rampstackco/claude-skills / skills/pm-spec-writing
pm-spec-writing
VerifiedTranslate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.7 KB |
| SKILL.md | skill md | 8.7 KB |
| references/dev-brief-template.md | markdown | 6.0 KB |
| references/feature-spec-template.md | markdown | 4.6 KB |
| references/prioritization-frameworks.md | markdown | 6.7 KB |
references/feature-spec-template.md
View on GitHub# Feature Spec: [Feature Name]
**Author:** [Name]
**Date:** [YYYY-MM-DD]
**Status:** [Draft / In Review / Approved / In Development / Shipped]
**Target ship:** [Date or sprint]
---
## TL;DR
[2 to 3 sentences. What this is, who it's for, why it matters. If a stakeholder reads only this section, they should understand the proposal.]
---
## Problem
[1 to 2 paragraphs. The user problem. The current state and why it's inadequate. Include data if available (analytics, support tickets, user research quotes).]
### Evidence
- [Specific data point or research finding]
- [Specific data point or research finding]
- [Specific data point or research finding]
---
## Users
**Primary user:** [Specific user segment that benefits most]
**Use cases:**
1. [Specific scenario where this user encounters the problem]
2. [Specific scenario]
3. [Specific scenario]
**Secondary users:** [Other segments affected]
**Anti-users:** [Segments this feature is NOT for; helps prevent scope creep]
---
## Proposal
[1 paragraph at the conceptual level. The solution, not the implementation. Stay at "what" not "how".]
### How it works (high level)
[3 to 5 bullets describing the user experience flow. Still high level; not implementation details.]
1. [User action]
2. [System response]
3. [User action]
4. [System response]
---
## User stories
- As a [user type], I want to [action], so that [outcome].
- As a [user type], I want to [action], so that [outcome].
- As a [user type], I want to [action], so that [outcome].
---
## Acceptance criteria
The feature ships when ALL of these are true.
- [ ] **Given** [context], **when** [action], **then** [expected outcome]
- [ ] **Given** [context], **when** [action], **then** [expected outcome]
- [ ] **Given** [context], **when** [action], **then** [expected outcome]
- [ ] [Additional criteria]
- [ ] [Additional criteria]
Each criterion must be observable and testable. If you cannot verify it with a specific check, rewrite it.
---
## Out of scope
[Explicit boundaries. What this spec does NOT cover. Critical for scope control.]
- [Thing explicitly not included, with reason]
- [Thing explicitly not included, with reason]
- [Thing explicitly not included, with reason]
---
## Dependencies
### Required before development can start
- [ ] [Design completed and approved]
- [ ] [API contracts defined]
- [ ] [Content delivered]
- [ ] [Legal/compliance review if applicable]
### External systems or services
- [System or service]: [What we depend on]
- [System or service]: [What we depend on]
### Team dependencies
- Design: [What's needed and who owns it]
- Engineering: [Specific resources and timeline]
- Content: [If applicable]
- Marketing: [If launch-related]
---
## Success metric
**Primary metric:** [The one metric that tells us this worked]
**Current baseline:** [If known]
**Target:** [What success looks like quantitatively]
**Measurement window:** [When and for how long we measure]
**Secondary metrics (signals to watch):**
- [Metric] - [why it matters]
- [Metric] - [why it matters]
**Negative signals (what would tell us this hurt):**
- [Metric] - [threshold for concern]
- [Metric] - [threshold for concern]
---
## Estimated effort
**Size:** [Small (hours) / Medium (1-3 days) / Large (1-2 weeks) / XL (multiple sprints)]
**Breakdown:**
- Design: [hours/days]
- Frontend: [hours/days]
- Backend: [hours/days]
- QA: [hours/days]
- Content: [hours/days]
- Total: [estimated]
---
## Priority
**P0** Launch blocker - must ship before [event/launch]
**P1** Next sprint - high impact, addressable now
**P2** Within quarter - valuable but not urgent
**P3** Backlog - nice-to-have, no commitment
**This spec:** [P0 / P1 / P2 / P3]
**Reasoning:** [Why this priority]
---
## Open questions
[Things that need to be decided before development can start, or before the feature can ship.]
- [ ] [Question] - **Owner:** [Who decides] - **Decision needed by:** [Date]
- [ ] [Question] - **Owner:** [Who decides] - **Decision needed by:** [Date]
---
## Risks and mitigations
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| [Risk description] | High/Med/Low | High/Med/Low | [How we'll mitigate] |
| [Risk description] | | | |
---
## Smallest shippable increment
**MVP:** What is the simplest version that delivers user value?
[Description of the MVP. Shippable in 1 to 2 weeks for most features. If you can't describe an MVP that fits, the feature is too big and should be split.]
**Future iterations** (NOT in MVP, may come later):
- [Iteration 1]
- [Iteration 2]
- [Iteration 3]
---
## Changelog
| Date | Author | Change |
|---|---|---|
| YYYY-MM-DD | [Name] | Initial draft |
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: 471k | Updated | Claude CodeCodex | Verified | 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 |