菜单
Use this whenever the user starts a workday or says "where were we", "what's the status", "catch me up", or needs one summary spanning Linear, GitHub, Vercel, Supabase, and Notion. NOT for single-system lookups — query that system directly.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | daily-brief |
| description | Use this whenever the user starts a workday or says "where were we", "what's the status", "catch me up", or needs one summary spanning Linear, GitHub, Vercel, Supabase, and Notion. NOT for single-system lookups — query that system directly. |
Generates a structured morning brief across all your systems so you don't open 6 tabs to figure out what to do.
Pull active state from Linear, GitHub, Vercel, Supabase, VPS/automation server, and Notion. Surface blockers, urgent items, and the highest-leverage focus task for today. Output a concise brief — to chat by default, to a Notion daily brief page if approved.
Reads from:
Writes to:
A blocker is anything that:
Apply this priority:
Anything Claude noticed but won't act on without explicit go-ahead:
Default format below. Adjust if you want shorter / different sections.
# Daily brief — [Date]
## ⚡ Top focus
[Single sentence: the one highest-leverage thing to start with]
## 🔥 Production / urgent
[Any production issues, P0/P1 blockers, automation failures. Empty if none.]
## 🟢 Active work
[Linear issues in progress, GitHub PRs in flight]
- PROJ-42: Dashboard cards — branch pushed, preview QA pending
- PROJ-138: Auth refactor — blocked on Supabase migration review
## 👀 Awaiting review (yours)
[PRs assigned to you for review]
- PR #47: [Feature] onboarding — 2 days old
## 🛑 Blockers
[Anything stopping forward progress on active work]
- PROJ-138 blocked on RLS policy decision (logged 1d ago)
## 🤖 Automations
[VPS/automation server jobs status]
- ✅ Fitness tracker → Notion sync ran at 06:00, success
- ❌ Weekly research scan failed at 02:00 — see logs
## 📋 Decisions / docs
[Notion updates worth knowing about]
- Decision logged: switched landing page hero to Three.js variant
- PRD updated: [Your feature] spec
## ⚠️ Approvals needed
[Things Claude noticed but won't act on without you]
- Should PROJ-103 move to blocked? (no movement in 7d)
- PR #47 ready to merge after review
## ⏭ Suggested order
1. [First thing — usually the top focus]
2. [Second thing]
3. [Third thing]
## 🧊 Stale or deferred
[Items worth glancing at occasionally — not today's priority]
- 3 issues with no movement in 14+ days
- Branch PROJ-100-experiments is 30 days stale
Tier 1 (default) — read everything, output to chat. No writes.
Tier 3 — needs approval:
Never auto:
notion-brain — for writing brief to Notion if approvedlinear-operator — for status drafts if approvedgithub-operator — for PR/check detailsautomation-sre — for routing to VPS/automation server failure investigationobservability-incident-loop — invoke if production incident is foundPERMISSION-MODEL.md (repo root) — for any escalation requestsShort brief (mid-day check-in): Skip stale/deferred section. Focus on top focus, urgent, and approvals.
Weekly version:
Run skill-creator instead, which produces a different output (patterns + skill updates) rather than a daily snapshot.
Pre-meeting brief: Add a section "What's relevant for [meeting topic]" pulling Notion docs tagged with that topic.
Brief is too long — Default to 1-screen output. If you have 15 active issues, the brief shows top 5 and counts the rest.
Brief is generic / unhelpful — Means the tool integrations aren't connected. With only chat + memory, the brief becomes a guess. Either wire up actual Linear/GitHub/Notion read access or accept the brief is just a "what should I do today" prompt.
Brief includes everything stale — Stale items go in the deferred section. Don't let them dominate the actual focus.
You never read it after week 1 — That means it's not useful. Either make it shorter, change what's in it, or drop it. Don't keep generating a brief no one reads.
Use this whenever a PR has a Vercel preview URL and needs browser QA against acceptance criteria — happy path, errors, empty states, responsive behavior, a11y basics — even if the user just says "check the preview". Requires a preview URL. NOT for release/deploy-readiness checks (no preview needed there) — use deploy-ready.
Plan and split work into parallel worktree sessions. Use whenever the user wants to work on multiple tasks at once, mentions parallel sessions, worktrees, "split this up", "dispatch", or lists several independent tasks for one work session.
Use this skill when implementing or reviewing UI that needs semantic HTML, keyboard navigation, focus management, ARIA labels, color contrast, reduced motion, forms, modals, or public-facing pages. Do not use as a standalone product-planning or backend workflow; pair it with design-system-ui, responsive-ui, or vercel-preview-qa when broader UI review is needed.
Use this skill when working across client, agency, consulting, or personal projects where code, data, credentials, prompts, or reusable patterns could leak between contexts. Do not use for ordinary single-project work with no cross-client or cross-workspace boundary risk.
Use this skill when creating components, implementing Figma designs, cleaning inconsistent styling, adding or reviewing tokens, spacing, typography, or component variants. Do not use for backend work, feature scoping, or visual QA that requires a live preview instead of design-system decisions.
Use this skill when importing ChatGPT or Claude exports, old Notion databases, local notes, or messy knowledge dumps into a durable knowledge system after redaction, deduplication, and classification. Do not use for live project planning, raw unredacted client data, or content that should remain out of Notion.