[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPBWVTKBATFNP7X2KNJ7S6":3,"skill-same:01M7EPBWVTKBATFNP7X2KNJ7S6":126},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M7EPBWVTKBATFNP7X2KNJ7S6","llm-wiki",null,"Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity\u002Fconcept pages, maintains cross-references, and keeps a synthesis current. Triggers include \"second brain\", \"Obsidian wiki\", \"personal knowledge management\", \"ingest this paper\u002Farticle\u002Fbook\", \"build a research wiki\", \"compound knowledge\", \"Memex\", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: llm-wiki\ndescription: Use when building or maintaining a persistent personal knowledge base\n  (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity\u002Fconcept\n  pages, maintains cross-references, and keeps a synthesis current. Triggers include\n  \"second brain\", \"Obsidian wiki\", \"personal knowledge management\", \"ingest this paper\u002Farticle\u002Fbook\",\n  \"build a research wiki\", \"compound knowledge\", \"Memex\", or whenever the user wants\n  knowledge to accumulate across sessions instead of being re-derived by RAG on every\n  query.\ncontext: fork\nversion: 2.9.0\nauthor: claude-code-skills\nlicense: MIT\ntags:\n- knowledge-management\n- obsidian\n- second-brain\n- pkm\n- rag-alternative\n- wiki\n- karpathy\n- memex\n---\n\n# LLM Wiki — Second Brain for Claude Code + Obsidian\n\nInspired by Andrej Karpathy's LLM Wiki pattern ([gist](https:\u002F\u002Fgist.github.com\u002Fkarpathy\u002F442a6bf555914893e9891c11519de94f)). This skill turns Claude Code (or any agent CLI) into a disciplined wiki maintainer that **incrementally builds and maintains** a persistent, interlinked Obsidian vault as you feed it sources. The knowledge compounds — cross-references, contradictions, and synthesis are already there when you query.\n\n## Core principle\n\nMost LLM+docs workflows are **RAG**: retrieve fragments at query time, synthesize from scratch, forget. The wiki is **compounding**: sources are read once, integrated into a persistent markdown knowledge base, and kept current. You curate and ask; the LLM reads, files, cross-references, and maintains.\n\n> Obsidian is the IDE. The LLM is the programmer. The wiki is the codebase.\n\n## When to use\n\n- **Personal**: track goals, health, psychology, journaling, self-improvement\n- **Research**: deep dives over weeks on a topic — papers, articles, reports, evolving thesis\n- **Book companion**: file chapters as you read; build a fan-wiki-style companion for characters, themes, plot threads\n- **Business\u002Fteam**: internal wiki fed by Slack, meeting notes, calls — LLM does maintenance nobody else wants to do\n- **Competitive analysis, due diligence, trip planning, course notes, hobby deep-dives**\n\n**Do NOT use when:** you need one-shot Q&A over a fixed document (use RAG), you don't plan to add sources over time, or you don't want Obsidian in the loop.\n\n## Architecture (three layers)\n\n```\nvault\u002F\n├── raw\u002F                    # Layer 1 — IMMUTABLE source of truth\n│   ├── \u003Csource files>      # Articles, papers, PDFs, images, data\n│   └── assets\u002F             # Downloaded images from clipped articles\n├── wiki\u002F                   # Layer 2 — LLM-owned knowledge base\n│   ├── index.md            # Content catalog (LLM updates every ingest)\n│   ├── log.md              # Append-only timeline (## [YYYY-MM-DD] \u003Cop> | \u003Ctitle>)\n│   ├── entities\u002F           # Person\u002FOrg\u002FPlace pages\n│   ├── concepts\u002F           # Ideas, theories, frameworks\n│   ├── sources\u002F            # One summary page per ingested source\n│   ├── comparisons\u002F        # Cross-source analysis pages\n│   └── synthesis\u002F          # High-level syntheses, theses, overviews\n├── CLAUDE.md               # Schema + conventions (Claude Code)\n└── AGENTS.md               # Same content, for Codex\u002FCursor\u002FAntigravity\n```\n\n- **Layer 1 (raw\u002F)** — you own. LLM only reads; never writes.\n- **Layer 2 (wiki\u002F)** — LLM owns. It creates, updates, and cross-references pages. You read it.