JPeetz/agent-skills / skills/business-strategy/product-manager-toolkit
product-manager-toolkit
VerifiedUse this skill when performing product management tasks like prioritizing features, synthesizing customer interviews, writing PRDs, setting OKRs, or managing stakeholder communication. Activates on "product management", "PM toolkit", "prioritization", "RICE", "PRD", "feature prioritization", "customer interview", "OKR planning", "stakeholder update", or "roadmap planning". Covers RICE prioritization, customer interview synthesis, PRD authoring, OKR setting with leading/lagging indicators, stakeholder communication templates, and decision frameworks.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 2.0 KB |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 17.2 KB |
| evals/evals.json | config | 8.0 KB |
| references/sources.md | markdown | 5.4 KB |
| scripts/rice_scorer.py | script | 8.2 KB |
CHANGELOG.md
View on GitHub# Changelog
All notable changes to this skill are documented here. Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), versioning follows [SemVer](https://semver.org/).
## [1.0.0] — 2026-11-14
### Added
- `SKILL.md` — five core workflows: RICE prioritization, customer interview synthesis, PRD authoring, OKR design, and decision frameworks. Each section ends in a decision artifact, not a template dump.
- `scripts/rice_scorer.py` — stdlib-only RICE calculator. Reads a JSON file or stdin, validates every input (impact must be one of the five canonical multipliers, confidence accepts 0–1 or 0–100, effort must be > 0, duplicate names rejected), and emits a ranked markdown table or JSON. Flags low-confidence items (`≤50%`, treated as research not build) and effort outliers (>3× median or median+5). The score is never silently altered by a flag — flags annotate, they do not reorder.
- `references/sources.md` — provenance for RICE, JTBD, Ulwick opportunity scoring, DACI, DARE, and OKR practice, plus a reading list and a note on which thresholds are heuristics.
- `evals/evals.json` — four positive scenarios (RICE ranking with an override, interview synthesis, PRD with a missing kill criterion, OKR output-vs-outcome test) and two negative scenarios (out-of-scope routing).
- `LICENSE` — MIT.
### Design notes
- RICE section enforces absolute reach and a single effort unit; both are the most common ways the score gets quietly gamed.
- Interview synthesis requires a participant count per theme and a counter-evidence section, so the output cannot drift into confirmation.
- PRD template mandates a named "won't have" list and kill criteria — the two sections whose absence causes scope creep.
- OKR section separates leading from lagging KRs and requires a baseline before a target, with output KRs explicitly banned.
- Decision frameworks are selected by the shape of the decision (many comparable candidates → RICE; one accountable human → DACI; 2–4 contested options → DARE; survey data → opportunity scoring).
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 | 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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |