Skill
Claude
PM: Scope-Disciplined Product Manager
pm/
2 views
0 downloads
A product manager for your agent team: build-ready PRDs with testable gates, a roadmap, brainstorming, standups and a single launch or no-launch verdict, with a scope guard that cites the spec.
The scope-disciplined product manager: plans the project, gates the launch, and says no.
Why use it
- Requirements that can't be tested, "the flow should feel smooth" is not a gate.
- Scope creep accepted one small ad-hoc ask at a time.
- "Looks ready" as a launch decision, with no scenario actually scored.
What it does
prd, turn the spec into a build-ready PRD: objectives, scope, out-of-scope guards, every success scenario mapped to a testable gate, the build plan.roadmap, own the docs/ roadmap: epics, user stories decomposed across the COMPLETE user-flow graph, milestones, and a machine-readable mirror.brainstorm, explore an idea with you before anything is specified: one question at a time, 2-3 approaches, a design you approve.acceptance, the terminal gate: every scenario PASS/FAIL with evidence, 100% end-to-end breadth, ONE binary LAUNCH / NO-LAUNCH verdict.standup, evidence-based Done / Next / Blockers, read-only.scope-guard, runs inside every mode: "is X in scope?" answered Yes/No with the spec section cited.
Benefits
- Requirements a machine can score. Testable gates, not adjectives.
- Scope creep stops here. Every "no" cites the spec and names the edit that would reverse it.
- No half-covered features. Stories map every path a user can take, not one happy path.
- Launch calls you can defend: one binary verdict, backed by per-scenario evidence.
- Retarget it in one file. Nothing about your product is baked in.
Install
Download this skill and copy the pm folder to .claude/skills/pm/ in your project, or to ~/.claude/skills/pm/ to use it in every project. Claude Code finds it on its own; you can also call it with /pm.
Part of the Agent Engineering bundle. To get the whole set as a Claude Code plugin: /plugin marketplace add endorphin-ai/hasbrains-agent-kit, then /plugin install agent-engineering@hasbrains-agent-kit.
Source: endorphin-ai/hasbrains-agent-kit. License: MIT.
Files (19)
Files
{
"skill": "pm",
"entry": "SKILL.md",
"description": "Master navigation map. Load SKILL.md + this file to orient, then open ONLY the one note the task needs.",
"notes": [
{
"id": "prd",
"kind": "workflow",
"path": "workflows/prd.md",
"title": "PRD Authoring Playbook",
"summary": "Read the spec, write objectives + scope-in, reproduce the out-of-scope wall, map EVERY success scenario to a testable gate copied 1:1 + its build phase, list the launch-blockers, write the build plan, run the scope pass, then create the work items in order (epic -> PRD -> stories) and hand off LAST.",
"tags": ["pm/prd", "pm/workflow"],
"load_when": "Authoring or updating the PRD from the spec or a user request.",
"links": ["roadmap", "scope-guard", "acceptance", "brainstorm"]
},
{
"id": "roadmap",
"kind": "workflow",
"path": "workflows/roadmap.md",
"title": "docs/ Roadmap Playbook",
"summary": "Own the roadmap as committed markdown: epic(s) per milestone, user stories decomposed across the COMPLETE flow graph (dependency chain + full entity lifecycle x every access state) and linked to their epic, the PRD, tasks, milestones, then regenerate + commit the roadmap mirror.",
"tags": ["pm/roadmap", "pm/workflow"],
"load_when": "Creating or refreshing the roadmap and its machine-readable mirror.",
"links": ["prd", "roadmap-json", "acceptance"]
},
{
"id": "brainstorm",
"kind": "workflow",
"path": "workflows/brainstorm.md",
"title": "Brainstorm / Idea-Exploration Playbook",
"summary": "Pre-PRD exploration WITH the user: load the brainstorming skill, ground in the project config + spec, ask ONE question at a time, propose 2-3 approaches with a recommendation, present a design, get approval. Read/think-only, scope wall still applies.",
"tags": ["pm/brainstorm", "pm/workflow"],
"load_when": "Shaping an idea or exploring options before any PRD exists.",
"links": ["prd", "scope-guard"]
},
{
"id": "acceptance",
"kind": "workflow",
"path": "workflows/acceptance.md",
"title": "Final Acceptance Sign-Off Playbook",
"summary": "The terminal gate: score EVERY success scenario PASS/FAIL with evidence, check every launch-blocker, verify 100% end-to-end breadth (every story = a dedicated passing test), compile blockers, emit ONE binary verdict, organize the docs/ folder (stale statuses, follow-ups), refresh + commit the roadmap mirror.",
"tags": ["pm/acceptance", "pm/workflow"],
"load_when": "The build is delivered and needs the final pass/fail sign-off.",
"links": ["prd", "scope-guard", "roadmap-json"]
},
{
"id": "standup",
"kind": "workflow",
"path": "workflows/standup.md",
"title": "On-Demand Standup Playbook",
"summary": "Evidence-based Done/Last, Next/Plan, Blockers. Roadmap mirror FIRST, live scan only when stale; test/CI numbers recency-reconciled most-recent-wins with timestamp/environment/commit. Read-only.",
"tags": ["pm/standup", "pm/workflow"],
"load_when": "Any on-demand status read.",
"links": ["standup-data-sources", "roadmap-json"]
},
{
"id": "scope-guard",
"kind": "workflow",
"path": "workflows/scope-guard.md",
"title": "Scope Guard Playbook",
"summary": "The continuous 'is X in scope?' check that runs INSIDE every mode: restate the request, check the out-of-scope list, check the declared business model, check the in-scope + launch-blocking sections, emit '<Yes|No> - <spec section>.' and name the spec edit that would reverse a No.",
"tags": ["pm/scope", "pm/workflow"],
"load_when": "Any request, feature idea, or proposal needs a scope ruling.",
"links": ["prd", "acceptance"]
},
{
"id": "roadmap-json",
"kind": "reference",
"path": "references/roadmap-json.md",
"title": "The Roadmap Mirror — docs/roadmap.json (PM-owned)",
"summary": "The machine-readable mirror of the docs/ roadmap: what it holds (every work item + status, milestones past/current/next, summary counts), the concrete schema, the one refresh moment (the acceptance gate), and the staleness rule.",
"tags": ["pm/roadmap", "pm/state"],
"load_when": "Reading or rebuilding the roadmap mirror, or judging whether the snapshot is stale.",
"links": ["standup", "standup-data-sources", "roadmap", "acceptance"]
},
{
"id": "standup-data-sources",
"kind": "reference",
"path": "references/standup-data-sources.md",
"title": "Standup — parts, data sources, and recency reconciliation",
"summary": "The three standup parts and what each pulls from, the priority-ordered data sources (mirror first, live scan last), and the most-recent-wins reconciliation for test/CI numbers by timestamp/environment/commit.",
"tags": ["pm/standup", "pm/state"],
"load_when": "Producing a standup, or deciding which test/CI status is current.",
"links": ["standup", "roadmap-json"]
}
]
}