\n- **Layer 3 (CLAUDE.md \u002F AGENTS.md)** — the *schema*. Conventions, workflows, frontmatter rules. Co-evolved by you and the LLM.\n\n## Three core operations\n\n1. **Ingest** — LLM reads a source, discusses takeaways with you, writes a source summary, updates 10-15 relevant pages, updates index, appends to log. See `references\u002Fingest-workflow.md`.\n2. **Query** — LLM reads `index.md` first, drills into relevant pages, synthesizes with citations. Good answers get **filed back into the wiki** so explorations compound. See `references\u002Fquery-workflow.md`.\n3. **Lint** — Health check: contradictions, stale claims, orphan pages, missing cross-refs, concepts mentioned but lacking their own page, data gaps to fill with web search. See `references\u002Flint-workflow.md`.\n\n## Quick start\n\n```bash\n# 1. Initialize a vault (in Obsidian's vault directory)\npython scripts\u002Finit_vault.py --path ~\u002Fvaults\u002Fresearch --topic \"LLM interpretability\"\n\n# 2. Drop a source into raw\u002F, then ingest\n\u002Fwiki-ingest ~\u002Fvaults\u002Fresearch\u002Fraw\u002Fanthropic-monosemanticity.pdf\n\n# 3. Ask questions (answers can be re-filed into the wiki)\n\u002Fwiki-query \"how does monosemanticity compare to mechanistic interpretability?\"\n\n# 4. Periodic health check\n\u002Fwiki-lint\n\n# 5. See the timeline\n\u002Fwiki-log --last 10\n```\n\n## Slash commands (this plugin ships)\n\n| Command | Purpose |\n|---|---|\n| `\u002Fwiki-init` | Bootstrap a fresh vault with schema files + starter structure |\n| `\u002Fwiki-ingest \u003Cpath>` | Read a source, discuss, update wiki, log it |\n| `\u002Fwiki-query \u003Cquestion>` | Search wiki, synthesize answer, offer to file back |\n| `\u002Fwiki-lint` | Run health check — contradictions, orphans, stale claims, gaps |\n| `\u002Fwiki-log` | Show recent log entries (uses unix tools on `log.md`) |\n\n## Sub-agents (this plugin ships)\n\n| Agent | When dispatched |\n|---|---|\n| `wiki-ingestor` | Delegated ingest flow — reads source, proposes updates, applies after your approval |\n| `wiki-linter` | Runs the health-check workflow independently, reports findings |\n| `wiki-librarian` | Answers queries using index-first search, synthesizes with citations |\n\n## Python tools (`scripts\u002F`)\n\nAll tools are **standard library only** (no pip installs). Run with `python scripts\u002F\u003Ctool>.py --help`.\n\n| Script | Purpose |\n|---|---|\n| `init_vault.py` | Create folder structure + seed CLAUDE.md, AGENTS.md, index.md, log.md |\n| `ingest_source.py` | Helper: extract text\u002Ffrontmatter from a source file, ready for LLM review |\n| `update_index.py` | Regenerate `index.md` from wiki page frontmatter (category, date, source count) |\n| `append_log.py` | Append a standardized log entry `## [YYYY-MM-DD] \u003Cop> \\| \u003Ctitle>` |\n| `wiki_search.py` | BM25 search over wiki pages (standalone fallback when index.md isn't enough) |\n| `lint_wiki.py` | Find orphans (no inbound links), stale pages, missing cross-refs, broken links |\n| `graph_analyzer.py` | Compute link graph stats — hubs, orphans, clusters, disconnected components |\n| `export_marp.py` | Render a wiki page (or subtree) to a Marp slide deck |\n\n## Cross-tool compatibility\n\nThe vault's **schema** lives in CLAUDE.md (Claude Code) or AGENTS.md (Codex\u002FCursor\u002FAntigravity\u002FOpenCode). The same content works in both. This plugin ships both templates. For per-tool setup instructions see `references\u002Fcross-tool-setup.md`.\n\n```\nCLAUDE.md       → Claude Code\nAGENTS.md       → Codex CLI, Cursor, Antigravity, OpenCode, Gemini CLI\n.cursorrules    → legacy Cursor (pre-AGENTS.md)\n```\n\nThe scripts are pure Python stdlib → run identically everywhere. Only the loader file changes per tool.