claude

pm-teams

Multi-agent team presets for high-stakes decisions: validation sprint, PRD stress test, competitive war room.

0 on GitHubby Brianna Lyv0.1.0updated 3 months ago
/

Plugin pm-teams from marketplace pm-agent-team in BriannavLy/PM. Commands read from the repo's manifest — 1 month ago.

What it installs

Slash commands (3)

  • /pm-teams:prd-stress-test

    Three parallel reviewers score a PRD before it goes to engineering. Usage - /pm-teams:prd-stress-test path/to/prd.md. Verdict - READY / NEEDS REVISION / MAJOR REWORK.

  • /pm-teams:validation-sprint

    Multi-agent validation of a product idea. Usage - /pm-teams:validation-sprint "idea description". Verdict - BUILD / DON'T BUILD / NEEDS MORE EVIDENCE.

  • /pm-teams:war-room

    Parallel competitor deep-dives synthesized into positioning + battle cards. Usage - /pm-teams:war-room "Competitor A, Competitor B, Competitor C

Subagents (4)

  • competitor-researcher

    Team agent for competitive war rooms. Runs a deep-dive on ONE assigned competitor. Multiple instances run in parallel, one per competitor. - Read - Glob - Grep - WebSearch - WebFetch

  • idea-researcher

    Team agent for validation sprints. Builds the strongest evidence-based case FOR an idea - demand signals, analogous successes, feasibility. Always paired with idea-skeptic. - Read - Glob - Grep - WebSearch - WebFetch

  • idea-skeptic

    Team agent for validation sprints. Builds the strongest case AGAINST an idea - failure modes, dead competitors, adoption barriers, unit-economics problems. Always paired with idea-researcher. - Read - Glob - Grep - WebSearch - WebFetch

  • prd-reviewer

    Team agent for PRD stress tests. Reviews a PRD from ONE assigned lens - market-fit, feasibility, or scope. Three instances run in parallel with different lens assignments. - Read - Glob - Grep

View source on GitHub

More from BriannavLy/PM

All 2 plugins →

pm-core

claude

Core PM copilot: product-manager router + 8 specialist agents, 6 framework skills, setup commands.

11 skills · 11 commands · 10 agents

0

Similar plugins

plugin-dev

claude

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

anthropics/claude-code 155,476

ruflo-plugin-creator

claude

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

azure

claude

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

accessibility-compliance

claudecodex

WCAG accessibility auditing, compliance validation, UI testing for screen readers, keyboard navigation, and inclusive design

2 skills · 1 command · 1 agent

wshobson/agents 42,461

Render

claude

Deploy, debug, and monitor applications on Render: skills for blueprints, deploys and troubleshooting, a Render assistant agent, deploy/status commands, a render.yaml validation hook, and the Render MCP connector preconfigured over OAuth.

21 skills · 2 commands · 1 agent · 1 MCP server · hooks

anthropics/knowledge-work-plugins 35,601

agent-launcher-skills

claude

Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).

6 skills · 8 commands · 4 agents · hooks

alirezarezvani/claude-skills 29,725

Maintain pm-teams?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins