work-workflow

Plugin work-workflow from marketplace work-workflow in thomfilg/ai-plugin-work. Commands read from the repo's manifest — 1 month ago.

Skills (27)

• bootstrap

  Setup multiple ticket tasks - creates worktrees and runs custom bootstrap scripts

• brief

  Generate a structured product brief from ticket requirements or a description

• check-browser

  Verify browser/UI state using API-first approach with browser fallback

• check-qa

  Run QA testing for a specific app using Playwright MCP

• check

  Script-driven quality check (code review, tests, requirements verification)

• cleanup-worktrees

  Safely clean up git worktrees by verifying code has been merged to main

• code-review

  Review code changes against target branch using code-checker agent

• configure

  Interactive env-var setup for the whole plugin family — generates or updates your .envrc (GH_TOKEN account pinning, git identity, and every var declared by work-workflow, heimdall, synapsys, maestro). Use when the user says "configure the plugin", "set up my env vars", "generate my .envrc", "configu

• create-design-doc

  Guide for writing Design Docs - a communication and decision documentation tool

• create-jira-agents

  Agent consultation prompts for multi-agent Jira task creation

• create-jira-consensus

  Multi-agent consensus protocol for Jira task creation

• create-jira-design-doc

  Design doc evaluation for complex Jira tasks

• create-jira-wiki

  Wiki publishing for Jira task design documents

• create-jira

  Orchestrated Jira task creation with deterministic step execution via workflow engine

• follow-up

  Script-driven PR follow-up (CI monitor, review handler, auto-fixer)

• health

  Validate work-state files and detect orphaned, stale, or dangling worktree/branch state; read-only by default

• install-followup-statusline

  Register (or remove) the /follow-up status bar — a live, agent-free 🔄 bar in Claude Code showing PR follow-up CI-wait progress (step + ✅🔴💬 counts) from monitor.js. Use when the user says "install the follow-up statusline", "show follow-up progress in the status bar", "register the follow-up statu

• install-work-statusline

  Register (or remove) the /work status bar — a live, agent-free ⚙ bar in Claude Code showing the current /work step, position (done/total), per-step detail (implement → which task, check → what it's doing), and a budget-coloured on-step timer from .work-state.json. Yields to the 🔄 follow-up bar duri

• spec

  Generate a technical specification from a product brief and codebase analysis

• split-in-tasks

  Split a spec into small, ordered, deliverable tasks with requirement traceability

• stats

  Report read-only workflow progress, duration, retry/loop count, and git metrics for a ticket (or all tickets)

• test-coordination

  Coordinate test coverage improvement - runs /tests-review and /tests-create in parallel until coverage is adequate

• tests-create

  Implement missing test edge cases using appropriate developer agent, writing changes to tests-made.txt

• tests-review

  Review test edge case coverage iteratively, writing feedback to tests-feedback.txt

• work-implement

  Quick implementation without the full /work workflow

• work-pr

  Updates PR description and adds visual documentation for a ticket task

• work

  Script-driven orchestrated workflow (v2) with auto-advance

Subagents (23)

• brief-writer

  Use this agent to generate a structured Product Brief from ticket requirements. The brief-writer analyzes ticket details and organizes them into a clear document covering problem statement, goals, requirements (P0/P1/P2), constraints, scope, and success metrics. This agent is invoked automatically b

• cleanup-runner

  Per-ticket cleanup agent invoked during the `cleanup` workflow step (after reports, last before complete). Deletes the feature branch, kills tmux sessions scoped to the ticket id, and archives the cleanup record. Refuses to act unless the PR is verified MERGED. CRITICAL: This agent must NEVER invoke

• code-architect

  Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

• code-checker

  Use this agent to analyze code implementations and provide detailed quality assessments and improvement suggestions. This agent excels at reviewing code patterns, identifying bugs and anti-patterns, suggesting optimizations, assessing test coverage, and ensuring adherence to best practices. Examples

• completion-checker

  Checks that all user requirements have been met before finalizing the conversation.

• developer-devops

  Use this agent for deploying, configuring, and managing infrastructure components such as cloud resources, containerized applications, CI/CD pipelines, and server configurations. Example tasks include provisioning AWS/Azure/GCP resources, configuring Kubernetes clusters, creating Docker deployments,

• developer-nodejs-tdd

  Use this agent when you need to develop Node.js TypeScript applications using frameworks like Express, Nest, or Next.js, following strict TDD practices. This agent should be invoked for creating new features, API endpoints, services, or any backend functionality that requires test-first development

• developer-react-senior

  Use this agent when you need to build, debug, or architect complex React applications with a focus on scalable architecture, performance optimization, and production-ready code. This includes developing SPAs, implementing state management, optimizing bundle sizes, solving React-specific challenges,

• developer-react-ui-architect

  Use this agent when you need to create, refactor, or enhance React-based user interfaces with a focus on stunning visual design, robust functionality through TDD, and production-ready code quality. This includes developing new React components, implementing complex layouts, optimizing UI performance

• jira-task-creator

  Use this agent to create professional, well-structured Jira tickets following a specific template format. This agent excels at filling templates with proper scope, testing requirements, acceptance criteria, and resource references. It validates all required fields, chooses appropriate issue types (S

• jira-transitioner

  Verifies if YOUR tasks "In Testing" have PRs merged to main and offers to transition them to Done.