\n\n## Obsidian setup (recommended)\n\n- **Obsidian Web Clipper** — browser extension; converts web articles to markdown and drops them in `raw\u002F`\n- **Download images locally** — Settings → Files and links → Attachment folder path = `raw\u002Fassets\u002F`. Settings → Hotkeys → bind \"Download attachments for current file\" to `Ctrl+Shift+D`\n- **Graph view** — see hubs\u002Forphans; essential for spotting structural problems\n- **Marp plugin** — Markdown-based slide decks directly from wiki pages\n- **Dataview plugin** — dynamic tables\u002Flists over page frontmatter (tags, dates, source counts)\n- **Git** — the vault is a plain markdown repo; version it\n\nFull setup walkthrough: `references\u002Fobsidian-setup.md`\n\n## Why this works (vs plain RAG)\n\n| Plain RAG | LLM Wiki |\n|---|---|\n| Rediscover knowledge each query | Knowledge accumulates |\n| Cross-references re-computed every time | Cross-references pre-written and maintained |\n| Contradictions surface only if you ask | Contradictions flagged during ingest |\n| Exploration disappears into chat history | Good answers re-filed as new pages |\n| Scales by embeddings infrastructure | Scales by markdown + `index.md` + optional local search |\n\nAt ~100 sources \u002F hundreds of pages, `index.md` + filesystem search is enough. Past that, layer in a local search tool like [qmd](https:\u002F\u002Fgithub.com\u002Ftobi\u002Fqmd) or use `scripts\u002Fwiki_search.py`.\n\n## Related skills (chains via `context: fork`)\n\nThis skill is marked `context: fork` so other skills can chain into it:\n\n- **`para-memory-files`** — PARA-method memory; complementary as long-term personal memory that feeds sources into the wiki\n- **`obsidian-vault`** (mattpocock) — lightweight Obsidian note helper; this skill is the maintained-wiki layer on top\n- **`rag-design`** — when wiki outgrows ~500 pages, use rag-design to bolt on a retrieval layer\n- **`mcp-design`** — expose the wiki as an MCP tool\n- **`agent-communication`** — for multi-agent wiki maintenance (ingestor + linter + librarian)\n\n## Reference docs\n\n- `references\u002Fwiki-schema.md` — full vault layout, page frontmatter, naming conventions\n- `references\u002Fpage-formats.md` — entity, concept, source, comparison, synthesis templates\n- `references\u002Fingest-workflow.md` — the detailed ingest flow the wiki-ingestor agent follows\n- `references\u002Fquery-workflow.md` — query patterns, citation format, re-filing answers\n- `references\u002Flint-workflow.md` — health-check heuristics\n- `references\u002Fobsidian-setup.md` — Obsidian plugins, hotkeys, vault config\n- `references\u002Fcross-tool-setup.md` — per-tool setup (Codex, Cursor, Antigravity, etc.)\n- `references\u002Fmemex-principles.md` — Bush's Memex, why the LLM changes the maintenance math\n\n## Templates (`assets\u002F`)\n\n- `CLAUDE.md.template`, `AGENTS.md.template`, `.cursorrules.template` — schema loaders per tool\n- `index.md.template`, `log.md.template` — starter index and log\n- `page-templates\u002F` — entity, concept, source-summary, comparison, synthesis\n- `example-vault\u002F` — small worked example you can study or copy\n\n## Iron rule\n\n**The LLM never edits files in `raw\u002F`.** Ever. Sources are immutable. All LLM writes go to `wiki\u002F`. If you need to correct a source, do it in `raw\u002F` yourself — then re-ingest.\n","# LLM Wiki — Second Brain for Claude Code + Obsidian\n\nInspired by Andrej Karpathy's LLM Wiki pattern ([gist](https:\u002F\u002Fgist.github.com\u002Fkarpathy\u002F442a6bf555914893e9891c11519de94f)). This skill turns Claude Code (or any agent CLI) into a disciplined wiki maintainer that **incrementally builds and maintains** a persistent, interlinked Obsidian vault as you feed it sources. The knowledge compounds — cross-references, contradictions, and synthesis are already there when you query.\n\n## Core principle\n\nMost LLM+docs workflows are **RAG**: retrieve fragments at query time, synthesize from scratch, forget. The wiki is **compounding**: sources are read once, integrated into a persistent markdown knowledge base, and kept current. You curate and ask; the LLM reads, files, cross-references, and maintains.\n\n> Obsidian is the IDE. The LLM is the programmer. The wiki is the codebase.\n\n## When to use\n\n- **Personal**: track goals, health, psychology, journaling, self-improvement\n- **Research**: deep dives over weeks on a topic — papers, articles, reports, evolving thesis\n- **Book companion**: file chapters as you read; build a fan-wiki-style companion for characters, themes, plot threads\n- **Business\u002Fteam**: internal wiki fed by Slack, meeting notes, calls — LLM does maintenance nobody else wants to do\n- **Competitive analysis, due diligence, trip planning, course notes, hobby deep-dives**\n\n**Do NOT use when:** you need one-shot Q&A over a fixed document (use RAG), you don't plan to add sources over time, or you don't want Obsidian in the loop.\n\n## Architecture (three layers)\n\n```\nvault\u002F\n├── raw\u002F                    # Layer 1 — IMMUTABLE source of truth\n│   ├── \u003Csource files>      # Articles, papers, PDFs, images, data\n│   └── assets\u002F             # Downloaded images from clipped articles\n├── wiki\u002F                   # Layer 2 — LLM-owned knowledge base\n│   ├── index.md            # Content catalog (LLM updates every ingest)\n│   ├── log.md              # Append-only timeline (## [YYYY-MM-DD] \u003Cop> | \u003Ctitle>)\n│   ├── entities\u002F           # Person\u002FOrg\u002FPlace pages\n│   ├── concepts\u002F           # Ideas, theories, frameworks\n│   ├── sources\u002F            # One summary page per ingested source\n│   ├── comparisons\u002F        # Cross-source analysis pages\n│   └── synthesis\u002F          # High-level syntheses, theses, overviews\n├── CLAUDE.md               # Schema + conventions (Claude Code)\n└── AGENTS.md               # Same content, for Codex\u002FCursor\u002FAntigravity\n```\n\n- **Layer 1 (raw\u002F)** — you own. LLM only reads; never writes.\n- **Layer 2 (wiki\u002F)** — LLM owns. It creates, updates, and cross-references pages. You read it.\n- **Layer 3 (CLAUDE.md \u002F AGENTS.md)** — the *schema*. Conventions, workflows, frontmatter rules. Co-evolved by you and the LLM.\n\n## Three core operations\n\n1. **Ingest** — LLM reads a source, discusses takeaways with you, writes a source summary, updates 10-15 relevant pages, updates index, appends to log. See `references\u002Fingest-workflow.md`.\n2. **Query** — LLM reads `index.md` first, drills into relevant pages, synthesizes with citations. Good answers get **filed back into the wiki** so explorations compound. See `references\u002Fquery-workflow.md`.\n3. **Lint** — Health check: contradictions, stale claims, orphan pages, missing cross-refs, concepts mentioned but lacking their own page, data gaps to fill with web search. See `references\u002Flint-workflow.md`.\n\n## Quick start\n\n```bash\n# 1. Initialize a vault (in Obsidian's vault directory)\npython scripts\u002Finit_vault.py --path ~\u002Fvaults\u002Fresearch --topic \"LLM interpretability\"\n\n# 2. Drop a source into raw\u002F, then ingest\n\u002Fwiki-ingest ~\u002Fvaults\u002Fresearch\u002Fraw\u002Fanthropic-monosemanticity.pdf\n\n# 3. Ask questions (answers can be re-filed into the wiki)\n\u002Fwiki-query \"how does monosemanticity compare to mechanistic interpretability?\"\n\n# 4. Periodic health check\n\u002Fwiki-lint\n\n# 5. See the timeline\n\u002Fwiki-log --last 10\n```\n\n## Slash commands (this plugin ships)\n\n| Command | Purpose |\n|---|---|\n| `\u002Fwiki-init` | Bootstrap a fresh vault with schema files + starter structure |\n| `\u002Fwiki-ingest \u003Cpath>` | Read a source, discuss, update wiki, log it |\n| `\u002Fwiki-query \u003Cquestion>` | Search wiki, synthesize answer, offer to file back |\n| `\u002Fwiki-lint` | Run health check — contradictions, orphans, stale claims, gaps |\n| `\u002Fwiki-log` | Show recent log entries (uses unix tools on `log.md`) |\n\n## Sub-agents (this plugin ships)\n\n| Agent | When dispatched |\n|---|---|\n| `wiki-ingestor` | Delegated ingest flow — reads source, proposes updates, applies after your approval |\n| `wiki-linter` | Runs the health-check workflow independently, reports findings |\n| `wiki-librarian` | Answers queries using index-first search, synthesizes with citations |\n\n## Python tools (`scripts\u002F`)\n\nAll tools are **standard library only** (no pip installs). Run with `python scripts\u002F\u003Ctool>.py --help`.