[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7XWGCW2EVDG2Q3RG1J247":3,"skill-same:01M7F7XWGCW2EVDG2Q3RG1J247":60},{"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":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M7F7XWGCW2EVDG2Q3RG1J247","briefing",null,"Compile daily briefing with meeting context, active deals, and citation tracking","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbriefing\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: briefing\nversion: 1.3.0\ndescription: Compile daily briefing with meeting context, active deals, and citation tracking\ntriggers:\n  - \"daily briefing\"\n  - \"morning briefing\"\n  - \"what's happening today\"\n  - \"brain pulse\"\n  - \"pre-briefing pull\"\ntools:\n  - search\n  - query\n  - get_page\n  - list_pages\n  - get_timeline\nmutating: false\nupstream: briefing@fc834ee\n---\n\n# Briefing Skill\n\nCompile a daily briefing from brain context.\n\n> **Filing rule:** When the briefing creates or updates brain pages,\n> follow `skills\u002F_brain-filing-rules.md`.\n\n## Contract\n\n- Every fact in the briefing includes an inline `[Source: slug, updated DATE]` citation.\n- Meeting participants are resolved against the brain; gaps are explicitly flagged.\n- Active deals and action items include deadlines and recency context.\n- The briefing is read-only: no brain pages are created or modified unless the user explicitly requests it.\n- Stale alerts surface pages relevant to today's context, not just all stale pages.\n\n## Pre-Briefing Context Pull\n\nRun these BEFORE composing the briefing sections. All four pulls are read-only.\n\n0a. **Salience scan.** Surface pages with high emotional or activity salience:\n\n   ```bash\n   gbrain salience --days 7\n   ```\n\n   Returns pages ranked by emotional weight and recent activity. Fold the top\n   5-10 into the briefing under a \"High-Salience Pages\" section — these are the\n   entities and topics that are emotionally or operationally hot right now. Use\n   this to prioritize which meetings\u002Fdeals\u002Fpeople get the most briefing depth.\n\n0b. **Anomaly detection.** Surface statistical anomalies in the brain:\n\n   ```bash\n   gbrain anomalies\n   ```\n\n   Defaults to today against a 30-day baseline; widen with\n   `--lookback-days N` or lower the threshold with `--sigma 2`. Flags cohorts\n   (by tag, by type) whose activity broke from their normal cadence — sudden\n   spikes in mentions or pages updating far off their usual rhythm. Add hits to\n   an \"Anomalies\" section after the brain pulse.\n\n0c. **Personal recall.** Check stored personal facts and preferences before\n   composing:\n\n   ```bash\n   gbrain recall --query \"current priorities and preferences\" --json\n   ```\n\n   Use recall to pull personal context — dietary preferences, communication\n   preferences, prior commitments or promises made. This prevents the briefing\n   from contradicting things the user has previously stated or decided.\n\n0d. **Hot memory pulse (v0.32).** Before composing anything else, run:\n\n   ```bash\n   gbrain recall --since-last-run --supersessions --pending --rollup --json\n   ```\n\n   Fold the result into the briefing under a \"Brain pulse\" section at the top:\n   1. **Contradictions resolved overnight** — the `--supersessions` output. Lead\n      with these because they're new corrections to your model of the world.\n   2. **Top mentions** — `top_entities` from `--rollup` (top 5 entity slugs by\n      fact count in the window).\n   3. **New facts since last briefing** — group the `facts` array under each\n      entity from the rollup; include `kind`, `notability`, and `confidence`.\n   4. **Pending consolidation footer** — when `pending_consolidation_count > 0`,\n      note `N facts await dream-cycle consolidation` so the operator can decide\n      whether to run `gbrain dream` before reading further.\n\n   The `--since-last-run` flag advances `~\u002F.gbrain\u002Frecall-cursors\u002F\u003Csource>.json`\n   so the next briefing picks up exactly where this one left off. If you're\n   running this as a cron job, pass `--source \u003Cslug>` or set `GBRAIN_SOURCE`\n   explicitly — cron doesn't start in your repo-root cwd, so dotfile resolution\n   may miss the right source. Thin-client installs (`gbrain init --mcp-only`)\n   route through the remote brain transparently.\n\n0e. **Open loops (when google sources exist).** Pull who is waiting on the\n   user and what they promised:\n\n   ```bash\n   gbrain waiting --json\n   ```\n\n   Fold the top counterparties (what's owed, due dates, evidence quotes,\n   deep links) into the ACTION ITEMS section — these are real loop rows, not\n   inferred follow-ups, so they outrank prose heuristics. `waiting` refuses\n   on stale google sources (no successful sync in 24h) and names the exact\n   fix — that's by design: run the sync it names, then retry (see\n   `skills\u002Fgoogle-loops\u002FSKILL.md`).\n\n## Phases\n\n1. **Today's meetings.** For each meeting on the calendar:\n   - Search gbrain for each participant by name\n   - Read their pages from gbrain for compiled_truth context\n   - Summarize: who they are, recent timeline, relationship to you\n2. **Active deals.** List deal pages in gbrain filtered to active status:\n   - Deadlines approaching in the next 7 days\n   - Recent timeline entries (last 7 days)\n3. **Time-sensitive threads.** Open items from timeline entries:\n   - Items with deadlines in the next 48 hours\n   - Follow-ups that are overdue\n4. **Recent changes.** Pages updated in the last 24 hours:\n   - What changed and why (read timeline entries from gbrain)\n5. **People in play.** List person pages in gbrain sorted by recency:\n   - Updated in last 7 days\n   - Have high activity (many recent timeline entries)\n6. **Stale alerts.** From gbrain health check:\n   - Pages flagged as stale that are relevant to today's meetings\n\n## GBrain-Native Context Loading\n\nBefore generating any briefing, load context from gbrain systematically.\n\n### Before a meeting\n\nFor every attendee on the calendar invite:\n- `gbrain search \"\u003Cattendee name>\"` -- find their brain page\n- `gbrain get \u003Cslug>` -- load compiled truth, recent timeline, relationship context\n- If no page exists, note the gap (\"No brain page for alice-example -- consider enrichment\")\n\n### Before an email reply\n\nBefore drafting or triaging any email:\n- `gbrain search \"\u003Csender name>\"` -- load sender context\n- Read their compiled truth to understand who they are, what they care about, and\n  your relationship history. This turns a cold reply into an informed one.\n\n### Daily briefing queries\n\nRun these queries to populate the briefing sections:\n- `gbrain query \"active deals status\"` -- deal pipeline snapshot\n- `gbrain query \"meetings this week\"` -- recent meeting pages with insights\n- `gbrain query \"pending commitments follow-ups\"` -- open threads and action items\n- `gbrain list --type person --sort updated_desc --limit 10` -- people in play\n\n## Output Format\n\n```\nDAILY BRIEFING -- [date]\n========================\n\nMEETINGS TODAY\n- [time] [meeting name]\n  Participants: [name] (slug: people\u002Fname, [key context])\n\nACTIVE DEALS\n- [deal name] -- [status], deadline: [date]\n  Recent: [latest timeline entry]\n\nACTION ITEMS\n- [item] -- due [date], related to [slug]\n\nRECENT CHANGES (24h)\n- [slug] -- [what changed]\n\nPEOPLE IN PLAY\n- [name] -- [why they're active]\n```\n\n## Back-Linking During Briefing\n\nIf the briefing creates or updates any brain pages (e.g., new meeting prep\npages, updated entity pages), the back-linking iron law applies: every entity\nmentioned must have a back-link from their page. See `skills\u002F_brain-filing-rules.md`.\n\n## Citation in Briefings\n\nWhen presenting facts from brain pages, include inline citations:\n- \"Jane is CTO of Acme [Source: people\u002Fjane-doe, updated 2026-04-01]\"\n- This lets the user trace any claim back to the brain page and assess freshness\n\n## Anti-Patterns\n\n- **Briefing without brain queries.** Never generate a briefing from memory alone; always query gbrain for current data.\n- **Uncited facts.** Every claim must include `[Source: slug, updated DATE]`. A fact without a citation is unverifiable.\n- **Stale context presented as current.** If a page hasn't been updated in 30+ days, flag the staleness explicitly rather than presenting it as fresh.\n- **Modifying brain pages unprompted.** The briefing is read-only by default. Do not create or update pages unless the user explicitly requests it.\n- **Ignoring coverage gaps.** When a meeting participant has no brain page, say so. Silence about gaps hides ignorance.\n\n## Tools Used\n\n- Search gbrain by name (query)\n- Read a page from gbrain (get_page)\n- List pages in gbrain by type (list_pages)\n- Check gbrain health (get_health)\n- View timeline entries in gbrain (get_timeline)\n","# Briefing Skill\n\nCompile a daily briefing from brain context.\n\n> **Filing rule:** When the briefing creates or updates brain pages,\n> follow `skills\u002F_brain-filing-rules.md`.\n\n## Contract\n\n- Every fact in the briefing includes an inline `[Source: slug, updated DATE]` citation.\n- Meeting participants are resolved against the brain; gaps are explicitly flagged.\n- Active deals and action items include deadlines and recency context.\n- The briefing is read-only: no brain pages are created or modified unless the user explicitly requests it.\n- Stale alerts surface pages relevant to today's context, not just all stale pages.\n\n## Pre-Briefing Context Pull\n\nRun these BEFORE composing the briefing sections. All four pulls are read-only.\n\n0a. **Salience scan.** Surface pages with high emotional or activity salience:\n\n   ```bash\n   gbrain salience --days 7\n   ```\n\n   Returns pages ranked by emotional weight and recent activity. Fold the top\n   5-10 into the briefing under a \"High-Salience Pages\" section — these are the\n   entities and topics that are emotionally or operationally hot right now. Use\n   this to prioritize which meetings\u002Fdeals\u002Fpeople get the most briefing depth.\n\n0b. **Anomaly detection.** Surface statistical anomalies in the brain:\n\n   ```bash\n   gbrain anomalies\n   ```\n\n   Defaults to today against a 30-day baseline; widen with\n   `--lookback-days N` or lower the threshold with `--sigma 2`. Flags cohorts\n   (by tag, by type) whose activity broke from their normal cadence — sudden\n   spikes in mentions or pages updating far off their usual rhythm. Add hits to\n   an \"Anomalies\" section after the brain pulse.\n\n0c. **Personal recall.** Check stored personal facts and preferences before\n   composing:\n\n   ```bash\n   gbrain recall --query \"current priorities and preferences\" --json\n   ```\n\n   Use recall to pull personal context — dietary preferences, communication\n   preferences, prior commitments or promises made. This prevents the briefing\n   from contradicting things the user has previously stated or decided.\n\n0d. **Hot memory pulse (v0.32).** Before composing anything else, run:\n\n   ```bash\n   gbrain recall --since-last-run --supersessions --pending --rollup --json\n   ```\n\n   Fold the result into the briefing under a \"Brain pulse\" section at the top:\n   1. **Contradictions resolved overnight** — the `--supersessions` output. Lead\n      with these because they're new corrections to your model of the world.\n   2. **Top mentions** — `top_entities` from `--rollup` (top 5 entity slugs by\n      fact count in the window).\n   3. **New facts since last briefing** — group the `facts` array under each\n      entity from the rollup; include `kind`, `notability`, and `confidence`.\n   4. **Pending consolidation footer** — when `pending_consolidation_count > 0`,\n      note `N facts await dream-cycle consolidation` so the operator can decide\n      whether to run `gbrain dream` before reading further.\n\n   The `--since-last-run` flag advances `~\u002F.gbrain\u002Frecall-cursors\u002F\u003Csource>.json`\n   so the next briefing picks up exactly where this one left off. If you're\n   running this as a cron job, pass `--source \u003Cslug>` or set `GBRAIN_SOURCE`\n   explicitly — cron doesn't start in your repo-root cwd, so dotfile resolution\n   may miss the right source. Thin-client installs (`gbrain init --mcp-only`)\n   route through the remote brain transparently.\n\n0e. **Open loops (when google sources exist).** Pull who is waiting on the\n   user and what they promised:\n\n   ```bash\n   gbrain waiting --json\n   ```\n\n   Fold the top counterparties (what's owed, due dates, evidence quotes,\n   deep links) into the ACTION ITEMS section — these are real loop rows, not\n   inferred follow-ups, so they outrank prose heuristics. `waiting` refuses\n   on stale google sources (no successful sync in 24h) and names the exact\n   fix — that's by design: run the sync it names, then retry (see\n   `skills\u002Fgoogle-loops\u002FSKILL.md`).\n\n## Phases\n\n1. **Today's meetings.** For each meeting on the calendar:\n   - Search gbrain for each participant by name\n   - Read their pages from gbrain for compiled_truth context\n   - Summarize: who they are, recent timeline, relationship to you\n2. **Active deals.** List deal pages in gbrain filtered to active status:\n   - Deadlines approaching in the next 7 days\n   - Recent timeline entries (last 7 days)\n3. **Time-sensitive threads.** Open items from timeline entries:\n   - Items with deadlines in the next 48 hours\n   - Follow-ups that are overdue\n4. **Recent changes.** Pages updated in the last 24 hours:\n   - What changed and why (read timeline entries from gbrain)\n5. **People in play.