
Systematically analyze an existing codebase and produce structured artifacts — architecture documentation, component-level rules, ADR candidates, convention comparison, or CLAUDE.md audit. Use when onboarding to a brownfield project, inheriting a codebase, wanting consistent architecture docs, comparing repo practices against team conventions, needing per-component .claude/rules/ files, or auditing an existing CLAUDE.md. Works for any language, framework, or project size.
Run pre-MR reviews (code health, security, deviation), push the branch, mark the Draft MR as ready for review, and update issue labels. The final step before the MR goes to a teammate for review.
Produce a multi-sprint product roadmap in Google Drive — the planning layer between a baselined PRD and individual sprint planning. Organises what gets built in what order across sprints, with priorities, dependencies, and capacity rationale. Feeds directly into plan-sprint.
Orient a new team member to their environment through the TeamCraft lens. Reads GitLab repos, active milestones, open issues, and Google Drive project artifacts — then presents the current state and explains how TeamCraft applies to their role. Advisory only. Never starts work.
Sync advisor after a GitLab MR has been merged. Confirms the issue is closed in GitLab, cleans up stale labels, syncs local git state, and guides the developer through each step with explicit approval. Use when an MR was just merged, saying "just merged", needing post-merge cleanup, or when the GitLab issue is still open after merge. Also run when the local branch is stale after a merge, or when asking "what do I do after merge".
QA support for the current sprint — surface what's ready to test, prepare a testing approach for a specific issue, or create a bug from findings. Works without codebase access. Use when asking "what's ready to test", "what can I QA", checking sprint testing status, reporting a bug found during testing, or needing a test plan for a specific ticket. Also run when someone says "found a bug", "how should I test this", or wants to file a defect from QA findings.
Set up Teamcraft scaffolding for a repo — project identity, work-item registry, and a minimal CLAUDE.md shell. Scaffolding only. Does NOT interview for team conventions, technology decisions, or product requirements — those are handled by dedicated capture skills. Use when the user says 'set up teamcraft', 'initialize teamcraft', 'scaffold this project for teamcraft', or is a new adopter and needs the basic structure in place.
Plan a sprint — organise a Jira backlog with issues the team commits to for the sprint period, then create the sprint, add the issues, and optionally start it. Works for first sprints on new projects and ongoing sprints. Use when doing sprint planning, asking "what should we build next", grooming the backlog, starting a new sprint, or deciding what goes into the next iteration. Also run when prioritizing issues for upcoming work or asking "what's in the backlog".
Learn the TeamCraft plugin — full overview or role-specific deep dive. Teaches the workflow, the skills available to your role, how artifacts flow between roles, and where you fit in the team's process. No environment access needed. Run this before onboard, or any time you want to understand the plugin better.
Run pre-PR reviews (code health, security, deviation), push the branch, mark the Draft PR as ready for review, and update Jira issue status to "In Review". The final step before the PR goes to a teammate for review.
Live requirements capture session with a client — interview, generate visual mockups and diagrams to confirm understanding, then produce or update a structured PRD. Use when a BA or product owner wants to run a requirements session, capture client needs visually, create a PRD from a client conversation, or update an existing PRD with new requirements. Works for any application type, first sessions and follow-ups. Stores PRD in Confluence.
Live requirements capture session with a client — interview, generate visual mockups and diagrams to confirm understanding, then produce or update a structured PRD. Use when a BA or product owner wants to run a requirements session, capture client needs visually, create a PRD from a client conversation, or update an existing PRD with new requirements. Works for any application type, first sessions and follow-ups.
Facilitate a live problem discovery session with a client or stakeholders. Designed for use during a meeting or call — helps the PM guide structured exploration of a problem space before any requirements are written. Produces a discovery summary in Google Drive that seeds capture-requirements. Works in Claude Cowork and Claude Code.
Conduct a merge request review without leaving Claude Code. Access the full MR diff, implementation context, and discussion thread. Leave review comments, respond to threads, approve, and merge — all without opening the GitLab UI.
Interpret CI/CD pipeline status with context — not raw logs, but an explanation of what failed and why. Optionally create a trackable GitLab issue from a persistent pipeline failure. Use when CI is failing, the build is broken, the pipeline is red, asking "why did the pipeline fail", or wanting to understand a CI/CD error. Also run when an MR's pipeline won't pass, deployments are stuck, or a recurring pipeline failure needs to be tracked as an issue.
Load all project context for a GitLab issue — conventions, tech decisions, tech stack, defaults — confirm completeness with the developer, then enter Claude Code's native plan mode which plans and implements the solution. Detects existing work (branch, plan file) and offers to resume. Use when planning a ticket, saying "plan this ticket", "how should we build this", "implement this issue", or thinking through the approach. Run this after fetch-issue.
Run a sprint retrospective for a completed GitLab milestone. Gathers sprint data via the retro-analyzer agent, facilitates the retrospective conversation, captures team insights, and writes the retrospective report to Google Drive. Use when running a retrospective, saying "retro", "what went well", "what didn't go well", reviewing how a sprint went, or reflecting on completed work. Also run when the sprint just ended and the team wants to capture lessons learned.
Generate an audience-appropriate stakeholder update by pulling live GitLab sprint data and Drive artifacts. Produces human-facing communication from AI-native project artifacts — status reports, client updates, executive summaries, engineering updates. Works in Claude Cowork and Claude Code.
--- name: teamcraft:work-board description: Launch (or re-launch) the user's live, multi-project work board. The dashboard is a single HTML file copied to a stable user-side location at ~/.claude/teamcraft-board.html and opened in the user's default browser. It has two views via a header toggle — a drag-and-drop Kanban Board and a live Status tab (analytics: work by status, throughput, cycle time, aging, blocked chains, recomputed on every poll). Each project is added via a header dropdown; the
Report project status from work items and git history — either as a quick, interpreted read here in the session, or by pointing the developer to the live Status dashboard (the work board's Status tab). Covers work by status, what's in flight, cycle times, throughput, backlog priorities, aging alerts, blocked chains, and how commit activity lines up with the board. Use when the user says 'project status', 'show me the project status', 'what's the status of the work items', 'how are we doing', 'generate a status report', or asks for a status dashboard.
Generate an audience-appropriate stakeholder update by pulling live Jira sprint data, GitHub PR/pipeline status, and Confluence artifacts. Produces human-facing communication from AI-native project artifacts — status reports, client updates, executive summaries, engineering updates. Works in Claude Cowork and Claude Code.
Set up .teamcraft/project.md, CLAUDE.md, .claude/rules/, and .gitlab-ci.yml for a project. Works for any project state — brand new empty repo, existing codebase with no teamcraft files, or existing project mid-sprint. Creates files that don't exist; audits and proposes updates to files that do.
Check for open reviewer feedback on your MR and work through it. Run proactively to poll for feedback, or in response to a notification. Surfaces all open threads, helps you decide what to change vs. reply to, makes code changes, pushes, and resolves addressed threads. Leaves the MR ready for the reviewer's next pass.
Check for open reviewer feedback on your PR and work through it. Run proactively to poll for feedback, or in response to a notification. Surfaces all open threads, helps you decide what to change vs. reply to, makes code changes, pushes, and notes threads to resolve. Leaves the PR ready for the reviewer's next pass.
Systematically analyze an existing codebase and produce structured artifacts — architecture documentation, component-level rules, ADR candidates, convention comparison, or CLAUDE.md audit. Use when onboarding to a brownfield project, inheriting a codebase, wanting consistent architecture docs, comparing repo practices against team conventions, needing per-component .claude/rules/ files, or auditing an existing CLAUDE.md. Works for any language, framework, or project size.
Build or extend your team's conventions knowledge base in Google Drive. Discovers what's already captured, surfaces gaps, and guides you through capturing what you choose. You stay in control of what gets captured, when, and how it's organised.
Build or extend your team's conventions knowledge base in Confluence. Discovers what's already captured, surfaces gaps, and guides you through capturing what you choose. You stay in control of what gets captured, when, and how it's organised.
Create a single well-formed GitLab issue at any time — bugs found in production, features requested by stakeholders, technical debt noticed during development, chores that need doing. Follows the same issue standards as plan-sprint, always. Works in Claude Cowork and Claude Code.