\n\n| Script | Purpose |\n|---|---|\n| `init_vault.py` | Create folder structure + seed CLAUDE.md, AGENTS.md, index.md, log.md |\n| `ingest_source.py` | Helper: extract text\u002Ffrontmatter from a source file, ready for LLM review |\n| `update_index.py` | Regenerate `index.md` from wiki page frontmatter (category, date, source count) |\n| `append_log.py` | Append a standardized log entry `## [YYYY-MM-DD] \u003Cop> \\| \u003Ctitle>` |\n| `wiki_search.py` | BM25 search over wiki pages (standalone fallback when index.md isn't enough) |\n| `lint_wiki.py` | Find orphans (no inbound links), stale pages, missing cross-refs, broken links |\n| `graph_analyzer.py` | Compute link graph stats — hubs, orphans, clusters, disconnected components |\n| `export_marp.py` | Render a wiki page (or subtree) to a Marp slide deck |\n\n## Cross-tool compatibility\n\nThe vault's **schema** lives in CLAUDE.md (Claude Code) or AGENTS.md (Codex\u002FCursor\u002FAntigravity\u002FOpenCode). The same content works in both. This plugin ships both templates. For per-tool setup instructions see `references\u002Fcross-tool-setup.md`.\n\n```\nCLAUDE.md       → Claude Code\nAGENTS.md       → Codex CLI, Cursor, Antigravity, OpenCode, Gemini CLI\n.cursorrules    → legacy Cursor (pre-AGENTS.md)\n```\n\nThe scripts are pure Python stdlib → run identically everywhere. Only the loader file changes per tool.\n\n## Obsidian setup (recommended)\n\n- **Obsidian Web Clipper** — browser extension; converts web articles to markdown and drops them in `raw\u002F`\n- **Download images locally** — Settings → Files and links → Attachment folder path = `raw\u002Fassets\u002F`. Settings → Hotkeys → bind \"Download attachments for current file\" to `Ctrl+Shift+D`\n- **Graph view** — see hubs\u002Forphans; essential for spotting structural problems\n- **Marp plugin** — Markdown-based slide decks directly from wiki pages\n- **Dataview plugin** — dynamic tables\u002Flists over page frontmatter (tags, dates, source counts)\n- **Git** — the vault is a plain markdown repo; version it\n\nFull setup walkthrough: `references\u002Fobsidian-setup.md`\n\n## Why this works (vs plain RAG)\n\n| Plain RAG | LLM Wiki |\n|---|---|\n| Rediscover knowledge each query | Knowledge accumulates |\n| Cross-references re-computed every time | Cross-references pre-written and maintained |\n| Contradictions surface only if you ask | Contradictions flagged during ingest |\n| Exploration disappears into chat history | Good answers re-filed as new pages |\n| Scales by embeddings infrastructure | Scales by markdown + `index.md` + optional local search |\n\nAt ~100 sources \u002F hundreds of pages, `index.md` + filesystem search is enough. Past that, layer in a local search tool like [qmd](https:\u002F\u002Fgithub.com\u002Ftobi\u002Fqmd) or use `scripts\u002Fwiki_search.py`.\n\n## Related skills (chains via `context: fork`)\n\nThis skill is marked `context: fork` so other skills can chain into it:\n\n- **`para-memory-files`** — PARA-method memory; complementary as long-term personal memory that feeds sources into the wiki\n- **`obsidian-vault`** (mattpocock) — lightweight Obsidian note helper; this skill is the maintained-wiki layer on top\n- **`rag-design`** — when wiki outgrows ~500 pages, use rag-design to bolt on a retrieval layer\n- **`mcp-design`** — expose the wiki as an MCP tool\n- **`agent-communication`** — for multi-agent wiki maintenance (ingestor + linter + librarian)\n\n## Reference docs\n\n- `references\u002Fwiki-schema.md` — full vault layout, page frontmatter, naming conventions\n- `references\u002Fpage-formats.md` — entity, concept, source, comparison, synthesis templates\n- `references\u002Fingest-workflow.md` — the detailed ingest flow the wiki-ingestor agent follows\n- `references\u002Fquery-workflow.md` — query patterns, citation format, re-filing answers\n- `references\u002Flint-workflow.md` — health-check heuristics\n- `references\u002Fobsidian-setup.md` — Obsidian plugins, hotkeys, vault config\n- `references\u002Fcross-tool-setup.md` — per-tool setup (Codex, Cursor, Antigravity, etc.)