[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PDPY9PSE1CNNCD2T1WYA8":3,"skill-same:01M77PDPY9PSE1CNNCD2T1WYA8":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M77PDPY9PSE1CNNCD2T1WYA8","obsidian-knowledge-base",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fo\u002Fobsidian-knowledge-base\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# SKILL.md — Obsidian Dual-Layer Knowledge Base System\n\n> Version: 0.2 | Updated: 2026-05-22\n> Skill Name: obsidian-knowledge-base\n> Tags: knowledge-management, obsidian, rag, agent-memory, daily-pipeline\n> Install: `npx clawhub@latest install obsidian-knowledge-base`\n\n---\n\n## 1. Skill Overview\n\nTurn Obsidian into a **Dual-Layer Knowledge Base** for AI Agents, supporting the full pipeline: daily incremental writes → structured indexing → context injection.\n\n- **INBOX Layer**: Raw material entry (articles\u002Fconversations\u002Flogs), unstructured\n- **WIKI Layer**: Structured knowledge (concept cards + Q&A cards), directly callable by AI\n\n**Core Value**: Solve the \"knowledge base paralysis\" problem — knowledge gets written in, but the AI starts from scratch every time because it doesn't know what's in the base.\n\n---\n\n## 2. Directory Structure\n\n```\nObsidian Vault\u002F\n├── INBOX\u002F                          # Input layer (raw materials)\n│   ├── articles\u002F                   # Articles (daily scheduled writes)\n│   ├── conversations\u002F            # Conversation records\n│   └── 日志\u002F                    # Work logs (date-indexed)\n└── wiki\u002F\n    ├── qa\u002F                        # Q&A knowledge cards\n    │   ├── index.md              # Q&A index (by category)\n    │   └── Q-分类-摘要.md\n    └── concepts\u002F                  # Concept cards (deep structure)\n        ├── index.md              # Concept card index\n        ├── 概念-主题名.md\n        └── ...\n```\n\n---\n\n## 3. Knowledge Base Scale & Context Strategy\n\n| Layer | File Count | Raw Size | How It Enters Context |\n|-------|-----------|---------|----------------------|\n| INBOX\u002Farticles | Daily incremental | Raw material | Not injected; searched on demand |\n| wiki\u002Fqa | ~200-500 cards | ~500KB-1MB | **Daily 6KB summary injected** |\n| wiki\u002Fconcepts | ~20-100 cards | ~50-100KB | Searched on demand |\n\n**Context Strategy (Progressive Disclosure)**:\n- **At startup**: Run `wiki_daily_brief.py` → generate 6KB category summary → inject into context\n- **During tasks**: Specific question → `tdai_memory_search` \u002F `wiki_search` → read raw snippet (~700 chars)\n- **Forbidden**: Do not pour full wiki content into context (session limit: 200KB)\n\n---\n\n## 4. Naming Conventions\n\n### 4.1 INBOX\u002Farticles\u002F\n\n```\n【Category】YYYY-MM-DD-Title.md\nExample: 【Industry Research】2026-05-22-Some Industry Deep Dive Summary.md\n```\n\n**Category Tags**: 城市更新 \u002F 物业管理 \u002F 土地市场 \u002F 楼市分析 \u002F 城投转型 \u002F 政策速递 \u002F 行业研究 \u002F 他山之石\n\n### 4.2 wiki\u002Fqa\u002F\n\n```\nQ-Category-ContentSummary.md\nExample: Q-IndustryResearch-WhatAreKeyPointsOfCommercialPropertyLeaseManagement.md\n```\n\n### 4.3 wiki\u002Fconcepts\u002F\n\n```\nConcept-TopicName.md\nExample: Concept-CityRenewal.md\n```\n\n---\n\n## 5. Card Templates\n\n### 5.1 Q&A Card Template (frontmatter)\n\n```yaml\n---\ntype: qa\ndate: 2026-05-22\ntitle: Q-Category-ContentSummary\ntags: [Category]\nscenarios: [Report Writing\u002FArticle Writing\u002FPolicy Research]\nkeywords: [keyword1, keyword2]\noperation: knowledge-query\n---\n\n## Question\n(Specific question)\n\n## Answer\n(Complete answer, cite the source text, do not generalize)\n```\n\n### 5.2 Concept Card Template (frontmatter)\n\n```yaml\n---\ntype: concept\ndate: 2026-05-22\ntitle: Topic Name\ntags: [Category, Subcategory]\nsource: Source\nsummary: One-sentence core conclusion\n---\n\n# Concept: Topic Name\n\n## When to Use\nWhen encountering the following keywords\u002Fscenarios, prioritize this card:\n- Keyword 1\n- Keyword 2\n\n## Core Conclusion (One Sentence)\n\n## Detailed Content\n\n## Source\u002FEvidence\n```\n\n---\n\n## 6. Filter Rules (Mandatory)\n\n**Content PROHIBITED from writing to wiki\u002Fqa\u002F and wiki\u002Fconcepts\u002F**:\n\n| Category | Examples | Correct Destination |\n|----------|---------|-------------------|\n| Work logs \u002F daily matters | \"Today's completed work\", \"Core completion items\" | INBOX\u002F日志\u002F |\n| OpenClaw operations config | \"How to batch process