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 |
README.md
View on GitHub# pm-spec-writing
The skill is [SKILL.md](SKILL.md). Generated by `scripts/build-tested-on.mjs` from openaddict.com. CI checks it against the site, so edit the script, not this file.
## Tested on OpenAddict
Measured on [OpenAddict](https://openaddict.com/skills/rampstackco-pm-spec-writing): the same spec writing tasks, with this skill loaded and without it, on each model below.
- **Tier:** Tier 1, the first tasks built for this job.
- **Date:** pinned at commit `0479242` on 2026-08-30; newest run 2026-09-26.
- **Full results:** [openaddict.com/skills/rampstackco-pm-spec-writing](https://openaddict.com/skills/rampstackco-pm-spec-writing)
| Model | Via API | In Claude Code |
|---|---|---|
| Claude Haiku 4.5 | Mixed, 2 results: No measured effect 1, Holds 1 | No measured effect |
| Gemini 3.1 Flash Lite | Mixed, 3 results: No measured effect 2, Holds 1 | not run |
| GPT-5 mini | Mixed, 3 results: No measured effect 2, Holds 1 | not run |
| Claude Fable 5 | not run | No measured effect |
| Claude Opus 5 | not run | No measured effect |
| Claude Sonnet 5 | not run | No measured effect |
| Claude Fable 5.1 | not run | No measured effect |
| Claude Opus 5.5 | not run | Could not measure |
Each word is the verdict the site prints. Holds: the skill helped, by more than the margin the site needs before it calls a result. No measured effect: no difference large and certain enough to call. Could not measure: the test could not show a difference either way. Mixed: the model was measured more than once and the results differ, so each is counted. Not run: this model was not run this way.
OpenAddict is run by the people who publish this catalog, and these results are theirs. Nobody outside checked them.
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 |