Create a single well-formed Jira issue at any time — bugs found in production, features requested by stakeholders, technical debt noticed during development, chores that need doing. Follows the same issue standards as plan-sprint, always. Works in Claude Cowork and Claude Code.
Produce a multi-sprint product roadmap in Confluence — the planning layer between a baselined PRD and individual sprint planning. Organises what gets built in what order across sprints, with priorities, dependencies, and capacity rationale. Feeds directly into plan-sprint.
Facilitate a live problem discovery session with a client or stakeholders. Designed for use during a meeting or call — helps the PM guide structured exploration of a problem space before any requirements are written. Produces a discovery summary in Confluence that seeds capture-requirements. Works in Claude Cowork and Claude Code.
Create, plan, and implement urgent work through a streamlined path that preserves quality gates while removing sprint planning ceremony. For production bugs, critical fixes, and emergency work that cannot wait for the next sprint planning session.
Create, plan, and implement urgent work through a streamlined path that preserves quality gates while removing sprint planning ceremony. For production bugs, critical fixes, and emergency work that cannot wait for the next sprint planning session.
Fetch a GitLab issue, analyze its requirements against the current codebase, and assess feasibility. The starting point for every build cycle. Accepts a GitLab issue IID as argument. Use when starting a ticket, picking up work, checking feasibility of an issue, pulling up a GitLab issue, asking "what does this issue need", or beginning any new piece of work. Also run this when you want to understand what an issue involves before committing to it, or when checking if an issue is ready to plan.
Fetch a Jira issue, analyze its requirements against the current codebase, and assess feasibility. The starting point for every build cycle. Accepts a Jira issue key as argument. Use when starting a ticket, picking up work, checking feasibility of an issue, pulling up a Jira ticket, asking "what does this issue need", or beginning any new piece of work. Also run this when you want to understand what a ticket involves before committing to it, or when checking if an issue is ready to plan.
Set up .teamcraft/project.md, CLAUDE.md, .claude/rules/, and .github/workflows/ci.yml for a project. Works for any project state — brand new empty repo, existing codebase with no teamcraft files, or existing project mid-sprint. Creates files that don't exist; audits and proposes updates to files that do.
Learn the TeamCraft plugin — full overview or role-specific deep dive. Teaches the workflow, the skills available to your role, how artifacts flow between roles, and where you fit in the team's process. No environment access needed. Run this before onboard, or any time you want to understand the plugin better.
Orient a new team member to their environment through the TeamCraft lens. Reads Jira projects, GitHub repos, open issues, and Confluence project artifacts — then presents the current state and explains how TeamCraft applies to their role. Advisory only. Never starts work.
Interpret GitHub Actions workflow status with context — not raw logs, but an explanation of what failed and why. Optionally create a trackable Jira issue from a persistent workflow failure. Use when CI is failing, the build is broken, checks are red, asking "why did the pipeline fail", or wanting to understand a workflow error. Also run when a PR's checks won't pass, deployments are stuck, or a recurring CI failure needs to be tracked as a ticket.
Load all project context for a Jira issue — conventions, tech decisions, tech stack, defaults — confirm completeness with the developer, then enter Claude Code's native plan mode which plans and implements the solution. Detects existing work (branch, plan file) and offers to resume. Use when planning a ticket, saying "plan this ticket", "how should we build this", "implement this issue", or thinking through the approach. Run this after fetch-issue.
Plan a sprint — organise a GitLab milestone with issues the team commits to for the sprint period. Works for first sprints on new projects and ongoing sprints. Use when doing sprint planning, asking "what should we build next", grooming the backlog, starting a new sprint, or deciding what goes into the next iteration. Also run when prioritizing issues for upcoming work or asking "what's in the backlog".
Sync advisor after a GitHub PR has been merged. Explicitly transitions the Jira issue to Done, cleans up stale Jira status, syncs local git state, and guides the developer through each step with explicit approval. Use when a PR was just merged, saying "just merged", needing post-merge cleanup, or when the Jira ticket is still open after merge. Also run when the local branch is stale after a merge, or when asking "what do I do after merge".
On-demand interpreted view of sprint progress, velocity, quality signals, and defect trends. Available to any role at any time — returns insight, not raw data. Works without codebase access.
