By DATA-AI-XYZ
Go from idea to production without the chaos: Tandem is a repo-native PM co-pilot for Claude Code that keeps every project on track from North Star → OKRs → PRD → Epic → Feature → Story → Testplan → ship. You get a closed-set status enum, mandatory Story↔Testplan pairing, Definition-of-Ready/Done gates, automatic ADRs on every decision, auto-filed bugs on test failure, and a self-generating interactive Command Center — all in plain Markdown, no external tools required. Stack-agnostic across web, mobile, CLI, library, backend, data-pipeline, Power Platform, and automation projects.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Close out a STORY through the Definition of Done gate. Use when the testplan is fully PASS, when the user asks to close a story, to finish a story, to mark a story done, or to run the DoD check. Runs the DoD checklist, flips status to done, updates MONITOR, regenerates the dashboard.
Close out a whole phase after an execution-strategist chat / execute-batch run finishes — gate on every phase story being done, compile a phase retrospective, capture follow-ups, update the board, then run a gated merge to main. Use when the user asks to close a phase, wrap up a phase, finish a batch/chat, run a phase retro, or integrate a finished phase.
Core PM Operating Kit rules — closed-set status enum, frontmatter timestamps, Story-Testplan pairing, DoR/DoD gates, hat protocol, ADR-on-the-spot, bug-auto-raise. Use when working anywhere under _00-Project-Management/, when creating or modifying any artefact (epic/feature/story/testplan/bug/ADR), or when uncertain about the project's PM conventions.
Advisory artefact quality review for planning artefacts (Epic, Feature, Story, Testplan). Use when the user asks to critique, review quality, check a planning artefact, audit a story or epic, or run a pre-refinement quality pass. Detects artefact type and runs the matching check set. Never rewrites the file.
Rank installed AI tools (Skills, Agents, Commands, Plugins) by fit for this project and write relevance overlays under 97-AI-Reference/. Reads PROJECT-CONTEXT.md (project type / tech stack) plus the installed inventory and ranks each item HIGH / MED / LOW with a one-line rationale keyed to project type. Use when the user wants to rank or audit which installed tools are relevant vs. off-stack, or invokes /Tandem:curate-toolkit.
Modifies files
Hook triggers on file write and edit operations
Tandem — the Claude Code project-management plugin. Your co-pilot for shipping ideas without the chaos.
Tandem is a Claude Code plugin that takes you from idea to production — without the chaos. You drive the whole plan with slash commands; Tandem makes sure nothing slips: no stories go in-progress without a testplan, no work ships without passing its gates, no decision disappears into the chat log. The result is a team-quality delivery rhythm, at solo-founder pace.
Tandem installs a _00-Project-Management/ scaffold into your project and registers a set of /Tandem:* skills that cover the full North Star → Done lifecycle. Two hooks keep everything honest: a linter that runs on every PM file edit, and a generator that rebuilds an interactive HTML Command Center whenever your plan changes. Both hooks run a single stdlib-only Node entrypoint (node ${CLAUDE_PLUGIN_ROOT}/_00-Project-Management/93-Scripts/hook.js) directly — no npm step is involved.
It's stack-agnostic — the bootstrap asks what you're building (web, mobile, CLI, library, backend, data-pipeline, Power Platform, or automation) and tailors the guidance to match.
Most "AI project management" is a chat log. Tandem is a contract:
flowchart LR
NS[North Star] --> OKR[OKRs]
OKR --> PRD[PRD]
PRD --> E[Epic]
E --> F[Feature]
F --> S[Story]
S --> TP[Testplan]
TP --> X[execute-story]
X --> R[run-testplan]
R --> C[close-out-story]
C --> M[(Command Center)]
M -. weekly / monthly review .-> OKR
Every arrow is a slash command. Every box is a markdown artefact in your repo.
# 1. Add the Tandem marketplace
/plugin marketplace add DATA-AI-XYZ/Tandem
# 2. Install the plugin
/plugin install Tandem@DATA-AI-XYZ
# 3. Bootstrap it into your project (drops _00-Project-Management/, wires hooks, seeds CLAUDE.md)
/Tandem:session-start
On install Tandem will:
_00-Project-Management/ scaffold into your project root (if absent)./Tandem:* skills covering the full North Star → Done lifecycle.CLAUDE.md (idempotent, under a managed marker).No plugin access? Tandem also ships a paste-prompt installer — see
BOOTSTRAP-PROMPT.md.
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 claimnpx claudepluginhub data-ai-xyz/tandem --plugin TandemComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-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
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.