delta-briefing

GitHub

用于生成周期性简报,聚焦于与上次的差异而非重复内容。通过对比新旧状态记录,输出变更摘要及机器可读的状态文件,确保后续版本仅展示实质性变化,避免信息冗余。

plugins/pm-autopilot/skills/delta-briefing/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

用户要求制作定期(如每周/每月)的更新报告 设置自动化监控或摘要 digest 现有简报出现内容重复时

Install

npx skills add mohitagw15856/pm-claude-skills --skill delta-briefing -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-autopilot/skills/delta-briefing -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@delta-briefing

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill delta-briefing -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": "delta-briefing",
    "description": "Make a recurring brief report what changed since the last edition instead of restating everything. Use when a weekly or monthly report keeps repeating itself, when setting up a scheduled monitor or digest, or when asked to make a recurring update delta-aware. Produces a changes-first brief plus the state record the next run will diff against."
}

Delta Briefing Skill

The failure mode of every recurring report is that edition 6 reads like edition 5. This skill structures a recurring brief around the delta: read the last edition's state, diff the world against it, lead with what changed, and save state for the next run.

What This Skill Produces

  • A changes-first brief: new / changed / resolved / unchanged-but-watched
  • A state record (compact, machine-readable) that the next edition diffs against
  • An explicit "nothing changed" edition format — short, honest, and still useful

Required Inputs

Ask for (if not already provided):

  • The brief's subject and audience (competitive landscape, product metrics, account health…)
  • The previous edition or state record — if none exists, this run is the baseline: say so in the output and produce the first state record
  • Current sources for this cycle
  • Where state lives between runs (a file next to the brief, a Brain folder — see BRAIN.md if using this library's memory)

Delta Method

  1. Load last state. Parse the previous state record (or previous edition if that's all there is). List the items it tracked and their status.
  2. Re-observe. Gather this cycle's facts from the sources — independently of the old state, so removals are caught too.
  3. Diff into four buckets:
    • New — present now, absent last time
    • Changed — tracked before, materially different now (state what moved, old → new)
    • Resolved / gone — tracked before, no longer present or no longer a concern
    • Watching — unchanged but still worth tracking (compressed to one line each)
  4. Judge materiality. A delta makes the brief only if the audience would act differently knowing it. Trivia goes to the state record, not the brief.
  5. Write state for next time. Every tracked item, its current status, the date, and the sources read.

Output Format

[Brief name] — [date] (edition [n], previous: [date])

TL;DR: [1-2 sentences: the most consequential delta, or "no material changes"]

New since last edition

  • [item] — [why it matters, one line]

Changed

  • [item]: [old] → [new] — [implication]

Resolved

  • [item] — [how it closed]

Still watching (one line each)

  • [item] — [status]
State record (for the next run)
{ "edition": n, "date": "YYYY-MM-DD", "sources": ["..."],
  "items": [ { "id": "...", "status": "...", "note": "..." } ] }

If nothing material changed: say exactly that in three lines — TL;DR ("no material changes"), what was checked, next edition date. Do not pad.

Quality Checks

  • The brief opens with the delta, not with background the audience read last time
  • Every "Changed" item shows both the old and the new value
  • Removals were checked by re-observing, not just re-confirming last edition's list
  • A state record exists at the end, complete enough that the next run needs no other memory
  • The baseline edition (no previous state) is labelled as a baseline, not presented as a delta

Anti-Patterns

  • Do not restate unchanged items at full length — one line in "Still watching" or nothing
  • Do not fabricate a delta to make a quiet cycle look productive — "nothing changed" is a valid, valuable edition
  • Do not diff against memory or vibes — only against the stored state record
  • Do not let the state record and the brief disagree — the record is written from the brief's facts
  • Do not track everything forever — items resolved two editions ago leave the state record

Version History

  • a38bc30 Current 2026-07-05 11:11

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-observability-spec/SKILL.md
exports/openclaw/agent-spec/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/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/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
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
66227a04
Indexed
2026-07-05 11:11

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 16:49
浙ICP备14020137号-1 $방문자$