- Home
- Skills
- Business & Operations
- PM Playbook
PM Playbook
A rigorous PM framework for opportunity scoring, one-page PRDs, roadmap sequencing, and GTM strategy.
$5
Works with the AI Agents you already use
PM Playbook
Example session with this skill installed
Evaluate an idea for a 'Magic Undo' button for deleted emails. Users keep accidentally deleting threads. Targeting busy professionals. We need to know if we should build it.
- Read your context and instructions
- Compiled the pm playbook
I have evaluated the 'Magic Undo' feature using the Stage 1 Opportunity Assessment framework. Based on the Switch Cost and Pain Depth, this scores a 14/25, which clears the threshold for development.
Opportunity Assessment: Magic Undo Button
| Lens | Score (1-5) | Rationale |
|---|---|---|
| Pain Depth Gauge | 4 | 65% of surveyed users report "accidental deletion" once per week. |
| Switch Cost Meter | 1 | Zero friction; it is a native UI addition requiring no new habit. |
| Wedge Test | 3 | Can evolve into a broader "Action History" suite. |
| Trend Window | 2 | Stable need; not rising, but a persistent UX debt item. |
| Gap Spotter | 4 | Current "Trash" folder recovery takes 4+ clicks; this takes 1. |
| Market Pull Score | 14 | Result: Pursue (Score > 12) |
Assumptions
- We assume the undo window is 10 seconds, matching standard web patterns.
- We assume backend latency for "soft deletes" is under 200ms.
Quantitative Targets
- Reduce "Trash folder visits per user" by 40% within 30 days.
- Target a 98% success rate for undo actions triggered within the 10-second window.
Trade-offs
Latency vs. Safety: Implementing a buffer adds a slight delay to immediate deletion, which may confuse power users who want instant cleanup.
*
UI Real Estate: Adding an "Undo" snackbar consumes bottom-screen space on mobile, potentially obscuring navigation for 3 seconds post-action.
Next steps
- Run
scripts/prd_scaffold.pyto generate the formal one-page PRD. - Define the exact "Scope Fence" for which folders (Inbox vs. Archive) support Undo.
- Select the "Beachhead Picker" group for a closed beta.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Vague product requirements lead to scope creep and missed deadlines. Product managers often struggle to quantify the impact of features or clearly communicate the trade-offs of their roadmap decisions.
What it does
- Evaluates new ideas using a weighted Market Pull Score to determine if a concept is worth pursuing.
- Generates concise, one-page PRDs that explicitly define scope fences and success metrics.
- Sequences roadmaps using a value-minus-effort calculation across Now, Next, and Later horizons.
- Constructs go-to-market plans focused on beachhead audiences and message spines.
- Builds post-launch signal dashboards to track retention, churn, and North Star metrics.
Why this beats prompting it yourself
General LLM prompts often produce "fluff" or generic business speak. This skill enforces a strict output discipline that requires every response to state assumptions, use concrete numbers, and name specific trade-offs, ensuring rigorous thinking rather than just text generation.
Use cases
- Writing a tight PRD for a new mobile search feature with clear in/out scope boundaries.
- Scoring three competing product ideas to see which one clears the Market Pull threshold.
- Planning a quarterly roadmap that accounts for team capacity and dependency webs.
- Designing a go-to-market strategy for a niche beachhead audience.
Known limitations
Requires a local Python environment to run the PRD scaffolding script. The PRD framework is strictly limited to one-page outputs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Requires python3 to run the prd_scaffold.py script. All requirement cards are strictly capped at one page.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected