m3taz-ahmed/aizee / skills/bmad-agent-pm
bmad-agent-pm
UnverifiedJohn, the Product Manager. Use when the user asks for John, the PM or the product manager, wants a planning document written, updated or reviewed.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.9 KB |
| assets/pitch-view.html | other | 4.5 KB |
| assets/template-agent-spec.md | markdown | 2.6 KB |
| assets/template-business-case.md | markdown | 2.2 KB |
| assets/template-charter.md | markdown | 2.3 KB |
| assets/template-experiment.md | markdown | 3.3 KB |
| assets/template-launch.md | markdown | 2.1 KB |
| assets/template-narrative.md | markdown | 2.0 KB |
| assets/template-opportunity.md | markdown | 4.0 KB |
| assets/template-pitch.md | markdown | 2.7 KB |
| assets/template-prd-light.md | markdown | 2.8 KB |
| assets/template-prd.md | markdown | 10.2 KB |
| assets/template-prototype-plan.md | markdown | 4.5 KB |
| assets/template-srs.md | markdown | 2.8 KB |
| bmod.toml | config | 259 B |
| customize.toml | config | 3.0 KB |
| evals/triggers.json | config | 4.2 KB |
assets/template-pitch.md
View on GitHub---
title: ""
template: pitch
version: 1.1.0
description: "A shaped, time-boxed proposal for teams that bet fixed cycles."
not_for: "Open-ended requirements (`prd`); funding by estimate (`business-case`); one feature handed to a coding agent (`agent-spec`)."
paced: true
facilitation_order: [problem, appetite, solution, rabbit-holes, no-gos]
guidance: guidance-planning
rubric: rubric-planning
view: pitch-view.html
html_view: always
status: draft
created: ""
updated: ""
---
<!-- purpose: Propose shaped work so a betting table can commit a fixed cycle to it. -->
<!-- stance: Ask how much time the problem is worth, then shape the solution to fit it; never derive appetite from an estimate. -->
<!-- inputs: The raw idea and one specific story of the problem. Only the user knows the appetite: a small or big batch, in weeks. -->
<!-- writing: Rough, not wireframes, leaving design room for the builders. Appetite opens with the time in bold, such as `**Six weeks, big batch.**`; each rabbit hole and each no-go is one list item. The view lays the page out from that shape. -->
<!-- done when: A builder could start without asking what is in or out, and every known rabbit hole has a patch or a no-go. -->
# {title}
## Table of Contents
## Problem
<!-- One specific story that shows what is broken and for whom. Ask for the time it happened, to whom, and what it cost them; a general complaint gets a request for one real case. Keep solutions out of it. Done when the story alone would make the betting table care. -->
## Appetite
<!-- How much time this is worth and why. You are the betting table: ask what the problem is worth, never how long a solution would take, and refuse an appetite derived from an estimate. A small batch is one or two weeks, a big batch six. Done when the time is fixed and the user would cut scope before extending it. -->
## Solution
<!-- The main elements and how a user moves between them. Shape it to fit the appetite: at each element, ask whether it fits the time and what a rougher version would be. Fat-marker level, so builders keep design room. Done when the elements and their connections are clear and nothing finer is fixed. diagram: flowchart -->
## Rabbit holes
<!-- Risks that could blow the appetite, each with how it is patched or avoided. You are now the senior builder looking for what will eat the cycle: unknown technology, an edge case that grows, a dependency on another team. Name the ones the user has not; each gets a patch or moves to the no-gos. Done when no known risk is left open. -->
## No-gos
<!-- What is deliberately left out to fit the appetite. Name what a builder would assume is in and is not. Done when a builder could start without asking what is in or out. -->
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |