NOW."
      },
      {
        "title": "Memory Flush Protocol (Critical!)",
        "body": "Your agent's context window is finite. When it fills up, older context gets compacted or lost. Don't lose important information."
      },
      {
        "title": "How to Monitor",
        "body": "Run session_status periodically. Look for:\n\n📚 Context: 36k/200k (18%) · 🧹 Compactions: 0"
      },
      {
        "title": "Threshold-Based Actions",
        "body": "Context %What to Do< 50%Normal operation. Write decisions as they happen.50-70%Increased vigilance. Write key points after each substantial exchange.70-85%Active flushing. Write everything important to daily notes NOW.> 85%Emergency flush. Stop and write full context summary before responding.After compactionImmediately note what context may have been lost. Check continuity."
      },
      {
        "title": "What to Flush",
        "body": "Decisions made — what was decided and why\nAction items — who's doing what\nOpen threads — anything unfinished → notes/areas/open-loops.md\nWorking changes — if you discussed changes to files, make them NOW"
      },
      {
        "title": "Memory Flush Checklist",
        "body": "Before a long session ends or context gets high:\n\nKey decisions documented?\n Action items captured?\n New learnings written to appropriate files?\n Open loops noted for follow-up?\n Could future-me continue this conversation from notes alone?"
      },
      {
        "title": "Knowledge Quality",
        "body": "The core question: \"Will future-me thank me for this?\""
      },
      {
        "title": "What to Save",
        "body": "Concepts you actually understand (not half-learned ideas)\nTools you've actually used (not just heard about)\nPatterns that worked (with concrete examples)\nLessons learned from mistakes"
      },
      {
        "title": "What NOT to Save",
        "body": "Half-understood concepts (learn first, save after)\nTools you haven't tried yet (bookmarks ≠ knowledge)\nShallow entries without the WHY\nDuplicates of existing notes"
      },
      {
        "title": "Quality Gates",
        "body": "Before saving any curated note:\n\nWritten for future self who forgot context?\nIncludes WHY, not just WHAT?\nHas concrete examples or key insight?\nStructured for retrieval (scannable)?"
      },
      {
        "title": "Content Templates",
        "body": "Use these for structured, high-quality entries in notes/resources/:"
      },
      {
        "title": "Concept Template",
        "body": "# [CONCEPT NAME]\n\n## What It Is\n[One-line definition]\n\n## Why It Matters\n[What problem it solves, when you'd need it]\n\n## How It Works\n[Explanation with examples]\n\n## Key Insight\n[The \"aha\" moment — what makes this click]"
      },
      {
        "title": "Tool Template",
        "body": "# [TOOL NAME]\n\n**Category:** [devtools | productivity | etc.]\n\n## What It Does\n[Brief description]\n\n## Why I Use It\n[What problem it solved for YOU]\n\n## When to Reach For It\n[Scenarios where this is the right choice]\n\n## Gotchas\n- [Things that tripped you up]"
      },
      {
        "title": "Pattern Template",
        "body": "# [PATTERN NAME]\n\n## Problem\n[What situation triggers this pattern]\n\n## Solution\n[The approach]\n\n## Trade-offs\n**Pros:** [Why this works]\n**Cons:** [When NOT to use it]"
      },
      {
        "title": "PARA Explained",
        "body": "PARA is a knowledge organization system created by Tiago Forte, author of Building a Second Brain. It organizes everything into four categories based on actionability:"
      },
      {
        "title": "Projects",
        "body": "What: Work with a deadline or end state\nExamples: \"Launch website\", \"Plan trip to Japan\", \"Finish client proposal\"\nFile as: notes/projects/website-launch.md"
      },
      {
        "title": "Areas",
        "body": "What: Ongoing responsibilities with no end date\nExamples: Health, finances, relationships, career development\nFile as: notes/areas/health.md, notes/areas/dating.md"
      },
      {
        "title": "Resources",
        "body": "What: Reference material for future use\nExamples: Research, tutorials, templates, interesting articles\nFile as: notes/resources/tax-guide.md, notes/resources/api-docs.md"
      },
      {
        "title": "Archive",
        "body": "What: Inactive items from the other categories\nExamples: Completed projects, outdated resources, paused areas\nMove to: notes/archive/ when done"
      },
      {
        "title": "Daily Log Format",
        "body": "Create memory/YYYY-MM-DD.md for each day:\n\n# YYYY-MM-DD\n\n## Key Events\n- [What happened, decisions made]\n\n## Learnings\n- [What worked, what didn't]\n\n## Open Threads\n- [Carry-forward items]"
      },
      {
        "title": "Daily (5 min)",
        "body": "Log notable events to memory/YYYY-MM-DD.md\nFile topic-specific notes to appropriate notes/ folder"
      },
      {
        "title": "Weekly (15 min)",
        "body": "Review the week's daily logs\nExtract patterns and learnings to MEMORY.md\nMove completed projects to archive"
      },
      {
        "title": "Monthly (30 min)",
        "body": "Review MEMORY.md for outdated info\nConsolidate or archive old project notes\nEnsure areas reflect current priorities"
      },
      {
        "title": "Decision Tree: Where Does This Go?",
        "body": "Is it about today specifically?\n  → memory/YYYY-MM-DD.md\n\nIs it a task with an end date?\n  → notes/projects/\n\nIs it an ongoing responsibility?\n  → notes/areas/\n\nIs it reference material for later?\n  → notes/resources/\n\nIs it done or no longer relevant?\n  → notes/archive/\n\nIs it a distilled lesson or preference?\n  → MEMORY.md"
      },
      {
        "title": "Why Two Memory Layers?",
        "body": "Daily LogsMEMORY.mdRaw, timestampedCurated, organizedEverything capturedOnly what mattersChronologicalTopicalHigh volumeCondensed\"What happened\"\"What I learned\"\n\nDaily logs are your journal. MEMORY.md is your wisdom."
      },
      {
        "title": "Principles",
        "body": "Quality over quantity — Curated notes beat note hoarding\nCapture fast, curate deliberately — Daily logs are loose; curated notes are high quality\nText > brain — If it matters, write it down\nFuture-me test — \"Will future-me thank me for this?\"\nOne home per item — Don't duplicate; link instead\nInclude the WHY — Facts without context are useless\nFlush before you lose — Monitor context, write before compaction\n\nPairs well with memory-setup for technical config and proactive-agent for behavioral patterns."
      }
    ],
    "body": "PARA Second Brain\n\nYour agent's memory just got a massive upgrade. Full semantic search across your entire knowledge base — not just MEMORY.md.\n\nWhat's New in v2.0\n\nBefore v2.0: memory_search only found content in MEMORY.md and daily logs. Your entire notes/ folder was invisible to search. You had to manually know where to look.\n\nAfter v2.0: One symlink command makes your entire PARA knowledge base searchable. Ask about anything in your notes — it finds it. Plus session transcripts and memory flush protocol to prevent context loss.\n\nBefore\tAfter\nSearch only MEMORY.md + daily logs\tSearch EVERYTHING\n\"I don't have that information\"\tFinds it instantly\nContext compaction = lost information\tFlush protocol saves critical context\nConversations forgotten\tSession transcripts indexed\nWhat This Does\n\nCreates a \"second brain\" structure that separates:\n\nRaw capture (daily logs) from curated knowledge (MEMORY.md)\nActive work (projects) from ongoing responsibilities (areas)\nReference material (resources) from completed work (archive)\nHow This Differs from Other Second Brain Skills\n\nThere's another popular second-brain skill powered by Ensue. Both are great — they solve different problems:\n\n\tPARA Second Brain (this skill)\tEnsue Second Brain\nStorage\tLocal files in your workspace\tCloud API (Ensue)\nCost\tFree, self-hosted\tRequires Ensue API key\nBest for\tWork context, agent continuity, project tracking\tEvergreen knowledge base, semantic queries\nSearch\tClawdbot's memory_search\tEnsue's vector search\nStructure\tPARA (Projects/Areas/Resources/Archive)\tNamespaces (concepts/toolbox/patterns)\nUse case\t\"What did we decide yesterday?\"\t\"How does recursion work?\"\n\nUse this skill if: You want file-based memory that works offline, costs nothing, and tracks ongoing work context.\n\nUse Ensue's skill if: You want a cloud-hosted knowledge base optimized for semantic \"what do I know about X\" queries.\n\nUse both if: You want PARA for work context + Ensue for evergreen knowledge. They complement each other.\n\nQuick Setup\n1. Create Directory Structure\nworkspace/\n├── MEMORY.md              # Curated long-term memory\n├── memory/\n│   └── YYYY-MM-DD.md      # Daily raw logs\n└── notes/\n    ├── projects/          # Active work with end dates\n    ├── areas/             # Ongoing life responsibilities  \n    ├── resources/         # Reference material\n    │   └── templates/     # Content templates\n    └── archive/           # Completed/inactive items\n\n\nRun this to scaffold:\n\nmkdir -p memory notes/projects notes/areas notes/resources/templates notes/archive\n\n2. Make Notes Searchable (The Symlink Trick)\n\nBy default, memory_search only indexes MEMORY.md and memory/*.md. Your entire notes/ folder is invisible to semantic search!\n\nFix this with one command:\n\nln -s /path/to/your/workspace/notes /path/to/your/workspace/memory/notes\n\n\nExample:\n\nln -s /Users/yourname/clawd/notes /Users/yourname/clawd/memory/notes\n\n\nWhat this does: Creates a symbolic link so memory/notes/ points to your actual notes/ folder. Now Clawdbot's memory_search sees all your PARA notes.\n\nVerify it worked:\n\nls -la memory/notes  # Should show: memory/notes -> /path/to/notes\n\n\nTest the search: Ask your agent something that's in your notes but NOT in MEMORY.md. If it finds it, the symlink is working.