[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75KCM47RC9XVG8X70KCVNJW":3,"skill-same:01M75KCM47RC9XVG8X70KCVNJW":67},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":60},"01M75KCM47RC9XVG8X70KCVNJW","daily-task-manager",null,"Task lifecycle management with stable task IDs. Add, complete, defer, remove,\nand review tasks with deterministic action routing and fail-closed ambiguity\nhandling. Maintains a running task list as a brain page.","cheRoma\u002Fgbrain-link-chat","cheRoma","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F265356812?v=4","01M75JVGAJEZK04E1THSDHYVNK","Roman Cherepanov","01M75JVGB5SWY40H959C3QXRAQ",0,"MIT","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fdaily-task-manager\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: daily-task-manager\nversion: 2.0.0\ndescription: |\n  Task lifecycle management with stable task IDs. Add, complete, defer, remove,\n  and review tasks with deterministic action routing and fail-closed ambiguity\n  handling. Maintains a running task list as a brain page.\ntriggers:\n  - \"add task\"\n  - \"complete task\"\n  - \"what are my tasks\"\n  - \"task list\"\n  - \"defer task\"\ntools:\n  - search\n  - get_page\n  - put_page\n  - add_timeline_entry\nmutating: true\nupstream: daily-task-manager@fc834ee\nwhen_to_use: \"Use when the user asks: \\\"add task\\\", \\\"complete task\\\", \\\"what are my tasks\\\", \\\"task list\\\", \\\"defer task\\\".\"\n---\n\n# Daily Task Manager\n\n## Contract\n\nThis skill guarantees:\n- Tasks stored as a brain page (`ops\u002Ftasks.md`) with structured format and a stable `id` per task\n- Task lifecycle: add → in-progress → complete | defer | remove\n- Priority levels: P0 (urgent), P1 (today), P2 (this week), P3 (backlog)\n- Completed tasks archived with completion date; deferred tasks carry a target date + reason\n- Mutations never drop unrelated tasks or unknown sections\n- Every action returns the structured result below (Returns)\n\n### Returns\n\nAfter every action, report a structured result so callers (including sub-agents) can chain reliably:\n\n```\n{action, task_id, status: ok|not_found|ambiguous|needs_confirmation, priority, date, page: \"ops\u002Ftasks.md\", saved: true|false}\n```\n\nFor `review`, return the grouped active-task list instead of a single task_id. When invoked with the trigger \"task list json\", return a JSON array of task objects `{id, description, priority, due, status}` instead of markdown.\n\n## Tool Interface\n\nUse ONLY the declared tools. `get_page(\"ops\u002Ftasks.md\")` to read, `put_page(\"ops\u002Ftasks.md\", …)` to write, `add_timeline_entry` for the audit trail, `search` for cross-referencing. Do not shell out to `gbrain` CLI verbs from this skill; the tools are the interface. (When the user runs this manually outside an agent, the CLI equivalents are `gbrain get ops\u002Ftasks` \u002F `gbrain put ops\u002Ftasks` — equivalents only, not the skill's interface.)\n\n## Action Routing\n\nMap user intent deterministically before touching state:\n- \"add \u002F remind me to \u002F put X on my list\" → **add**\n- \"done with X \u002F finished X \u002F completed X \u002F ✅ X\" → **complete**\n- \"push X \u002F defer X \u002F move X to next week\" → **defer**\n- \"delete X \u002F remove X \u002F kill task X\" → **remove** (explicit delete words only — never infer remove)\n- \"what are my tasks \u002F task list \u002F what's on my plate (today)\" → **review** (\"today\" filters to P0+P1)\n\n## Phases\n\n1. **Load.** `get_page(\"ops\u002Ftasks.md\")`. **First run:** if the page does not exist, create it from the Output Format template, then proceed.\n2. **Validate.** Determine the action via Action Routing. If required fields are missing (see per-action rules), ask ONE concise clarification before mutating state. Never fabricate priorities, due dates, or defer reasons.\n3. **Identify the target task** (complete\u002Fdefer\u002Fremove): match by `id` when given; otherwise fuzzy-match description against ACTIVE tasks only. Zero matches → return `not_found`, do not mutate. Multiple matches → list candidates with IDs, return `ambiguous`, do not mutate.\n4. **Execute:**\n   - **Add:** Require a description. Priority: use the user's stated\u002Fclearly-implied level; otherwise default to **P3 and say so in the reply + timeline entry**. Due date only if supplied or explicit in the user's words. Mint a new task ID (`t-YYYYMMDD-NN`, NN = next free ordinal that day). Add a timeline entry.