Agent Skillsmohitagw15856/pm-claude-skills › async-update-format

async-update-format

GitHub

提供异步状态更新格式,采用红绿灯+叙事结构。强调先报状态、再述变更、 blockers 转为具体行动请求,并分离30秒速览层与详情层,提升信息阅读效率。

exports/openclaw/async-update-format/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

撰写周报或状态更新 格式化团队同步内容 解决更新无人阅读的问题 优化异步检查点结构

Install

npx skills add mohitagw15856/pm-claude-skills --skill async-update-format -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/async-update-format -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@async-update-format

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill async-update-format -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "async-update-format",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/async-update-format.html",
    "metadata": {
        "openclaw": {
            "emoji": "🧠"
        }
    },
    "description": "Write status updates people actually read — the traffic-light-plus-narrative format (state first, story second), the blockers-are-asks rule, and the skimmable structure that respects a reader with thirty seconds. Use when asked write my weekly update, format our team's status posts, nobody reads my updates, or what goes in a good async check-in. Produces the update format with a filled example, the blockers-as-asks discipline, and the reader-time contract."
}

Async Update Format Skill

Status updates die of two diseases: the activity log ("attended meetings, worked on the project") that says nothing, and the essay that says everything to readers with thirty seconds. The format that survives: state first (on-track / at-risk / blocked, with the one-line why), then the delta (what changed since last time — not what exists), then blockers written as asks with names ("blocked on X — need [person] to approve Y by Friday"), then the next milestone with its date. Skimmable in thirty seconds, expandable for the reader who wants more.

What This Skill Produces

  • The format — state → delta → asks → next, with length budgets per section
  • A filled example — realistic, showing the delta-not-inventory discipline
  • The blockers-as-asks rule — every blocker names a person and an action, or it's just weather
  • The reader-time contract — the 30-second skim layer and the optional depth layer, separated

Required Inputs

Ask for these if not provided:

  • The update's audience and altitude — the manager (risks and asks), the team (coordination detail), stakeholders (outcomes) — one update rarely serves all three; the format flexes or splits
  • The cadence and the vehicle — weekly in a channel? Biweekly in a doc? The format compresses for chat, breathes in docs
  • This period's raw material — what actually happened, honestly including the nothing-moved weeks (the format has an honest shape for those too)

Framework: The Format Rules

  1. State leads, unhedged: 🟢 on-track / 🟡 at-risk / 🔴 blocked — plus one line of why. Readers triage by state; burying "we're going to miss the date" in paragraph three is how misses become surprises. A 🟡 with a clear why builds more trust than a 🟢 streak that flips red overnight.
  2. Delta, not inventory: what changed since the last update — shipped, decided, learned, slipped. The inventory ("still working on X, Y continues") is noise wearing progress's clothes; a nothing-moved week says so in one line with the why, which is itself information.
  3. Blockers are asks with names and dates: "blocked on legal review" is weather; "need [name] to approve the DPA by Thu or the launch slips a week" is an ask that can be actioned — by the reader, which is the point of telling them. Every blocker that stays nameless stays blocked.
  4. Next is a milestone with a date: "next: ship the beta to 10 customers by the 28th" — the line that makes the following update verifiable, which is what makes the whole cadence honest. "Continue making progress" is the anti-milestone.
  5. Two layers, visibly separated: the skim layer (state/delta/asks/next — the 30-second contract) and below a divider, the depth (details, links, numbers) for the readers who want it. Respecting the skimmer is what keeps updates read; the depth layer is what keeps them useful.

Output Format

Update: [project] — [date]

State: 🟢/🟡/🔴 — [the one-line why] Since last time: [2–4 delta bullets — shipped/decided/learned/slipped] Asks: [each: what, from whom, by when — or "none"] Next: [milestone + date]


Depth (optional): [details, links, metrics for the interested]

Quality Checks

  • The state is first and its why fits one line
  • Every bullet is a delta — no inventory restatements
  • Every blocker names a person, an action, and a date
  • Next is a dated milestone, verifiable next update
  • The skim layer stands alone in under 30 seconds

Anti-Patterns

  • Do not log activity — attended, discussed, and continued are not deltas
  • Do not hedge the state — 🟡 announced early is cheap; 🔴 discovered late is expensive
  • Do not post nameless blockers — unaddressed asks are the sender's fault after the first update
  • Do not write one essay for three audiences — flex the altitude or split the update
  • Do not skip the nothing-happened weeks — silence reads as chaos; "no movement, because X" reads as control

Version History

  • 471c606 Current 2026-07-22 13:12

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-hiring-panel/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-severance/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/agm-in-a-box/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/behavior-intervention-plan/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bennett-time-audit/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-game-designer/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md

Metadata

Files
0
Version
e4def4c
Hash
8b95beff
Indexed
2026-07-22 13:12

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-31 00:43
浙ICP备14020137号-1 $방문자$