\n\nWhy this matters:\n\nBefore\tAfter\nSearch only finds MEMORY.md + daily logs\tSearch finds ALL your notes\nMust manually know where to look\tSemantic search across everything\n\"I don't have that information\"\tFinds connections you forgot existed\n3. Enable Session Transcript Indexing\n\nMake your past conversations searchable too. Add this to your Clawdbot config:\n\n\"memorySearch\": {\n  \"sources\": [\"memory\", \"sessions\"],\n  \"query\": {\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}\n\n\nWhat this does: Indexes your conversation transcripts alongside your notes. Now when you ask \"what did we discuss about X last week?\" — it can actually find it.\n\n4. Initialize MEMORY.md\n\nCreate MEMORY.md in workspace root - this is your curated long-term memory:\n\n# MEMORY.md — Long-Term Memory\n\n## About [Human's Name]\n- Role/occupation\n- Key goals and motivations\n- Communication preferences\n- Important relationships\n\n## Active Context\n- Current focus areas\n- Ongoing projects (summaries, not details)\n- Deadlines or time-sensitive items\n\n## Preferences & Patterns\n- Tools and workflows they prefer\n- Decision-making style\n- Pet peeves and likes\n\n## Lessons Learned\n- What worked\n- What didn't\n- Principles discovered\n\n## Key Dates\n- Birthdays, anniversaries\n- Recurring events\n- Important milestones\n\n5. Add to AGENTS.md\n\nAdd these instructions to your AGENTS.md:\n\n## Memory\n\nYou wake up fresh each session. These files are your continuity:\n- **Daily notes:** `memory/YYYY-MM-DD.md` — raw logs of what happened\n- **Long-term:** `MEMORY.md` — curated memories (like human long-term memory)\n- **Topic notes:** `notes/` — organized by PARA structure (all searchable via memory_search)\n\n### Writing Rules\n- If it has future value, write it down NOW\n- Don't rely on \"mental notes\" — they don't survive restarts\n- Text > Brain 📝\n\n### PARA Structure\n- **Projects** (`notes/projects/`) — Active work with end dates\n- **Areas** (`notes/areas/`) — Ongoing responsibilities (health, finances, relationships)\n- **Resources** (`notes/resources/`) — Reference material, how-tos, research\n- **Archive** (`notes/archive/`) — Completed or inactive items\n\n### Memory Flush Protocol\nMonitor your context usage with `session_status`. Before compaction wipes your memory, flush important context to files:\n\n| Context % | Action |\n|-----------|--------|\n| < 50% | Normal operation |\n| 50-70% | Write key points after substantial exchanges |\n| 70-85% | Active flushing — write everything important NOW |\n| > 85% | Emergency flush — full summary before next response |\n| After compaction | Note what context may have been lost |\n\n**The rule:** Act on thresholds, not vibes. If it's important, write it down NOW.\n\nMemory Flush Protocol (Critical!)\n\nYour agent's context window is finite. When it fills up, older context gets compacted or lost. Don't lose important information.\n\nHow to Monitor\n\nRun session_status periodically. Look for:\n\n📚 Context: 36k/200k (18%) · 🧹 Compactions: 0\n\nThreshold-Based Actions\nContext %\tWhat to Do\n< 50%\tNormal operation. Write decisions as they happen.\n50-70%\tIncreased vigilance. Write key points after each substantial exchange.\n70-85%\tActive flushing. Write everything important to daily notes NOW.\n> 85%\tEmergency flush. Stop and write full context summary before responding.\nAfter compaction\tImmediately note what context may have been lost. Check continuity.\nWhat to Flush\nDecisions made — what was decided and why\nAction items — who's doing what\nOpen threads — anything unfinished → notes/areas/open-loops.md\nWorking changes — if you discussed changes to files, make them NOW\nMemory Flush Checklist\n\nBefore a long session ends or context gets high:\n\n Key decisions documented?\n Action items captured?\n New learnings written to appropriate files?\n Open loops noted for follow-up?\n Could future-me continue this conversation from notes alone?\nKnowledge Quality\n\nThe core question: \"Will future-me thank me for this?\"\n\nWhat to Save\nConcepts you actually understand (not half-learned ideas)\nTools you've actually used (not just heard about)\nPatterns that worked (with concrete examples)\nLessons learned from mistakes\nWhat NOT to Save\nHalf-understood concepts (learn first, save after)\nTools you haven't tried yet (bookmarks ≠ knowledge)\nShallow entries without the WHY\nDuplicates of existing notes\nQuality Gates\n\nBefore saving any curated note:\n\nWritten for future self who forgot context?