\n   - **Complete:** Mark `[x]`, move to Completed with `(completed: YYYY-MM-DD)`.\n   - **Defer:** Require a target date\u002Ftimeframe AND a reason; ask if missing. Move to Deferred preserving original text, ID, and priority unless the user changes them.\n   - **Remove:** Destructive — require explicit confirmation unless the user's message already contains it. Prefer suggesting complete or defer.\n   - **Review:** Read-only. Never mutates. Active tasks grouped by priority, IDs shown.\n5. **Save.** `put_page(\"ops\u002Ftasks.md\")` after any mutation. Diff-mindset: touch only the affected lines; preserve all other content, including sections this skill doesn't recognize.\n\n## Edge Cases\n\n- **First run:** page missing → create from template before acting; `status: ok`, note \"initialized\".\n- **Malformed page:** if `ops\u002Ftasks.md` exists but doesn't match the schema, do NOT rewrite it wholesale. Append\u002Fedit within it minimally, preserve unknown content verbatim, and flag the malformation in the reply.\n- **Retry\u002Fduplicate add:** if an identical description already exists in active tasks, do not add a duplicate — report the existing task ID instead.\n- **Dates:** ISO 8601 (`YYYY-MM-DD`) everywhere. Compute \"today\"\u002F\"next week\" with code\u002Fclock, never guess.\n- **Page identifier:** always `ops\u002Ftasks.md` (with extension) in tool calls; this is the single canonical location.\n- **Single-writer assumption (concurrency limitation).** The task cycle is read-modify-write: `get_page(\"ops\u002Ftasks.md\")` → edit → `put_page(\"ops\u002Ftasks.md\")`. `put_page` replaces the WHOLE page and has no compare-and-swap, so two mutations that interleave are last-writer-wins: the second `put_page` overwrites the first's change (a completed task reappears, an added task vanishes), and the `t-YYYYMMDD-NN` minting can hand the same ordinal to two concurrent adds (duplicate IDs). Serialize task edits — never run parallel task mutations (multiple subagents, concurrent chat turns) against `ops\u002Ftasks.md`. If a mutation might race, re-`get_page` immediately before `put_page` and re-derive the next free ordinal from the freshly-read page.\n\n## Output Format\n\n### Persisted page format\n\nEach task carries a stable ID so later actions can target it safely:\n\n```markdown\n# Tasks\n\n## P0 — Urgent\n- [ ] \u003C!-- id: t-20260115-01 --> {task description} (due: {date})\n\n## P1 — Today\n- [ ] \u003C!-- id: {task-id} --> {task description} (due: {date optional})\n\n## P2 — This Week\n- [ ] \u003C!-- id: {task-id} --> {task description} (due: {date optional})\n\n## P3 — Backlog\n- [ ] \u003C!-- id: {task-id} --> {task description}\n\n## Deferred\n- [ ] \u003C!-- id: {task-id} --> {task description} (deferred until: {date}; reason: {reason})\n\n## Completed\n- [x] \u003C!-- id: {task-id} --> {task description} (completed: {date})\n```\n\n### User-facing response\n\nAfter a mutation: one concise line — action, task ID, priority\u002Fstatus, relevant date, saved-or-not. For review: active tasks grouped by priority. Keep replies compact; avoid tables on narrow chat surfaces.\n\n## When it fails\n\nFollow the [agent operator protocol](..\u002Fconventions\u002Fagent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:\n\n- The tasks page update returns `revision_conflict`: re-read `ops\u002Ftasks.md`, re-apply the one task change, and save; never overwrite the whole list from an old read.\n- `write_pending` (exit 10): report `saved: false` with the pending receipt and poll `gbrain write-request \u003Crequest_id>`; do not tell the user the task is recorded yet.\n- Ambiguous or missing task id: return `ambiguous` \u002F `not_found` and ask which task; never mutate the closest match.\n\n## Anti-Patterns\n\nEach with its corrective action:\n- Adding a task without priority → default P3 and SAY the default was applied (never silent).\n- Mutating on an ambiguous reference → stop, list candidates with IDs, ask.\n- Completing without a completion date → always stamp `(completed: YYYY-MM-DD)`.\n- Deferring without target date + reason → ask for both first.\n- Removing without explicit confirmation → confirm first; offer complete\u002Fdefer instead.\n- Overwriting the page wholesale \u002F dropping unknown sections → minimal diff edits only.\n- Using undeclared tools or CLI verbs → `get_page`\u002F`put_page`\u002F`search`\u002F`add_timeline_entry` only.\n- Fabricating due dates, priorities, or reasons → never invent required fields; ask.\n- Unbounded list growth → when Backlog exceeds ~20 items, prompt a weekly review.\n- Storing tasks outside the brain page → everything lives in `ops\u002Ftasks.md` (searchable).\n- Running parallel task mutations against `ops\u002Ftasks.md` → last-writer-wins whole-page `put_page` silently loses updates and mints duplicate IDs; serialize edits, re-read immediately before writing.\n\n## Design Rationale (failure modes this version closes)\n\n- **Interface drift:** an earlier version declared `get_page`\u002F`put_page` as tools but instructed CLI verbs in the body — models picked one at random. The declared tools are now the interface; CLI is relegated to a human-equivalent note.\n- **Unmatchable tasks:** without task IDs, \"complete the deploy task\" against two similar tasks silently mutated the wrong one. Stable `t-YYYYMMDD-NN` IDs + fail-closed ambiguity handling fix this.\n- **First-run crash:** assuming `ops\u002Ftasks.md` exists made a missing page undefined behavior. Create-from-template on first run fixes this.\n- **Wholesale overwrite risk:** \"write updated task list\" invited full-page rewrites that drop concurrent edits. Minimal-diff mandate + preserve-unknown-content rule fix this.\n","# Daily Task Manager\n\n## Contract\n\nThis skill guarantees:\n- Tasks stored as a brain page (`ops\u002Ftasks.md`) with structured format and a stable `id` per task\n- Task lifecycle: add → in-progress → complete | defer | remove\n- Priority levels: P0 (urgent), P1 (today), P2 (this week), P3 (backlog)\n- Completed tasks archived with completion date; deferred tasks carry a target date + reason\n- Mutations never drop unrelated tasks or unknown sections\n- Every action returns the structured result below (Returns)\n\n### Returns\n\nAfter every action, report a structured result so callers (including sub-agents) can chain reliably:\n\n```\n{action, task_id, status: ok|not_found|ambiguous|needs_confirmation, priority, date, page: \"ops\u002Ftasks.md\", saved: true|false}\n```\n\nFor `review`, return the grouped active-task list instead of a single task_id. When invoked with the trigger \"task list json\", return a JSON array of task objects `{id, description, priority, due, status}` instead of markdown.\n\n## Tool Interface\n\nUse ONLY the declared tools. `get_page(\"ops\u002Ftasks.md\")` to read, `put_page(\"ops\u002Ftasks.md\", …)` to write, `add_timeline_entry` for the audit trail, `search` for cross-referencing. Do not shell out to `gbrain` CLI verbs from this skill; the tools are the interface. (When the user runs this manually outside an agent, the CLI equivalents are `gbrain get ops\u002Ftasks` \u002F `gbrain put ops\u002Ftasks` — equivalents only, not the skill's interface.)\n\n## Action Routing\n\nMap user intent deterministically before touching state:\n- \"add \u002F remind me to \u002F put X on my list\" → **add**\n- \"done with X \u002F finished X \u002F completed X \u002F ✅ X\" → **complete**\n- \"push X \u002F defer X \u002F move X to next week\" → **defer**\n- \"delete X \u002F remove X \u002F kill task X\" → **remove** (explicit delete words only — never infer remove)\n- \"what are my tasks \u002F task list \u002F what's on my plate (today)\" → **review** (\"today\" filters to P0+P1)\n\n## Phases\n\n1. **Load.** `get_page(\"ops\u002Ftasks.md\")`. **First run:** if the page does not exist, create it from the Output Format template, then proceed.\n2. **Validate.** Determine the action via Action Routing. If required fields are missing (see per-action rules), ask ONE concise clarification before mutating state. Never fabricate priorities, due dates, or defer reasons.\n3. **Identify the target task** (complete\u002Fdefer\u002Fremove): match by `id` when given; otherwise fuzzy-match description against ACTIVE tasks only. Zero matches → return `not_found`, do not mutate. Multiple matches → list candidates with IDs, return `ambiguous`, do not mutate.\n4. **Execute:**\n   - **Add:** Require a description. Priority: use the user's stated\u002Fclearly-implied level; otherwise default to **P3 and say so in the reply + timeline entry**. Due date only if supplied or explicit in the user's words. Mint a new task ID (`t-YYYYMMDD-NN`, NN = next free ordinal that day). Add a timeline entry.\n   - **Complete:** Mark `[x]`, move to Completed with `(completed: YYYY-MM-DD)`.\n   - **Defer:** Require a target date\u002Ftimeframe AND a reason; ask if missing. Move to Deferred preserving original text, ID, and priority unless the user changes them.\n   - **Remove:** Destructive — require explicit confirmation unless the user's message already contains it. Prefer suggesting complete or defer.\n   - **Review:** Read-only. Never mutates. Active tasks grouped by priority, IDs shown.\n5. **Save.** `put_page(\"ops\u002Ftasks.md\")` after any mutation. Diff-mindset: touch only the affected lines; preserve all other content, including sections this skill doesn't recognize.\n\n## Edge Cases\n\n- **First run:** page missing → create from template before acting; `status: ok`, note \"initialized\".\n- **Malformed page:** if `ops\u002Ftasks.md` exists but doesn't match the schema, do NOT rewrite it wholesale. Append\u002Fedit within it minimally, preserve unknown content verbatim, and flag the malformation in the reply.\n- **Retry\u002Fduplicate add:** if an identical description already exists in active tasks, do not add a duplicate — report the existing task ID instead.\n- **Dates:** ISO 8601 (`YYYY-MM-DD`) everywhere. Compute \"today\"\u002F\"next week\" with code\u002Fclock, never guess.\n- **Page identifier:** always `ops\u002Ftasks.md` (with extension) in tool calls; this is the single canonical location.\n- **Single-writer assumption (concurrency limitation).** The task cycle is read-modify-write: `get_page(\"ops\u002Ftasks.md\")` → edit → `put_page(\"ops\u002Ftasks.md\")`. `put_page` replaces the WHOLE page and has no compare-and-swap, so two mutations that interleave are last-writer-wins: the second `put_page` overwrites the first's change (a completed task reappears, an added task vanishes), and the `t-YYYYMMDD-NN` minting can hand the same ordinal to two concurrent adds (duplicate IDs). Serialize task edits — never run parallel task mutations (multiple subagents, concurrent chat turns) against `ops\u002Ftasks.md`. If a mutation might race, re-`get_page` immediately before `put_page` and re-derive the next free ordinal from the freshly-read page.\n\n## Output Format\n\n### Persisted page format\n\nEach task carries a stable ID so later actions can target it safely:\n\n```markdown\n# Tasks\n\n## P0 — Urgent\n- [ ] \u003C!-- id: t-20260115-01 --> {task description} (due: {date})\n\n## P1 — Today\n- [ ] \u003C!-- id: {task-id} --> {task description} (due: {date optional})\n\n## P2 — This Week\n- [ ] \u003C!-- id: {task-id} --> {task description} (due: {date optional})\n\n## P3 — Backlog\n- [ ] \u003C!-- id: {task-id} --> {task description}\n\n## Deferred\n- [ ] \u003C!-- id: {task-id} --> {task description} (deferred until: {date}; reason: {reason})\n\n## Completed\n- [x] \u003C!-- id: {task-id} --> {task description} (completed: {date})\n```\n\n### User-facing response\n\nAfter a mutation: one concise line — action, task ID, priority\u002Fstatus, relevant date, saved-or-not. For review: active tasks grouped by priority. Keep replies compact; avoid tables on narrow chat surfaces.\n\n## When it fails\n\nFollow the [agent operator protocol](..\u002Fconventions\u002Fagent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:\n\n- The tasks page update returns `revision_conflict`: re-read `ops\u002Ftasks.md`, re-apply the one task change, and save; never overwrite the whole list from an old read.\n- `write_pending` (exit 10): report `saved: false` with the pending receipt and poll `gbrain write-request \u003Crequest_id>`; do not tell the user the task is recorded yet.\n- Ambiguous or missing task id: return `ambiguous` \u002F `not_found` and ask which task; never mutate the closest match.\n\n## Anti-Patterns\n\nEach with its corrective action:\n- Adding a task without priority → default P3 and SAY the default was applied (never silent).\n- Mutating on an ambiguous reference → stop, list candidates with IDs, ask.\n- Completing without a completion date → always stamp `(completed: YYYY-MM-DD)`.\n- Deferring without target date + reason → ask for both first.