Thirteen product management skills and four chained workflow agents for PM workflows
End-to-end research-to-spec workflow. Takes raw user research and produces a complete Feature Request with persona context — running synthesize-user-research, build-user-persona, and write-feature-request in sequence. Use when you have research data and want to go straight to a finished FR without managing each skill separately. Trigger on: "run discovery-to-fr", "turn my research into a feature request", "I have interview notes and need a feature spec", "go from research to FR", "full discovery pipeline".
Feature-request-to-dev-ready workflow. Takes a raw feature idea or existing FR through authoring, AC verification, and engineering handoff — running write-feature-request, verify-acceptance-criteria, and write-technical-brief in sequence. Use when you want a complete, dev-ready handoff package in one session. Trigger on: "run fr-to-ready", "make this FR dev-ready", "I need a complete handoff package for this feature", "get this feature ready for engineering", "full FR pipeline".
Full sprint-to-communications workflow. Takes sprint data and produces all three stakeholder artefacts — running sprint-review, write-release-notes, and write-stakeholder-update in sequence. Use at the end of every sprint to produce the complete communication package in one run. Trigger on: "run sprint-to-stakeholders", "generate all my sprint comms", "write everything I need for end of sprint", "produce the full sprint communication package", "sprint comms pipeline".
Full strategy-to-execution workflow. Takes product context through strategy, OKRs, and roadmap — running write-product-strategy, write-okrs, and write-roadmap in sequence to produce three aligned planning documents. Use at the start of a planning cycle when you want all three artefacts built and aligned in one session. Trigger on: "run strategy-to-roadmap", "help me build our strategy and roadmap", "I need a full planning cycle", "take me from strategy to execution plan", "full strategy pipeline".
Build evidence-backed user personas from research inputs. Creates structured persona documents grounded in evidence, with each attribute clearly labeled as research-validated or inferred. Use this skill when you need personas for an FR, strategy doc, or design brief. Trigger on: "build a persona", "create user personas from this research", "who are our users", "describe our target user", "make a persona for [segment]", or when synthesised research is ready and needs a persona layer.
Structure a competitive landscape analysis — player profiles, capability comparison matrix, whitespace opportunities, and strategic implications. Use this skill when entering a new market, refreshing strategy, or preparing for a planning cycle. Trigger on: "do a competitive analysis", "who are our competitors", "compare us to X and Y", "what's the competitive landscape for [space]", "where is there whitespace in the market", "how do we stack up against [competitor]".
Score and rank a list of features or initiatives using RICE by default. Scans existing strategy and OKRs to ground Impact scores in what the team is actually optimizing for. Use when deciding what to build next, preparing for planning, or presenting a ranked backlog to stakeholders. Accepts a pasted list, FR filenames, or a mix of both. Supports RICE (default), Agentic RICE (for AI-delegated work), ICE, and MoSCoW as alternative frameworks.
Generate a professional sprint review report for stakeholders — PMs, leadership, and cross-functional teams. Use this skill whenever a user wants to write up a sprint, summarize what the team shipped, produce a sprint retrospective document, recap what was completed in an iteration, or create a sprint summary for leadership. Triggers include: "write my sprint review", "generate a sprint recap", "create a sprint report", "summarize what we shipped this sprint", "help me write up our sprint for stakeholders", or any mention of sprint outcomes, velocity reports, or iteration summaries — even if they don't use the word "skill" or "report". Also trigger when a user pastes a list of tickets/tasks and asks for a write-up or summary.
Synthesize raw user research (interview notes, survey results, support tickets, NPS verbatims) into structured insights: themes, pain points, jobs-to-be-done, and research gaps. Use this skill when you need to make sense of qualitative research data before writing a feature request or building personas. Trigger on: "synthesize my research", "what are the themes in these interviews", "extract insights from this feedback", "summarize what users are saying", "pull out the key themes from this data", or when someone pastes raw research notes.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of skills and chained workflow agents designed to streamline product management workflows, from research synthesis to feature specification, strategic planning, and stakeholder communication.
Via the Claude community marketplace (recommended):
/plugin marketplace add anthropics/claude-plugins-community
/plugin install gambit@claude-community
Or from the author's marketplace:
/plugin marketplace add felipecabargas/gambit
/plugin install gambit@felipecabargas-gambit
See Installation for Antigravity CLI, OpenCode, and manual options.
| Category | Skill | What it does |
|---|---|---|
| Core | verify-acceptance-criteria | Score ACs against five quality dimensions, flag gaps, and rewrite weak criteria |
| Core | write-feature-request | Guided FR authoring with auto-generated ACs for every requirement |
| Core | write-product-strategy | Generate a STRATEGY.md with pillars tied to research evidence |
| Core | sprint-review | Turn ticket lists or sprint data into a polished stakeholder report |
| Core | prioritize | Score and rank features using RICE, ICE, or MoSCoW grounded in your strategy |
| Discovery | synthesize-user-research | Pull themes, pain points, and jobs-to-be-done from raw research |
| Discovery | build-user-persona | Build evidence-backed personas with research-validated vs. inferred attributes |
| Discovery | competitive-analysis | Player profiles, capability matrix, and whitespace opportunities |
| Communication | write-okrs | Derive Objectives and Key Results from a product strategy |
| Communication | write-roadmap | Horizon-based roadmap (Now/Next/Later) from strategy and OKRs |
| Communication | write-release-notes | Customer-facing release notes from sprint tickets and PRs |
| Communication | write-stakeholder-update | Data-led leadership status update with OKR progress |
| Handoff | write-technical-brief | Engineering handoff document from a verified Feature Request |
Agents chain multiple skills in sequence, pausing for confirmation between steps.
| Agent | Chain | When to use |
|---|---|---|
discovery-to-fr | synthesize-user-research → build-user-persona → write-feature-request | Raw research → finished FR |
fr-to-ready | write-feature-request → verify-acceptance-criteria → write-technical-brief | Feature idea → dev-ready handoff |
strategy-to-roadmap | write-product-strategy → write-okrs → write-roadmap | Start of a planning cycle |
sprint-to-stakeholders | sprint-review → write-release-notes → write-stakeholder-update | End of every sprint |
No terminal? If you're a non-technical PM using Claude's desktop app, see Using Gambit in Claude Cowork for a terminal-free setup guide and a full end-to-end workflow walkthrough.
Gambit is listed in the Claude community plugin directory. From within Claude Code, run:
/plugin marketplace add anthropics/claude-plugins-community
/plugin install gambit@claude-community
Skills are immediately available as both model-invoked skills and slash commands (/gambit:sprint-review, /gambit:verify-acceptance-criteria, etc.).
Alternatively, install directly from the author's marketplace:
/plugin marketplace add felipecabargas/gambit
/plugin install gambit@felipecabargas-gambit
agy plugin install https://github.com/felipecabargas/gambit
Update later:
agy plugin update gambit
{
"plugins": ["gambit-opencode"]
}
Add to your opencode.json. Commands are available as /gambit-write-feature-request, /gambit-sprint-review, etc. See gambit-opencode for the full list.
npx claudepluginhub felipecabargas/gambit --plugin gambitHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
AI-powered development tools for code review, research, design, and workflow automation.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.