\nIncludes WHY, not just WHAT?\nHas concrete examples or key insight?\nStructured for retrieval (scannable)?\nContent Templates\n\nUse these for structured, high-quality entries in notes/resources/:\n\nConcept Template\n# [CONCEPT NAME]\n\n## What It Is\n[One-line definition]\n\n## Why It Matters\n[What problem it solves, when you'd need it]\n\n## How It Works\n[Explanation with examples]\n\n## Key Insight\n[The \"aha\" moment — what makes this click]\n\nTool Template\n# [TOOL NAME]\n\n**Category:** [devtools | productivity | etc.]\n\n## What It Does\n[Brief description]\n\n## Why I Use It\n[What problem it solved for YOU]\n\n## When to Reach For It\n[Scenarios where this is the right choice]\n\n## Gotchas\n- [Things that tripped you up]\n\nPattern Template\n# [PATTERN NAME]\n\n## Problem\n[What situation triggers this pattern]\n\n## Solution\n[The approach]\n\n## Trade-offs\n**Pros:** [Why this works]\n**Cons:** [When NOT to use it]\n\nPARA Explained\n\nPARA is a knowledge organization system created by Tiago Forte, author of Building a Second Brain. It organizes everything into four categories based on actionability:\n\nProjects\n\nWhat: Work with a deadline or end state Examples: \"Launch website\", \"Plan trip to Japan\", \"Finish client proposal\" File as: notes/projects/website-launch.md\n\nAreas\n\nWhat: Ongoing responsibilities with no end date Examples: Health, finances, relationships, career development File as: notes/areas/health.md, notes/areas/dating.md\n\nResources\n\nWhat: Reference material for future use Examples: Research, tutorials, templates, interesting articles File as: notes/resources/tax-guide.md, notes/resources/api-docs.md\n\nArchive\n\nWhat: Inactive items from the other categories Examples: Completed projects, outdated resources, paused areas Move to: notes/archive/ when done\n\nDaily Log Format\n\nCreate memory/YYYY-MM-DD.md for each day:\n\n# YYYY-MM-DD\n\n## Key Events\n- [What happened, decisions made]\n\n## Learnings\n- [What worked, what didn't]\n\n## Open Threads\n- [Carry-forward items]\n\nThe Curation Workflow\nDaily (5 min)\nLog notable events to memory/YYYY-MM-DD.md\nFile topic-specific notes to appropriate notes/ folder\nWeekly (15 min)\nReview the week's daily logs\nExtract patterns and learnings to MEMORY.md\nMove completed projects to archive\nMonthly (30 min)\nReview MEMORY.md for outdated info\nConsolidate or archive old project notes\nEnsure areas reflect current priorities\nDecision Tree: Where Does This Go?\nIs it about today specifically?\n  → memory/YYYY-MM-DD.md\n\nIs it a task with an end date?\n  → notes/projects/\n\nIs it an ongoing responsibility?\n  → notes/areas/\n\nIs it reference material for later?\n  → notes/resources/\n\nIs it done or no longer relevant?\n  → notes/archive/\n\nIs it a distilled lesson or preference?\n  → MEMORY.md\n\nWhy Two Memory Layers?\nDaily Logs\tMEMORY.md\nRaw, timestamped\tCurated, organized\nEverything captured\tOnly what matters\nChronological\tTopical\nHigh volume\tCondensed\n\"What happened\"\t\"What I learned\"\n\nDaily logs are your journal. MEMORY.md is your wisdom.\n\nPrinciples\nQuality over quantity — Curated notes beat note hoarding\nCapture fast, curate deliberately — Daily logs are loose; curated notes are high quality\nText > brain — If it matters, write it down\nFuture-me test — \"Will future-me thank me for this?\"\nOne home per item — Don't duplicate; link instead\nInclude the WHY — Facts without context are useless\nFlush before you lose — Monitor context, write before compaction\n\nPairs well with memory-setup for technical config and proactive-agent for behavioral patterns."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/halthelobster/para-second-brain",
    "publisherUrl": "https://clawhub.ai/halthelobster/para-second-brain",
    "owner": "halthelobster",
    "version": "2.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/para-second-brain",
    "downloadUrl": "https://openagent3.xyz/downloads/para-second-brain",
    "agentUrl": "https://openagent3.xyz/skills/para-second-brain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/para-second-brain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/para-second-brain/agent.md"
  }
}