documents\", \"cron config\" | skills\u002FSKILL.md |\n| Memory\u002Fsession mechanisms | \"OpenClaw memory scheme\", \"session structure\" | memory\u002F (non-wiki) |\n| Scheduled tasks\u002FCron | \"How to write cron tasks\" | skills\u002FSKILL.md |\n| Technical troubleshooting | \"API Key invalid troubleshooting\" | skills\u002FSKILL.md |\n\n**Content ALLOWED in wiki**:\n\nAny **structured knowledge** refined through analysis and processing, including but not limited to:\n- Industry\u002Fdomain knowledge (concepts, models, cases, data)\n- Policy interpretation and applicable scenarios\n- Core conclusions and methods from research reports\n- Standards and operational guidelines\n- Cross-domain comparative analysis\n\n**Rule of Thumb**: If a user can directly use it to write a report or make a decision, it's knowledge.\n\n---\n\n## 7. Daily Pipeline\n\n```\n05:00 ── INPUT END ──────────────────────────────\n│\n│  cron: Daily news scraping\n│  → Scrape news → write to INBOX\u002Farticles\u002F\n│  → Push Word summary to relevant people\n│\n│  Note: Do NOT write to wiki\u002F directly; 8:30 handles it\n│\n08:30 ── OUTPUT END (Knowledge Base Injection) ──\n│\n│  cron: Daily knowledge base injection\n│  → Scan INBOX\u002Farticles\u002F for today's new files\n│  → Write to wiki\u002Fqa\u002F (extract Q&A pairs)\n│  → Write to wiki\u002Fconcepts\u002F (extract concept cards)\n│  → Filter out operational content (see Section 6)\n│  → Run wiki_daily_brief.py to update daily summary\n│  → Push summary to owner (X new cards today, Z total in base)\n│\n│  At Session Startup (automatic):\n│  → Run wiki_daily_brief.py\n│  → Inject 6KB category summary into context\n│  → AI knows what's available in the knowledge base today\n```\n\n---\n\n## 8. Retrieval Flow (Per Task)\n\n```\nReceiving an analysis\u002Fwriting task\n  → wiki_daily_brief already injected at startup (6KB summary)\n  → wiki_search(topic keywords) → match Q&A cards\n  → High match → use the answer directly\n  → Low match → wiki_search(subtopic) → read concept card\n  → Still insufficient → search INBOX\u002Farticles\u002F raw materials\n  → Last resort → web_search\n```\n\n---\n\n## 9. wiki_daily_brief.py Script\n\n```python\n#!\u002Fusr\u002Fbin\u002Fenv python3\n\"\"\"\nwiki_daily_brief.py\nRun at first session startup each day. Generates a wiki knowledge base\ndaily summary so the model knows what's available in the knowledge base.\n\nOutput: ~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Fwiki_daily_brief.md\n\"\"\"\nWIKI_QA_DIR = \"\u002Fpath\u002Fto\u002FObsidian\u002Fwiki\u002Fqa\"\nOUT = \"~\u002F.openclaw\u002Fworkspace\u002Fmemory\u002Fwiki_daily_brief.md\"\n\n# Script logic:\n# 1. Scan all .md files in wiki\u002Fqa\u002F (excluding index.md)\n# 2. Extract frontmatter tags, count by category\n# 3. Take top 3 per category as examples, generate ~6KB summary\n# 4. Write to OUT, ready for session startup injection\n```\n\n---\n\n## 10. Daily Summary Format\n\n```markdown\n# Wiki Knowledge Base Daily Summary\n> Generated: 2026-05-22 | Total: 230 Q&A Cards\n\n---\n\n## Available Knowledge Cards (By Category)\n\n### Industry Research (83 cards)\n- **What is the core content of「Some Report」?** (Source: `Q-IndustryResearch-SomeReport.md`)\n- ...\n  - ...and 80 more\n\n### City Renewal (66 cards)\n- ...\n\n## Usage Guide\nTo query specific card content, call `tdai_memory_search` or `wiki_search`.\n```\n\n---\n\n## 11. Installation\n\n```bash\n# Method 1: ClawHub\nnpx clawhub@latest install obsidian-knowledge-base\n\n# Method 2: Manual\ncp -r obsidian-knowledge-base ~\u002F.openclaw\u002Fskills\u002F\n```\n\n---\n\n## 12. Use Cases\n\n- Knowledge workers who need AI to write reports, analysis, or official documents\n- Teams that want AI to have \"memory\" instead of starting from scratch every time\n- Scenarios with daily incremental material inputs (news, reports, data)\n- Teams that want knowledge base and AI context to work together, not in silos\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fo\u002Fobsidian-knowledge-base",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill obsidian-knowledge-base",{"tool":37,"command":38},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill obsidian-knowledge-base",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill obsidian-knowledge-base","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fo\u002Fobsidian-knowledge-base\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]