{"skill":{"slug":"zettelclaw","displayName":"Zettelclaw","summary":"Work inside a Zettelclaw vault using the current typed frontmatter schema, inbox + Base workflows, and human-write/agent-read guardrails. Use when creating,...","description":"---\nname: zettelclaw\ndescription: \"Work inside a Zettelclaw vault using the current typed frontmatter schema, inbox + Base workflows, and human-write/agent-read guardrails. Use when creating, updating, organizing, or searching notes in a Zettelclaw vault, including inbox processing, /ask callouts, and journal scaffolding.\"\n---\n\n# Zettelclaw\n\nFollow the canonical Zettelclaw vault model: capture externally, write durable notes manually, and use the agent for navigation/synthesis.\n\nThis is an instruction-only skill. It does not install software by itself. `qmd` is optional when it is already available in the environment, and `rg` is the supported fallback for search.\n\n## Vault structure\n\n```\n<vault>/\n├── 00 Inbox/\n├── 01 Notes/\n├── 02 Journal/\n├── 03 Templates/\n├── 04 Attachments/\n└── README.md\n```\n\n## Note types\n\nUse YAML frontmatter on every note:\n\n- Required on all notes:\n  - `type`\n  - `tags`\n  - `created`\n- Required on `doc` and content notes:\n  - `status` (`queued | in-progress | done | archived`)\n- Optional content metadata:\n  - `author`\n  - `source`\n\nUse these primary types:\n\n- `note`: durable atomic thinking note; no `status`\n- `doc`: non-atomic working/reference note; uses `status`\n- `journal`: daily log note; no `status`\n- content types: `article`, `book`, `movie`, `tv`, `youtube`, `tweet`, `podcast`, `paper` (and extensible additional content types); uses `status`\n\n## Templates\n\nAlways read the matching template in `03 Templates/` before creating a note:\n\n- `note.md`\n- `journal.md`\n- `clipper-capture.json`\n\nUse core templates/date syntax. Do not require Templater.\n\n## Inbox workflow\n\n- Web captures land in `00 Inbox/` via `clipper-capture.json`.\n- Clipper sets `type` by URL (`tweet`, `youtube`, else `article`) and `status: queued`.\n- Process inbox captures by keeping/moving, converting into a `type: note`, or deleting.\n- Do not auto-write durable thinking notes from captured content unless explicitly asked.\n\n## Bases workflow\n\n- `00 Inbox/inbox.base` is the canonical queue view.\n- Grouping is by `note.type` for scan-by-content-type triage.\n- Prefer creating/editing `.base` files over Dataview.\n\n## Titles as APIs\n\nA note's title is its interface. Use complete, declarative phrases: \"Spaced Repetition Works Because of Retrieval,\" not \"Spaced Repetition.\" A well-titled note can be linked and understood without opening it. When creating or renaming notes, always prefer a full declarative statement.\n\n## Tag conventions\n\nTags live in the frontmatter `tags` array, not inline in the body.\n\n- Lowercase, hyphenated: `spaced-repetition`, not `Spaced Repetition` or `spacedRepetition`.\n- Topic-oriented, not structural: `learning` (what it's about), not `important` (how you feel about it).\n- Nest only when a hierarchy is genuinely useful: `ai/transformers` is fine, deep nesting is not.\n- Suggest tags based on the vault's existing taxonomy rather than inventing new ones.\n\n## Editing rules\n\n- Preserve existing prose unless user asks to rewrite.\n- Do not add or maintain an `updated` frontmatter field.\n- Use dense wikilinking (`[[Note Title]]`) and allow unresolved links as stubs.\n- Do not create top-level folders unless explicitly requested.\n- Do not assign/change `status`, move notes, or delete notes without explicit instruction.\n- Agent write surface is limited to:\n  - `/ask` response callouts\n  - optional daily briefing callout in journals\n\n## Search patterns\n\nDefault QMD collections:\n\n- `zettelclaw-inbox`\n- `zettelclaw-notes`\n- `zettelclaw-journal`\n- `zettelclaw-attachments`\n\n```bash\n# qmd (preferred when installed)\nqmd query \"spaced repetition and retrieval\" -c zettelclaw-notes\nqmd search \"status: queued\" -c zettelclaw-inbox\nqmd vsearch \"what have I been learning about memory\" -c zettelclaw-notes\n\n# ripgrep fallback\nrg -l 'type: note' \"01 Notes/\"\nrg -l 'type: article' \"00 Inbox/\" \"01 Notes/\"\nrg -l 'status: queued' \"00 Inbox/\" \"01 Notes/\"\n```\n\n## OpenClaw integration\n\nIf configuring OpenClaw memory paths, use:\n\n- `agents.defaults.memorySearch.extraPaths`\n\nDo not write legacy top-level `memorySearch`.\nOnly change OpenClaw config when the operator explicitly wants this vault wired into an OpenClaw installation.\n","tags":{"latest":"2026.3.11"},"stats":{"comments":0,"downloads":1004,"installsAllTime":37,"installsCurrent":4,"stars":0,"versions":3},"createdAt":1771824438353,"updatedAt":1778491617178},"latestVersion":{"version":"2026.3.11","createdAt":1773254512364,"changelog":"**Full Changelog**: https://github.com/maxpetretta/zettelclaw/compare/v2026.3.7...v2026.3.11","license":"MIT-0"},"metadata":null,"owner":{"handle":"maxpetretta","userId":"s172zqvhw8n09d3yfcv853zkmh8840m4","displayName":"Max Petretta","image":"https://avatars.githubusercontent.com/u/19291506?v=4"},"moderation":null}