• pr-generator

  Use this agent when you need to generate a pull request description from git diffs. The agent: - Checks if branch is in sync with main and rebases if needed - Intelligently selects the right diff based on context (last commit only vs entire branch) - Analyzes code changes and creates properly format

• pr-post-generator

  Use this agent after PR is created/updated to add visual documentation and test results. Reads QA reports and screenshots from tasks folder, uploads images to wiki, updates PR with wiki link. <example> Context: PR was just created and QA reports exist user: "add screenshots to the PR" <commentary> I

• pr-reviewer

  Use this agent to perform thorough, consistent code reviews on pull requests. Ensures code quality, maintainability, security, and adherence to project standards. Reviews TypeScript/React/Node.js code against strict typing, error handling, logging, and testing coverage. CRITICAL: This agent must NEV

• project-coordinator

  Orchestrates multiple specialized agents for complex tasks. Breaks down requirements, delegates to appropriate agents, ensures quality, and maintains context throughout workflow.

• qa-api-tester

  Use this agent for manual API and backend service testing. This agent tests APIs using curl, verifies database state, and validates service behavior WITHOUT browser automation. **CRITICAL: This agent must NEVER invoke itself via Task tool - do the work directly.** Examples: <example> Context: The us

• qa-feature-tester

  Use this agent for comprehensive QA testing that includes BOTH planning AND execution. This agent will actually run the application, interact with the UI, query databases, and call APIs to verify features work correctly. Examples: <example> Context: The user wants to test a newly implemented login f

• quality-checker

  **TEST RUNNER AGENT** - Runs automated tests and reports results. This agent RUNS the test commands (not just asks for proof): - pnpm test (unit tests) - pnpm dev:integration <app> (preferred - auto-maps DB env vars) - pnpm dev:smoke <app> (preferred - auto-maps DB env vars) - Fallback: pnpm test:in

• reports-writer

  Aggregates per-step artifacts (brief, spec, tasks, qa, code-review, completion, CI) into a single cross-step summary `reports.md` — plus a structured `learnings.md` (decisions, lessons, patterns, surprises, metrics) — during the `reports` workflow step (after ci, before cleanup, so the merged outcom

• spec-writer

  Use this agent to generate a Technical Specification from a product brief and codebase analysis. The spec-writer explores the codebase to understand architecture, patterns, and data models, then produces a spec with architecture decisions, API changes, security considerations, and Given/When/Then te

• split-in-tasks

  Use this agent to split a technical specification into small, ordered, deliverable tasks with requirement traceability. The split-in-tasks agent reads brief.md and spec.md, extracts every requirement, then produces tasks.md where each task is tied back to the requirement IDs it implements and the Gi

• task-reviewer

  Per-task review agent invoked during the `task_review` step (between commit and check). Reviews ONLY the most-recent task's diff (not the whole branch) for code quality, reuse, kind-specific risks, and test coverage. CRITICAL: This agent must NEVER invoke itself via Task tool — do the review work di

• work-documenter

  Records what a ticket's work taught, during the `document` workflow step (between ready and follow_up). Reads the ticket's own artifacts and diff, writes ONE note in its own words, and saves it to the configured memory plugin — or to the ticket worktree's docs when no memory plugin exists. The step

Hooks (30)

• UserPromptSubmit

  node ${CLAUDE_PLUGIN_ROOT}/hooks/work-hook.js

• UserPromptSubmit

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/reminder-dispatcher.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/hooks/enforce-follow-up-script.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-step-workflow.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/resolve-plugin-root-hook.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-dev-commands.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-step-workflow.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-tasks-md.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-gherkin.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-orchestrator-state.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-task-scope.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-agent-usage.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-agent-usage.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-agent-usage.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-step-workflow.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-step-workflow.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-tasks-md.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-gherkin.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-orchestrator-state.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/protect-task-scope.js

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work-implement/hooks/work-implement-enforce.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-env-start-failure.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-screenshot-requirement.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/work-enforce-steps.js

• PreToolUse

  CLAUDE_HOOK_TYPE=PreToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/agent-hook-dispatcher.js

• PostToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/capture-usage.js

• PostToolUse

  CLAUDE_HOOK_TYPE=PostToolUse node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/lib/hooks/enforce-step-workflow.js

• PostToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/work/hooks/work-auto-advance.js

• PostToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/check/hooks/check-auto-advance.js

• PostToolUse

  node ${CLAUDE_PLUGIN_ROOT}/scripts/workflows/follow-up/hooks/follow-up-auto-advance.js

Similar plugins