[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ED3QHW6HNAKB8EC9YWHVSS":3,"skill-same:01M7ED3QHW6HNAKB8EC9YWHVSS":49},{"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":13,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":27,"updatedAt":28,"install":29,"resources":42},"01M7ED3QHW6HNAKB8EC9YWHVSS","capture",null,"jonahthan433\u002FCortexOS","jonahthan433","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211465495?v=4","01M7ECH9HPHGA89DCXHHJBTS3C","jonah.ai","01M7ECH9JCEM45DZMWPT7148S1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fcapture\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# capture\n\n# Capture — Brain-Dump Organizer\n\nA fast-to-action skill for transforming unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.\n\n## Invocation Triggers\n\n**Explicit phrases** (any of):\n- \"brain dump\"\n- \"capture this\"\n- \"let me dump some ideas\"\n- \"I've got a bunch of thoughts\"\n- \"here's everything on my mind\"\n- \"idea dump\"\n- \"let me just get this out of my head\"\n- \"I need to organize my thoughts\"\n- \"here's what I'm thinking\"\n\n**Implicit signals** (no phrase, but the intent is unmistakable):\n- User pastes or dictates a long unstructured block of mixed ideas, tasks, plans\n- Multiple unrelated thoughts in one message without organizing framing\n- A wall of bullet-y text covering 3+ unrelated topics\n\nWhen you detect an implicit trigger, run the skill. Do NOT ask \"do you want me to organize this?\" first — the dump itself IS the request.\n\n## Operating Principles (All Five Apply Always)\n\n1. **Capture everything.** Zero loss. Trivial items go in; the user prunes later. Never silently drop something because it \"seemed unimportant\".\n2. **Preserve voice.** If the user said \"build something crazy with AI\", do NOT restate as \"Explore innovative AI-driven solutions.\" Keep the energy and the casual register. See `references\u002Fvoice_preservation.md` for concrete anti-patterns.\n3. **Match output complexity to input.** A 5-task dump does NOT get forced into 4 elaborate sections. See `references\u002Fcomplexity_matching.md` and the Compressed Output Pattern below.\n4. **Be honest about ambiguity.** If you're unsure what something means, flag it. Don't guess silently.\n5. **No action without approval.** The ONLY immediate action is the organization itself. Every offer in Section 4 waits for the user's explicit pick.\n\n## Grill-Me Mid-Organization Clarifier\n\nCapture is fast-to-action by design. **No upfront intake.** The dump is enough — start organizing immediately.\n\nThe grill-me discipline applies as a **single mid-organization clarifying question**, asked **only when** one item in the dump is genuinely ambiguous between *task* and *project*, AND the misclassification would meaningfully change the output:\n\n> **Quick clarification — one item in your dump could go either way. Is [X] a one-shot task or a multi-step project?**\n>\n> *Why I'm asking:* If I guess wrong on a borderline item I either bury a project as a task or inflate a task into a project that doesn't need the structure. One question per dump prevents that.\n\n**Stop condition:** Max 1 clarifying question per dump. After the answer (or if no clarification was needed), deliver the four (or compressed) sections.\n\nIf the dump is unambiguous, skip the clarifier entirely.\n\n**Anti-pattern (do not do this):** asking 3 clarifying questions up front. That breaks the dump-and-organize flow that makes capture useful.\n\n## Section 1: Projects & Ideas\n\nCluster related items into themed projects when natural clustering exists. This section also holds:\n- Standalone creative sparks\n- Half-formed concepts\n- \"What if\" thoughts\n- Embedded decisions (`Decide: X or Y`) and open questions (`Q: ...`) — kept WITHIN the relevant project, NOT extracted into a separate top-level category\n\n**Format per project:**\n\n```\n### {Project name in user's voice}\n\n- {component \u002F sub-idea}\n- {component}\n- Q: {open question this project needs answered}\n- Decide: {decision this project requires}\n```\n\nUse the user's words for the project name. If the user wrote \"ai dating app for ferrets\", do NOT rename it to \"AI-Powered Pet Companion Platform\".\n\n## Section 2: Tasks\n\nFlat, scannable, action-oriented. Includes:\n- Explicit todos\n- Decisions framed as `Decide: ...`\n- Open questions framed as `Resolve: ...`\n\nIf a task belongs to a project from Section 1, append `[Project: X]` to link it — but don't repeat the project's context.\n\n**Format:**\n\n```\n- {task in imperative voice}  [Project: X if related]\n- Decide: {decision}  [Project: X if related]\n- Resolve: {open question}\n- ...\n```\n\n## Section 3: Connections\n\nThis is where the skill earns its keep — and where **fabrication is forbidden**.\n\n**Workflow:**\n\n1. **Inventory the workspace** — Glob for filename patterns matching dump keywords, Grep for content matches, read the top-level directory structure. Use `scripts\u002Fworkspace_inventory.py` to do this deterministically.