pmlisted

The pm-agent-os orchestrator. Use when the user invokes /pm or hands over any product-management request — synthesizing interviews, mining feedback, mapping assumptions, tearing down a competitor, sizing an opportunity, framing jobs-to-be-done, planning research, or any multi-step product task spanning discovery, strategy, build, launch, or iterate. Classifies the request into lifecycle stage(s), invokes the matching stage skills in sequence, and blocks every output whose verification gate has not passed. Also use when the user asks to run any output past a reviewer persona — 'review as engineer/designer/executive/skeptic/customer/data-analyst/legal' — routing to the persona agents in .claude/agents/. Do NOT use for coding tasks, repo maintenance, PR reviews (/pr-review's job), or knowledge questions about PM concepts with no work item attached.
Abhillashjadhav/PM-agent-OS · ★ 1 · AI & Automation · score 60

Install: claude install-skill Abhillashjadhav/PM-agent-OS

# /pm — Orchestrator Route → execute → verify → return. Nothing reaches the user unverified. ## The one hard rule above all others **No output returns to the user until its verification gate passes.** Every stage skill defines binary gates in its own SKILL.md. The orchestrator runs them (or confirms the skill ran them) before relaying anything. A gate failure triggers repair, not delivery. ## Stage routing table | Stage | Status | Skills | |---|---|---| | Discovery | **Shipped** | interview-synthesizer · feedback-pattern-miner · assumption-mapper · competitor-teardown · opportunity-sizer · jtbd-framer · research-brief (all under `.claude/skills/<name>/SKILL.md`) | | Strategy | **Shipped** | strategy-review · roadmap-reality-check · ai-feature-go-no-go · north-star-designer · build-buy-partner · pricing-tradeoff | | Build | **Shipped** | model-complexity-router · builder-validator · prompt-optimizer-loop · context-auditor · pm-context-system · prd-to-eval · prototype-first-workflow · rag-vs-agent-architect · latency-ux-tradeoff · unit-economics-stress-test | | Launch | **Shipped** | launch-checklist · gtm-brief · stakeholder-update · announcement-drafter · launch-retro (+ 7 reviewer personas in `.claude/agents/`) | | Iterate | **Shipped** | eval-engine · llm-as-judge-designer · judge-calibration-auditor · golden-dataset-builder · failure-to-eval-capture · guardrail-designer · loop-designer · regression-gatekeeper · model-upgrade-evaluator · eval-vs-abtest-router · drift-m