菜单
Entry point for the decision toolkit. Routes to the right decision skill based on your situation. Use when you say 'decision', 'help me decide', 'should I', 'which option', 'what are my choices', 'what could go wrong', 'is this reversible', or want decision help without knowing which specific tool fits.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/TuYv/ccpm --skill s4h-decision命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分
Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. 广告创意/广告文案/RSA标题
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
基于 SOC 职业分类
正在显示 SKILL.md
| name | s4h-decision |
| description | Entry point for the decision toolkit. Routes to the right decision skill based on your situation. Use when you say 'decision', 'help me decide', 'should I', 'which option', 'what are my choices', 'what could go wrong', 'is this reversible', or want decision help without knowing which specific tool fits. |
Applies structured decision thinking to any choice. Diagnoses what kind of decision work is needed and applies the right tool.
| You need to... | Tool |
|---|---|
| Make sure you're seeing all the real options | option-mapping |
| Compare options against weighted criteria | criteria-weighting |
| Stress-test a decision by imagining it failed | premortem-analysis |
| Calibrate how much process this decision deserves | reversibility-analysis |
Framing check: Confirm the decision and its intended outcome before routing. State what you've identified — the actual choice being faced and what the user is trying to achieve — in one sentence, then use AskUserQuestion:
Question: "I'm reading this as: [your one-sentence framing of the specific decision and its intended outcome]. Is that right?"
Header: "Framing"
Options:
About to decide between 2 options — may be missing others → option-mapping first
Options are visible, need to compare them systematically → criteria-weighting
Leaning toward a direction, want to stress-test it → premortem-analysis
Unsure how much time to spend on this decision → reversibility-analysis
Unclear → option-mapping; the option space is almost always narrower than it should be
After diagnosing which tool fits, use the AskUserQuestion tool to confirm direction. Construct the question dynamically to include your diagnosis:
Proceed based on their selection.
Ensures all real options are visible before choosing.
Counter the false dichotomy: the first two options that come to mind are rarely all that exists. Generate options across three levels: (1) direct solutions to the stated problem, (2) alternative framings of the problem that suggest different solutions, (3) options that combine or transcend the initial set. Apply the deliberate quota: find at least 5 options. Don't evaluate until the inventory is complete.
Output: Option inventory (5+ minimum), including options that reframe the problem, with brief descriptions. No evaluation yet — just the full map.
Runs a weighted multi-criteria analysis.
Step 1: List what actually matters for this decision. Step 2: Weight each criterion by importance (1-5 scale). Step 3: Score each option on each criterion (1-5). Step 4: Calculate weighted scores. Step 5: Check the winner against intuition — if the numbers say X but your gut says Y, that gap is information worth understanding, not a flaw in the method.
Output: Weighted decision matrix, ranked options, and an interpretation of whether the quantitative result matches or challenges intuition.
Imagines the decision was made and failed — then diagnoses why.
Set the scene: it's 12 months from now. The decision was made, and it failed badly. Write the failure story: what went wrong? Be specific — not "it didn't work" but the actual mechanism of failure. Generate 5+ distinct failure paths. Now: which failure modes are most probable? Which are most damaging if they occur? Which can be mitigated before committing?
Output: 5+ failure paths, ranked by probability and severity. For each high-priority failure mode: the mitigation that reduces it. The adjusted decision recommendation.
Categorises a decision by reversibility to apply the right level of process.
Two-way door decisions (easily reversible) should be made quickly with less process — the cost of deliberating exceeds the cost of being wrong. One-way door decisions (hard or impossible to reverse) deserve thorough analysis. Classify this decision: what would it take to undo it? How quickly? At what cost? Many decisions that feel irreversible aren't. Many that feel casual are more binding than they appear.
Output: Decision classification (reversibility score 1-5), what undoing it would require, and the recommended level of process given that classification.