Pm Weekly ReviewCAUTION

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: pm-weekly-review
description: "Structure a PM's weekly review and planning session. Use when doing a weekly PM review, writing a weekly update, preparing for Monday planning, or reviewing sprint health. Produces a shareable weekly update covering metrics movement, shipping progress, blockers, insights, and next week's top 3 priorities."
---

# PM Weekly Review Skill

Turn the chaotic end-of-week brain dump into a structured 20-minute ritual that keeps you, your team, and your stakeholders aligned — without a meeting.

> **Not quite this?** Use `weekly-review-ritual` when you want a personal GTD-style weekly review rather than a product review.

## The Weekly Review Structure (20 minutes)

**5 min — Metrics check:** What moved? What didn't? What's surprising?
**5 min — Ship progress:** What shipped? What slipped? What's blocked?
**5 min — Insights:** Any customer feedback, support tickets, or research findings?
**5 min — Next week priorities:** What are the 3 things that matter most?

---

## Output Format

### PM Weekly Review — Week of [Date]

**Product Area:** [What you own]
**Written by:** [PM Name]
**Time to read:** ~3 minutes

---

### 📊 Metrics This Week

| Metric | This Week | Last Week | Target | Trend |
|---|---|---|---|---|
| [Primary metric] | [Value] | [Value] | [Target] | ↑ / ↓ / → |
| [Secondary metric] | [Value] | [Value] | [Target] | ↑ / ↓ / → |
| [Health metric] | [Value] | [Value] | [Target] | ↑ / ↓ / → |

**Notable movement:**
- [What changed and why — 1 sentence each]

**Concern to watch:**
- [Anything trending in the wrong direction]

---

### 🚢 This Week's Progress

**Shipped:**
- ✅ [What went live] — [1-line impact or observation]

**In Progress:**
- 🔄 [Feature/initiative] — [% complete or current status]

**Slipped / Blocked:**
- ⚠️ [What didn't happen] — Reason: [brief] — Action: [who's unblocking it]

**Carry-forward to next week:**
- [Item + why it's carrying over]

---

### 💡 Insights & Signals

**Customer feedback:**
- "[Quote or paraphrase]" — Source: [user/channel] — Theme: [tag]

**Support signals:**
- [Top ticket category this week + volume]
- [Anything that signals a product gap]

**Research / data:**
- [Any discovery from user interviews, analytics, or experiments]

---

### 🎯 Next Week — Top 3 Priorities

| # | Priority | Why This Week | Owner | Done = |
|---|---|---|---|---|
| 1 | [Most important thing] | [Reason it can't wait] | [Name] | [Clear definition of done] |
| 2 | [Second priority] | [Why] | [Name] | [Done criteria] |
| 3 | [Third priority] | [Why] | [Name] | [Done criteria] |

**Decisions needed:**
- [Any decision that's blocking progress — who needs to make it]

**Asks / dependencies:**
- [What you need from engineering / design / data / leadership]

---

### 🧠 Reflection (Optional but powerful)

> What's one thing from this week I'd do differently?
> [Your honest answer — 1–2 sentences]

> What's the biggest unknown I'm carrying into next week?
> [Name the uncertainty explicitly]

---

## Required Inputs

Work from what is given. If any of these is missing, still produce the complete output: fill each gap with a reasonable assumption marked *(assumed, confirm)* and list those assumptions at the end. Ask a question first only when the core subject itself is missing (there is nothing to write about).
- **Product area or team** you own
- **Key metrics this week** (with values and prior week comparison)
- **What shipped, slipped, or is blocked**
- **Top 3 priorities for next week**
- **Any customer insights or signals** (optional)

## Quality Checks

- [ ] Metrics include period-over-period comparison (not just raw numbers)
- [ ] Every blocked item has an owner and a specific unblocking action
- [ ] Next week's priorities have a "why this week" rationale
- [ ] Total length is under 400 words (skimmable in 3 minutes)
- [ ] Reflection section is honest, not aspirational

## Anti-Patterns

- [ ] Do not report metrics without comparing to target or the prior week — absolute numbers without context are not useful
- [ ] Do not list blockers without a named owner and proposed resolution — unowned blockers stay blocked
- [ ] Do not write a weekly review that is longer than one page — it must be scannable in under 2 minutes
- [ ] Do not include more than 3 priorities for next week — a list of 8 "top priorities" means nothing is prioritised
- [ ] Do not skip the insights section — observations that inform future decisions are a PM's key value add

## Guidelines

- Keep the whole document under 400 words — if stakeholders won't read it, it doesn't exist
- The reflection section is for you, not your stakeholders — keep it honest
- Always name a clear owner for every blocked item — "the team will figure it out" is a blocker in disguise
- Recommend sending this by end of Friday — Monday morning is too late to course-correct
- If three weeks of weekly reviews show the same blocked item, escalate immediately

## Example Trigger Phrases

- "Doing a weekly PM review."
- "Write a weekly update."
- "Prepare for Monday planning."
- "Review sprint health."

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (5)

templates/pm-discovery-agent/skills/assumption-mapper/SKILL.md

templates/pm-discovery-agent/skills/discovery-interview-guide/SKILL.md

templates/pm-discovery-agent/skills/job-story-mapper/SKILL.md

templates/pm-discovery-agent/skills/user-interview-synthesis/SKILL.md

templates/pm-launch-agent/skills/content-calendar/SKILL.md

Gates applied: no_behavioural_pass.