跳到正文
cccskills
免费在 GitHub 公开

morning-standup

Use when: Good morning Team, start-of-day briefing, or morning status request. Architect orchestrates; Builder, Tester, and Router return their sections as subagents.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md5.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Morning Standup

Start-of-day briefing routine. Triggered by the team lead saying "Good morning Team" (or variants). Architect orchestrates; Builder, Tester, and Router are invoked as subagents and return their sections to Architect.

Trigger

Phrases: "Good morning Team", "Good morning", "Morning Team".

Read your agent identity and follow the section below that matches.

Memory reading (every agent)

  • Read live memory through the active storage plugin using read-memory(<agent>). For yesterday's outcomes read its WARM view, read-memory(<agent>, 'warm'), where the plugin keeps tiers; otherwise the latest archive snapshot (path defined in the plugin file), if one exists.
  • Live memory wins for current state; use WARM or the snapshot only for carry-forward items, blockers and yesterday's outcomes.
  • Sub-agents never sweep. Any memory command they run takes --read-only (or MEMORY_READONLY=1), so parallel runs cannot race.

Architect — Orchestrator

Rules

  • Read-only apart from the one sweep in Step 1: no other file writes, git operations or memory updates.
  • Bullet points only. The team lead will ask for detail if needed.
  • Dispatch Builder, Tester, and Router as subagents in parallel before compiling the briefing.
  • Do not scan all historical archive files by default.

Protocol

Step 1 — Sweep, then read Architect's memory

  • If the active storage plugin defines sweep-memory(), run it once now, before dispatching (it skips itself if it already ran today).
  • Read memory per "Memory reading" above, including all tiers the plugin exposes.

Step 2 — Dispatch subagents

Run Builder, Tester, and Router as subagents simultaneously with the morning-standup prompt. Collect their reports. When dispatching Router, use the fastest/economy-tier model your runtime offers for the dispatch — Router is economy-tier per its manifest. This skill file ships identically to every adapter, so it never asserts one runtime's literal model-selection syntax; see ROUTING.md's "Dispatch Builder" model-selection guidance for how each adapter's own generated instructions resolve this to a concrete identifier.

Step 3 — Compile and deliver briefing

Good morning. Team brief for [DATE].

**Architect**
- [HOT item 1 — one line status]
- [HOT item 2 — one line status]
- Today's focus: [from architect.md or latest archive Carry-Forward section]
- Decisions needed: [any team lead decision or approval needed, or "None"]

**Builder**
[paste Builder's bullets verbatim]

**Tester**
[paste Tester's bullets verbatim]

**Router**
[paste Router's bullets verbatim]

**Needs team lead today**
- [consolidated list of decisions, approvals, or inputs required across all agents — or "Nothing urgent"]

No closing questions. No narrative. Deliver and stop.


Builder — Subagent

Rules

  • Invoked as a subagent by Architect.
  • Read-only. No file writes, no git operations, no memory updates.
  • Return bullet points only to Architect — do not deliver directly to the team lead.

Protocol

Step 1 — Read Builder's memory per "Memory reading" above, if it exists.

Step 2 — Return brief

**Builder**
- Active: [current branch or ticket — one line, or "No active work"]
- Yesterday: [one-line outcome summary, or "No sessions"]
- Blockers: [blocked on decision or environment issue, or "None"]

Three bullets maximum unless there are multiple active items. If nothing to report, return:

**Builder**
- Clear. No active work.

Tester — Subagent

Rules

  • Invoked as a subagent by Architect.
  • Read-only. No file writes, no git operations, no memory updates.
  • Return bullet points only to Architect — do not deliver directly to the team lead.

Protocol

Step 1 — Read Tester's memory per "Memory reading" above, if it exists.

Step 2 — Return brief

**Tester**
- QA queue: [tickets in state:ready-for-qa — list briefly, or "Clear"]
- Yesterday: [one-line outcome summary, or "No QA runs"]
- Blockers: [environment issues, missing data, or "None"]

Three bullets maximum unless there are multiple queue items. If nothing to report, return:

**Tester**
- QA clear. Nothing pending.

Router — Subagent

Rules

  • Invoked as a subagent by Architect.
  • Read-only. No file writes, no git operations, no memory updates.
  • Return bullet points only to Architect — do not deliver directly to the team lead.
  • If no remote team is configured, return: **Router** - Not configured. No relay activity.

Protocol

Step 1 — Read Router's memory per "Memory reading" above, if it exists.

Step 2 — Return brief

**Router**
- Routing: [any unresolved classifications or pending escalations — or "Clear"]
- Yesterday: [one-line summary of routing activity, or "No routing events"]

Two bullets maximum. If nothing to report, return:

**Router**
- Relay clear. Nothing pending.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic ticket.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges, and untested preconditions in a finished plan/ticket/ADR before it is handed to Builder. Optional pass — Architect judges when to apply it; not a mandatory gate on every ticket.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

Use when: Tester needs UI state evidence for VBR, or Builder needs to verify an integration wire is observable end-to-end. Powered by agent-browser MCP — token-efficient browser automation (200–400 tokens/page).

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

Use when drafting a bug or defect ticket, reviewing one someone else wrote, or deciding whether a reported problem is ready to file. Keeps what the reporter actually saw separate from what the agent later found out, so a reader can tell which lines are testimony and which are collected proof. Trigger phrases: 'file a bug', 'write up this defect', 'triage this report', 'is this ticket ready to file', 'what did the reporter actually see'.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

中文简介正在准备中。当前显示原文说明。

Agistra/agistra.dev52026年10月21日 更新

查看 Agistra 的全部技能

报告此技能的问题