On-demand interpreted view of sprint progress, velocity, quality signals, and defect trends. Available to any role at any time — returns insight, not raw data. Works without codebase access.
Conduct a pull request review without leaving Claude Code. Access the full PR diff, implementation context, and discussion thread. Leave review comments, respond to threads, approve, and merge — all without opening the GitHub UI.
QA support for the current sprint — surface what's ready to test, prepare a testing approach for a specific issue, or create a bug from findings. Works without codebase access. Use when asking "what's ready to test", "what can I QA", checking sprint testing status, reporting a bug found during testing, or needing a test plan for a specific ticket. Also run when someone says "found a bug", "how should I test this", or wants to file a defect from QA findings.
Run a sprint retrospective for a completed Jira sprint. Gathers sprint data via the retro-analyzer agent, facilitates the retrospective conversation, captures team insights, and writes the retrospective report to Confluence. Use when running a retrospective, saying "retro", "what went well", "what didn't go well", reviewing how a sprint went, or reflecting on completed work. Also run when the sprint just ended and the team wants to capture lessons learned.
Audit and update CLAUDE.md, .claude/rules/, and .teamcraft/project.md to reflect the current state of the project. Run anytime — mid-ticket, end of sprint, pure maintenance, or first-time setup for a project with none of these files. Developer drives what changes; skill provides the analysis.
Audit and update CLAUDE.md, .claude/rules/, and .teamcraft/project.md to reflect the current state of the project. Run anytime — mid-ticket, end of sprint, pure maintenance, or first-time setup for a project with none of these files. Developer drives what changes; skill provides the analysis.
First-time setup for the Teamcraft GLGD plugin. Verifies that GitLab MCP and Google Drive MCP are configured and working, guides through setup if not, and recommends companion plugins. Run this before any other Teamcraft skill. Works in Claude Code and Claude Cowork.
Capture the technology stack and key decisions for this project. Reads the PRD from Google Drive, surfaces matching team conventions as context, and records what the team has decided to use and why. Simple format — what was decided and why, not a full ADR ceremony.
First-time setup for the Teamcraft JCG plugin. Verifies that the Atlassian MCP server (sooperset/mcp-atlassian) and GitHub CLI are configured and working, guides through setup if not, and recommends companion plugins. Run this before any other Teamcraft skill. Works in Claude Code and Claude Cowork.
Capture the technology stack and key decisions for this project. Reads the PRD from Confluence, surfaces matching team conventions as context, and records what the team has decided to use and why. Simple format — what was decided and why, not a full ADR ceremony. Stores in Confluence.
The main build skill. Fetch a work item or take a description of work, establish the work branch, research current technology docs, consult the project's captured knowledge, and enter plan mode. Use when the user says 'implement this issue', 'build this feature', 'code this up', 'start implementing feat-notification-prefs', 'plan and implement', 'let's work on this work item', or explicitly asks to implement, build, or code something specific.
Show the highest-priority work items from the backlog and help the developer pick one to work on next. Use when the user says 'pick next issue', 'what should I work on next from the backlog', 'show me the backlog', 'what's highest priority in the backlog', or 'pick an issue for me'.
Capture feedback about Teamcraft itself and turn it into a well-structured GitHub issue on the plugin's repo. Vets whether the problem is really a Teamcraft skill defect (vs. misuse, the harness, or the user's own project) by root-causing against the actual skill source, then helps the developer decide whether to file and publishes via the GitHub CLI. Use when the user says 'improve teamcraft', 'a teamcraft skill did the wrong thing', 'file feedback on teamcraft', 'report a teamcraft bug', 'I have an idea to make teamcraft better', or when a Teamcraft skill clearly misbehaved and the user wants that captured upstream.
Diagnostic tool — tests whether Claude has absorbed this project's conventions, decisions, and constraints from .claude/rules/ and CLAUDE.md, and reports the certification status of the captured-knowledge docs. Use when the user says 'quiz yourself on the project rules', 'check project context', 'verify the project setup', 'did you absorb the rules', or 'pop quiz'. This is specifically for testing rule absorption, not for general questions about the codebase.