\n- Removing without explicit confirmation → confirm first; offer complete\u002Fdefer instead.\n- Overwriting the page wholesale \u002F dropping unknown sections → minimal diff edits only.\n- Using undeclared tools or CLI verbs → `get_page`\u002F`put_page`\u002F`search`\u002F`add_timeline_entry` only.\n- Fabricating due dates, priorities, or reasons → never invent required fields; ask.\n- Unbounded list growth → when Backlog exceeds ~20 items, prompt a weekly review.\n- Storing tasks outside the brain page → everything lives in `ops\u002Ftasks.md` (searchable).\n- Running parallel task mutations against `ops\u002Ftasks.md` → last-writer-wins whole-page `put_page` silently loses updates and mints duplicate IDs; serialize edits, re-read immediately before writing.\n\n## Design Rationale (failure modes this version closes)\n\n- **Interface drift:** an earlier version declared `get_page`\u002F`put_page` as tools but instructed CLI verbs in the body — models picked one at random. The declared tools are now the interface; CLI is relegated to a human-equivalent note.\n- **Unmatchable tasks:** without task IDs, \"complete the deploy task\" against two similar tasks silently mutated the wrong one. Stable `t-YYYYMMDD-NN` IDs + fail-closed ambiguity handling fix this.\n- **First-run crash:** assuming `ops\u002Ftasks.md` exists made a missing page undefined behavior. Create-from-template on first run fixes this.\n- **Wholesale overwrite risk:** \"write updated task list\" invited full-page rewrites that drop concurrent edits. Minimal-diff mandate + preserve-unknown-content rule fix this.\n",{"name":5,"tools":24,"version":29,"mutating":30,"triggers":31,"upstream":37,"description":38,"when_to_use":39},[25,26,27,28],"search","get_page","put_page","add_timeline_entry","2.0.0",true,[32,33,34,35,36],"add task","complete task","what are my tasks","task list","defer task","daily-task-manager@fc834ee","Task lifecycle management with stable task IDs. Add, complete, defer, remove,\nand review tasks with deterministic action routing and fail-closed ambiguity\nhandling. Maintains a running task list as a brain page.\n","Use when the user asks: \"add task\", \"complete task\", \"what are my tasks\", \"task list\", \"defer task\".","feat\u002Flink-chat-distiller","b7935e119783c2f35d6d182ede452faf32de675c","plugin\u002Fskills\u002Fdaily-task-manager","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat","https:\u002F\u002Fgithub.com\u002FcheRoma","https:\u002F\u002Fostov.dev","Engineer and founder of Ostov. Websites, Telegram apps, business automation and ERP\u002FCRM integrations.","2026-11-12 20:40:42",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":30},[50,53,56],{"tool":51,"command":52},"npx","npx skills add cheRoma\u002Fgbrain-link-chat --skill daily-task-manager",{"tool":54,"command":55},"bunx","bunx skills add cheRoma\u002Fgbrain-link-chat --skill daily-task-manager",{"tool":57,"command":58},"pnpm","pnpm dlx skills add cheRoma\u002Fgbrain-link-chat --skill daily-task-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fdaily-task-manager\u002FSKILL.md",[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"routing-eval.jsonl","OTHER","其他",860,"https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fdaily-task-manager\u002Frouting-eval.jsonl",[68,74,80,87,94,101],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M75M5HR90P229V66Q4Q1GM0W","query-helper","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M75M5GZ1WQB7NHR07QV38YB8","broken","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M75M5FDJV3M4GP71SKD31P33","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M75M5DYW3WBGDC6M90YMC843","meeting-prep","Build a briefing before you meet someone, from their recent threads, open loops and what they care about.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fmeeting-prep\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M75M5CJZX22MV7XKJQYEMC9Y","inbox-zero","Triage the inbox into replies, delegations and archives.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Finbox-zero\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M75M5B953478ACM9X3MPAX3P","deal-memo","Draft an investment memo from the deal pages and the founder history already in the brain.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fdeal-memo\u002FSKILL.md",[],[]]