Agent Skillsmohitagw15856/pm-claude-skills › decision-log-setup

decision-log-setup

GitHub

用于建立团队决策日志以终结重复争论。提供单行记录格式、基于现有仪式的捕获机制、重开规则及检索习惯,确保决策可追溯且高效。

skills/decision-log-setup/SKILL.md mohitagw15856/pm-claude-skills

触发场景

设置决策日志 团队反复重议相同决策 询问决策记录位置 新成员质疑现有做法原因

安装

npx skills add mohitagw15856/pm-claude-skills --skill decision-log-setup -g -y
更多选项

不安装直接使用

npx skills use mohitagw15856/pm-claude-skills@decision-log-setup

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill decision-log-setup -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": "decision-log-setup",
    "description": "Set up the team decision log that ends relitigation — the one-line-per-decision format (what, why, who, when, reopening rule), the capture moments wired into existing rituals, and the lookup habit that makes it pay. Use when asked set up a decision log, we keep re-deciding the same things, where do decisions get recorded, or new people keep asking why we do X. Produces the log format, the capture wiring, the reopening rule, and the retrieval habits."
}

Decision Log Setup Skill

Teams re-decide because decisions evaporate: made in a meeting, mentioned in a thread, remembered differently by everyone, and relitigated the moment someone new (or someone persistent) asks "wait, why do we…?" The decision log is the cheapest institutional memory there is — one line per decision (what, why, who, when, and the reopening rule) — but logs fail as shelf-ware unless capture is wired into existing moments (the meeting's last five minutes, the thread's landing) and retrieval becomes reflex ("checked the log?" as the first response to why-questions).

What This Skill Produces

  • The format — the five-field line, with the two-sentence-why discipline and the option-we-rejected field that does the anti-relitigation work
  • The capture wiring — the existing moments (decision-meeting-format closes, thread-to-decision landings, 1:1 calls) that now end with a log line
  • The reopening rule — what reopens a decision (new information) and what doesn't (new mood, new people)
  • The retrieval habits — the log-first reflex, the onboarding tour, the link-not-relitigate response

Required Inputs

Ask for these if not provided:

  • Where decisions currently happen — the meetings, threads, and hallways; capture wires into real venues, and unwired venues keep leaking
  • The platform — a doc, a wiki page, a database/table; sortable-and-searchable beats beautiful, and the log lives where the team already looks
  • The scope line — which decisions get logged (the test: would someone plausibly ask "why" in six months?) vs. the operational micro-calls that don't; over-logging kills the habit as surely as under-logging kills the value
  • The relitigation history — the decisions that keep reopening; they get back-filled first, because they're the demonstration

Framework: The Log Rules

  1. The line is five fields and stays a line: date · decision (one sentence, the what) · why (two sentences max, including the rejected alternative: "chose X over Y because Z") · decider · reopening trigger. The rejected-alternative clause is the anti-relitigation payload — "we considered that and here's why not" is the sentence that ends the third rehash.
  2. Capture rides existing rituals: the decision meeting's on-screen close writes the line · the thread landing's record is the line · the weekly's "any decisions this week?" sweeps the strays. New ceremony fails; hitching to existing ceremony sticks. One person per venue owns the write (the facilitator, the thread-lander).
  3. The reopening rule is stated per decision: default — "reopens on new information, not new preferences" — with specific triggers where known ("revisit if churn exceeds X"). This converts "can we talk about this again?" from a social negotiation into a rule lookup, which is the log's quiet superpower.
  4. Retrieval is the ROI moment: the why-question response becomes a link ("logged here — short version: chose X over Y for Z"), the onboarding tour includes the log's greatest hits, and decisions cite prior decisions ("consistent with #47"). A log that's written but never linked is a diary; the link habit is what compounds.
  5. Back-fill the greatest hits only: the 10–15 decisions people actually re-ask about get retro-logged (best-effort whys, marked as reconstructed) — full historical back-fill is archaeology that delays the living log. Forward capture from today; history only where it's actively bleeding.

Output Format

Decision Log: [team] — lives at [location]

The Format

Date Decision Why (incl. rejected alt.) Decider Reopens if

Capture Wiring

[Venue → moment → who writes the line · the weekly sweep as the catch-all]

The Reopening Rule

[The default · how specific triggers get set · the link-instead-of-debate response]

Retrieval Habits

[The why-question → link reflex · onboarding's greatest-hits tour · the back-fill list (10–15, marked reconstructed)]

Quality Checks

  • Every field fits the one-line discipline; whys include the rejected alternative
  • Capture is attached to named existing moments with named writers
  • The reopening default is stated and per-decision triggers are possible
  • The link-first response habit has been demonstrated on a real why-question
  • Back-fill stopped at the greatest hits

Anti-Patterns

  • Do not log without the rejected alternative — "we chose X" without "over Y because Z" relitigates fine
  • Do not build capture as new ceremony — hitch to rituals that already happen
  • Do not log everything — the six-month-why test keeps the log readable and the habit light
  • Do not let new-people-energy reopen settled calls — the rule distinguishes information from mood
  • Do not write and never link — retrieval is where the log earns; capture alone is journaling

版本历史

  • 471c606 当前 2026-07-22 14:46

同 Skill 集合

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

元信息

文件数
0
版本
471c606
Hash
b920826a
收录时间
2026-07-22 14:46

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 00:51
浙ICP备14020137号-1 $访客地图$