Learn the Teamcraft plugin itself — how its workflow, skills, and artifacts fit together. A guided overview for a human getting started, or a system map for Claude orienting itself to how Teamcraft works before working in a Teamcraft repo. Teaching only; needs no project or environment access. Use when someone wants to understand Teamcraft (the tool, not their specific project), asks "how does Teamcraft work", "explain the workflow", "which skill do I use for X", or when Claude needs the big picture of how the skills hook together.
Run a retrospective — AI compiles evidence from recent work, facilitates human reflection, and captures process decisions back into living docs. Use when the user says 'run a retro', 'let's do a retrospective', 'run a retrospective on the last 2 weeks', 'let's reflect on how that feature went', or 'time for a retro'.
Plan a time-boxed iteration (sprint, cycle, milestone) from the backlog and the PRD/roadmap behind it — gather the goal, the window, and the team's real capacity, then select, sequence, and size a committed set of work items to fit. Writes an `iteration` label onto each chosen work item. Use when the user says 'plan a sprint', 'plan the next iteration', 'plan our cycle', 'sprint planning', 'iteration planning', 'plan the next two weeks', 'set up a milestone', 'what should we take on this sprint', 'plan from the PRD', or otherwise wants to commit a scoped, time-boxed batch of work rather than create issues one at a time. This is the planning layer between requirements and the build loop — distinct from create-issue (one item) and pick-next-issue (pick one to build now).
Capture or evolve architecture and technology decisions for this project — system structure, components, boundaries, and discrete technology choices with rationale. Handles first-time capture, adding new decision areas, migrations (e.g., Prisma to Drizzle, REST to GraphQL), revisit-when triggers, targeted updates, and architectural evolution. Writes developer-approved gotcha promotions directly. Use when the user says 'capture our architecture', 'document our tech stack', 'add a decision for our new auth approach', 'we're migrating from X to Y', or 'revisit our testing decision'.
Create or evolve the product requirements document (PRD). Handles new PRDs, major overhauls, adding new feature sets to existing PRDs, targeted section updates, and structural reorganization between single-file and per-feature structures. Identifies constraints that Claude would get wrong without always-loaded guidance and writes developer-approved promotions. Can decompose requirements into work items. Use when the user says 'write a PRD', 'update the PRD', 'capture requirements', 'add requirements for this new feature', 'revise the requirements', or 'rewrite the PRD for the new architecture'.
Create a work item in the repo's backlog. Interviews for requirements and acceptance criteria, checks for external context, and writes a structured work item to `.teamcraft/work/`. Use when the user says 'create an issue', 'add a work item', 'I need to track this', 'new feature request', 'log this bug', 'add this to the backlog', or describes work they want to capture for later.
Run pre-PR reviews (code health, security, acceptance criteria), address findings, and submit the PR for review. Ends when the PR is ready and CI has passed. Use when implementation is done and ready for review, or when the user says "I'm done coding", "validate this", "ready for review", "submit this for review", "run the pre-PR reviews", or "prepare this for review".
Pull review comments from the PR, work through them with the developer, make approved changes, re-validate, and push. Use when the user says "reviewers left comments", "address review feedback", "handle review comments", "respond to the PR review", or "someone commented on my PR".
Capture or evolve the team's operating conventions — branching, testing, review, merge, deploy, security, on-call, anything that shapes how the team works. Handles first-time capture, adding new convention areas, updating existing conventions, capturing newly-discovered gotchas, and cleanup. After capture, identifies items Claude would get wrong without always-loaded guidance and writes approved promotions. Use when the user says 'capture our team conventions', 'document our workflow', 'update our branching strategy', 'we changed our review process', or 'Claude keeps getting X wrong — let's capture it'.
Finalize and merge an approved (or solo-flow) PR. Verifies approval and CI status, marks the work item as done on the branch, commits, then merges. This is the skill that actually completes the work. Use when the user says "merge this issue", "ship this", "PR is approved, merge it", "finalize this issue", or "the review is done, let's merge".
Re-evaluate what Claude needs to be told about this project as the codebase evolves. Some gotchas become obvious from the code (remove them). New gotchas emerge. Decisions change. Use when the user says 'refresh the rules', 'update Claude's context', 'are the rules still accurate', 'clean up claude rules', or after significant codebase changes.