\n- `references\u002Fmemex-principles.md` — Bush's Memex, why the LLM changes the maintenance math\n\n## Templates (`assets\u002F`)\n\n- `CLAUDE.md.template`, `AGENTS.md.template`, `.cursorrules.template` — schema loaders per tool\n- `index.md.template`, `log.md.template` — starter index and log\n- `page-templates\u002F` — entity, concept, source-summary, comparison, synthesis\n- `example-vault\u002F` — small worked example you can study or copy\n\n## Iron rule\n\n**The LLM never edits files in `raw\u002F`.** Ever. Sources are immutable. All LLM writes go to `wiki\u002F`. If you need to correct a source, do it in `raw\u002F` yourself — then re-ingest.\n",{"name":5,"tags":24,"author":33,"context":34,"license":15,"version":35,"description":7},[25,26,27,28,29,30,31,32],"knowledge-management","obsidian","second-brain","pkm","rag-alternative","wiki","karpathy","memex","claude-code-skills","fork","2.9.0","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-imp-llm-wiki",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill llm-wiki",{"tool":50,"command":51},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill llm-wiki",{"tool":53,"command":54},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill llm-wiki","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002FSKILL.md",true,[58,64,68,72,76,80,84,88,92,98,102,106,110,114,118,122],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fcross-tool-setup.md","REFERENCE","参考文档",3644,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fcross-tool-setup.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fingest-workflow.md",3926,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fingest-workflow.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Flint-workflow.md",3613,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Flint-workflow.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fmemex-principles.md",4097,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fmemex-principles.md",{"path":77,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fobsidian-setup.md",2991,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fobsidian-setup.md",{"path":81,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fpage-formats.md",5172,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fpage-formats.md",{"path":85,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fquery-workflow.md",3129,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fquery-workflow.md",{"path":89,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fwiki-schema.md",4528,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Freferences\u002Fwiki-schema.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fappend_log.py","SCRIPT","脚本",4291,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fappend_log.py",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fexport_marp.py",4561,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fexport_marp.py",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fgraph_analyzer.py",4814,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fgraph_analyzer.py",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fingest_source.py",5709,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fingest_source.py",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Finit_vault.py",7182,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Finit_vault.py",{"path":115,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Flint_wiki.py",6765,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Flint_wiki.py",{"path":119,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fupdate_index.py",6580,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fupdate_index.py",{"path":123,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fwiki_search.py",4771,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-llm-wiki\u002Fscripts\u002Fwiki_search.py",[127,134,142,149,156,163],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":138,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]