\n2. **Match dump items to existing content** — files \u002F folders relating to dumped items, prior thinking in documents, in-progress projects with overlap.\n3. **Surface dependencies within the dump** — items that affect each other, themes, ordering implications.\n4. **Be honest about inaccessibility** — if you can't inspect the workspace (no filesystem available, MCP not connected), say so explicitly. Do NOT make up plausible-sounding connections.\n\n**Hard rule:** NEVER fabricate connections. Only surface ones actually found by Glob\u002FGrep\u002FRead. If no real connections exist:\n\n> **Connections:** No connections found — workspace inventory clean.\n\nIf the workspace is inaccessible:\n\n> **Connections:** No workspace accessible from here. If you're running this from Claude Code or have a project with files attached, I can fill this in. Want to share where this work lives?\n\nSee `references\u002Fworkspace_detection.md` for the per-context detection-tactic catalog.\n\n## Section 4: How I Can Help\n\n**Concrete offers, not abstract possibilities.** Every offer specifies what would be produced AND where it would go.\n\n| ✅ Right pattern | ❌ Anti-pattern |\n|---|---|\n| \"I can research Consensus MCP integration patterns and give you 3 options. Output: `docs\u002Fconsensus-options.md`.\" | \"You might want to look into integration approaches.\" |\n| \"I can draft the Q3 launch plan as a 1-pager. Output: chat reply, then `docs\u002Fq3-launch.md` if you want it filed.\" | \"Maybe think about Q3 planning.\" |\n| \"I can scaffold the new auth module with the existing pattern from `src\u002Fusers\u002F`. Output: 4 files in `src\u002Fauth\u002F`.\" | \"We could explore auth options.\" |\n\nEnd with the directive question:\n\n> **Which of these should I tackle?**\n\n## Compressed Output Pattern\n\nWhen the dump has **5 or fewer items** and items are **unrelated** (no natural clustering), drop the 4-section format and use compressed:\n\n```\n## What I heard\n\n- {item}\n- {item}\n- {item}\n- ...\n\n## How I can help\n\n- {concrete offer with what + where}\n- {concrete offer with what + where}\n\nWhich should I tackle?\n```\n\nThe trigger is the `complexity_estimator.py` recommendation OR your judgment when no clusters exist. See `references\u002Fcomplexity_matching.md` for worked examples of when each format applies.\n\n## Workspace Detection Strategy\n\n| Context | Detection method |\n|---|---|\n| Claude Code CLI | Glob for files matching dump keywords; Grep for content matches; read top-level structure. Use `scripts\u002Fworkspace_inventory.py`. |\n| Claude.ai with project | Check project knowledge files for thematic overlap. List file titles; surface matches by keyword. |\n| Connected tools (Notion, Drive, etc.) | Search via MCP if available. See **Notion MCP** section below. |\n| No accessible workspace | State the limitation explicitly; ask user about their setup; do NOT fabricate. |\n\n## Notion MCP (Optional)\n\nThis skill integrates with the Notion MCP connector when available. After delivering the organized sections to chat, attempt `notion-query-data-sources`. If it returns results, Notion is connected — run the save flow below. If it fails or is unavailable, skip silently and append the alert.\n\n### Save Flow (If Notion Connected)\n\nRun this **after** the 4-section (or compressed) output is delivered and the user has not yet picked a Section 4 offer — it is a parallel background action, not a gate.\n\n1. Call `notion-search` with keywords from the top Projects and Tasks to detect existing matching pages in the workspace\n2. For each **Project\u002FIdea** in Section 1: check if a matching project page already exists\n   - If yes: surface the match to the user (\"Found existing page: [title] — want me to link or update it?\") — do NOT auto-update without approval\n   - If no: offer to create it with `notion-create-pages` in a Projects database\n3. For each **Task** in Section 2: call `notion-query-database-view` to check if a tasks database exists\n   - If yes: offer to add the tasks to that database via `notion-create-pages`\n   - If no: offer to create a Tasks database via `notion-create-database` and add them\n4. All Notion actions are **offers, not auto-executions** — present a single grouped offer at the end of Section 4:\n\n> **Save to Notion?** I found [N] projects and [N] tasks from your dump. I can add them to your Notion workspace — [X] matching existing pages, [Y] new entries. Say \"save to Notion\" to proceed, or pick a Section 4 offer instead.\n\n5. On approval: execute `notion-create-pages` for approved items, confirm with page links\n\n### Fallback (If Notion Not Connected)\n\n> 💡 **Notion not connected** — your organized brain dump is output to chat only. Connect the Notion MCP connector to automatically save projects and tasks to your workspace. Setup: [notion-mcp-server](https:\u002F\u002Fgithub.com\u002Fmakenotion\u002Fnotion-mcp-server)\n\n## Approval Gate\n\nAfter the four (or compressed) sections are delivered:\n\n- **Wait for the user's explicit pick** before doing anything else.\n- If the user says \"go\" without picking a specific offer: honor it, but explicitly note any items you weren't 100% sure about so they can correct.\n- The organization itself is the only auto-action. Every Section 4 offer requires green light.\n\n## Error Handling\n\n| Situation | Behavior |\n|---|---|\n| Workspace inaccessible | State this; skip Section 3 or surface \"no workspace accessible\" + ask about setup |\n| Dump is very short (3-5 items) | Use compressed output; don't force 4 sections |\n| Items are highly ambiguous | Flag in output, ask up to 1 clarifier (or skip clarifier and surface ambiguity in delivery) |\n| Dump contains sensitive info | Acknowledge but don't echo verbatim if user asks for organization without quoting |\n| Conflicting items in the dump | Surface the conflict in Section 1 or 3 explicitly (`Conflict: X says A, Y says B`) |\n| User says \"go\" before approval | Honor it, but explicitly note items you weren't sure about |\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fworkspace_inventory.py` | Glob+Grep helper for Section 3. `python workspace_inventory.py --root . --keywords \"k1,k2\"` returns matches by keyword + folder structure. |\n| `scripts\u002Fdump_classifier.py` | Regex-classifies each dump line into `task` \u002F `decision` \u002F `question` \u002F `idea` \u002F `project-component`. Heuristic — override with judgment. |\n| `scripts\u002Fcomplexity_estimator.py` | Counts items, detects clustering signal, recommends `format=full` or `format=compressed`. |\n\n## References\n\n- `references\u002Fworkspace_detection.md` — context-specific detection tactics (CLI \u002F web \u002F MCP \u002F inaccessible)\n- `references\u002Fvoice_preservation.md` — corporate-speak anti-patterns with concrete examples\n- `references\u002Fcomplexity_matching.md` — compressed vs full output, worked examples\n\n## Anti-Patterns To Reject\n\n- Fabricating workspace connections that weren't actually Glob\u002FGrep-verified\n- Dropping items deemed \"trivial\" — capture everything, let the user prune\n- Corporate-ifying the user's casual language\n- Forcing 4-section structure when input is small (5 simple tasks doesn't need it)\n- Acting on Section-4 offers immediately without approval\n- Splitting decisions\u002Fquestions into a separate top-level category instead of embedding them in the relevant project\n- Vague Section-4 offers (\"you might want to consider…\")\n- Asking 3+ clarifying questions up front (breaks fast-to-action)\n",{},"main","38b32c99e7ed0b8e215d638e92cfa452c1ec3079","skills\u002Fimported\u002Fproductivity\u002Fcapture","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS","https:\u002F\u002Fgithub.com\u002Fjonahthan433","AI Consultant","2026-10-24 05:13:39",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add jonahthan433\u002FCortexOS --skill capture",{"tool":35,"command":36},"bunx","bunx skills add jonahthan433\u002FCortexOS --skill capture",{"tool":38,"command":39},"pnpm","pnpm dlx skills add jonahthan433\u002FCortexOS --skill capture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fcapture\u002FSKILL.md",true,[43],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"skill.json","REFERENCE","参考文档",566,"https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fcapture\u002Fskill.json",[50,56,62,68,74,80],{"skillNo":51,"name":52,"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":53,"categories":54,"keywords":55,"publishedAt":18},"01M7EDQZDQX3Q8Y7GCQX6KN9V7","opportunity-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fsales\u002Fopportunity-brief\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"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":59,"categories":60,"keywords":61,"publishedAt":18},"01M7EDQYA0V9Y99VKBREJJ3MRT","morning-intel","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fmorning-intel\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"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":65,"categories":66,"keywords":67,"publishedAt":18},"01M7EDQVX1JVY0B6PDHKKGM19G","decision-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fdecision-brief\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"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":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EDQV1GENZAC2SZSD8KZ3GM","weekly-review","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"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":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EDQT2KETJ1Y3CGVN9EKW2J","system-health","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fsystem-health\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"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":83,"categories":84,"keywords":85,"publishedAt":18},"01M7EDQQN2JK3XPWMS1M4T0F3K","backup-restore","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fbackup-restore\u002FSKILL.md",[],[]]