** List person pages in gbrain sorted by recency:\n   - Updated in last 7 days\n   - Have high activity (many recent timeline entries)\n6. **Stale alerts.** From gbrain health check:\n   - Pages flagged as stale that are relevant to today's meetings\n\n## GBrain-Native Context Loading\n\nBefore generating any briefing, load context from gbrain systematically.\n\n### Before a meeting\n\nFor every attendee on the calendar invite:\n- `gbrain search \"\u003Cattendee name>\"` -- find their brain page\n- `gbrain get \u003Cslug>` -- load compiled truth, recent timeline, relationship context\n- If no page exists, note the gap (\"No brain page for alice-example -- consider enrichment\")\n\n### Before an email reply\n\nBefore drafting or triaging any email:\n- `gbrain search \"\u003Csender name>\"` -- load sender context\n- Read their compiled truth to understand who they are, what they care about, and\n  your relationship history. This turns a cold reply into an informed one.\n\n### Daily briefing queries\n\nRun these queries to populate the briefing sections:\n- `gbrain query \"active deals status\"` -- deal pipeline snapshot\n- `gbrain query \"meetings this week\"` -- recent meeting pages with insights\n- `gbrain query \"pending commitments follow-ups\"` -- open threads and action items\n- `gbrain list --type person --sort updated_desc --limit 10` -- people in play\n\n## Output Format\n\n```\nDAILY BRIEFING -- [date]\n========================\n\nMEETINGS TODAY\n- [time] [meeting name]\n  Participants: [name] (slug: people\u002Fname, [key context])\n\nACTIVE DEALS\n- [deal name] -- [status], deadline: [date]\n  Recent: [latest timeline entry]\n\nACTION ITEMS\n- [item] -- due [date], related to [slug]\n\nRECENT CHANGES (24h)\n- [slug] -- [what changed]\n\nPEOPLE IN PLAY\n- [name] -- [why they're active]\n```\n\n## Back-Linking During Briefing\n\nIf the briefing creates or updates any brain pages (e.g., new meeting prep\npages, updated entity pages), the back-linking iron law applies: every entity\nmentioned must have a back-link from their page. See `skills\u002F_brain-filing-rules.md`.\n\n## Citation in Briefings\n\nWhen presenting facts from brain pages, include inline citations:\n- \"Jane is CTO of Acme [Source: people\u002Fjane-doe, updated 2026-04-01]\"\n- This lets the user trace any claim back to the brain page and assess freshness\n\n## Anti-Patterns\n\n- **Briefing without brain queries.** Never generate a briefing from memory alone; always query gbrain for current data.\n- **Uncited facts.** Every claim must include `[Source: slug, updated DATE]`. A fact without a citation is unverifiable.\n- **Stale context presented as current.** If a page hasn't been updated in 30+ days, flag the staleness explicitly rather than presenting it as fresh.\n- **Modifying brain pages unprompted.** The briefing is read-only by default. Do not create or update pages unless the user explicitly requests it.\n- **Ignoring coverage gaps.** When a meeting participant has no brain page, say so. Silence about gaps hides ignorance.\n\n## Tools Used\n\n- Search gbrain by name (query)\n- Read a page from gbrain (get_page)\n- List pages in gbrain by type (list_pages)\n- Check gbrain health (get_health)\n- View timeline entries in gbrain (get_timeline)\n",{"name":5,"tools":24,"version":30,"mutating":20,"triggers":31,"upstream":37,"description":7},[25,26,27,28,29],"search","query","get_page","list_pages","get_timeline","1.3.0",[32,33,34,35,36],"daily briefing","morning briefing","what's happening today","brain pulse","pre-briefing pull","briefing@fc834ee","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fbriefing",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill briefing",{"tool":52,"command":53},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill briefing",{"tool":55,"command":56},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill briefing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbriefing\u002FSKILL.md",true,[],[61,68,73,80,87,94],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":69,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"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},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\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},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\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},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\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},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]