workflow-browser

Plugin workflow-browser from marketplace dotclaude in phantien133/dotclaude. Commands read from the repo's manifest — 1 month ago.

Skills (35)

• ai-regression-testing

  Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

• coding-standards

  Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

• continuous-learning-v2

  Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

• doc-coauthoring

  Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc

• f-extract

  Extract all Figma design data (nodes, components, tokens, assets) in one MCP round and write a persistent figma-snapshot.md. Run once per task — downstream steps read the snapshot, never call MCP again.

• f-implement

  Implement UI components and screens from a figma-snapshot.md file. Never calls Figma MCP. Never generates SVG or approximates icons. Tracks missing assets in figma-assets.md and gates on human export before completing.

• figma-code-connect-components

  Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code impl

• figma-create-design-system-rules

  Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma

• figma-create-new-file

  Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteb

• figma-generate-design

  Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in

• figma-generate-library

  Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT to build and in WHAT

• figma-implement-design

  Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma ca

• figma-use

  **MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requ

• figma-verify-parity

  Verify that an implemented screen matches its Figma design 1:1 by rendering it in a real browser and diffing computed styles and assets against the Figma spec. Use after implementing UI from Figma, before opening a PR, or whenever someone says the build "looks a bit off" from the design.

• figma

  Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

• github-ops

  GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task

• skill-creator

  Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better t

• dotclaude-component-picker

  Use when picking, vendoring, porting, or syncing agents, skills, commands, hooks, or rules from any upstream source (ECC = everything-claude-code, anthropic-skills, mcp-servers, wshobson/agents, or other external repos) into this dotclaude project's claudekit/ directory. Trigger on phrases like "pic

• tdd-workflow

  Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

• w-acceptance-verify

  Phase 5b helper for w-task — proves the finished task actually delivers what the ticket asked for. Builds a requirement-to-evidence matrix from intake/questions/plan, fans out independent verifier agents, and (for UI work) compares the implementation against the Figma design export so wrong or inven

• w-adr

  Phase 2 helper for w-task — append a new Architecture Decision Record entry to the project's ADR doc when impact analysis surfaces a new decision. Generic version of streaming-adr.

• w-api-doc

  Phase 5 helper for w-task — append/update module api.md with new API operations (GraphQL queries/mutations/subscriptions or REST endpoints) introduced or changed in the current task.

• w-checkpoint

  Create a standardized TDD checkpoint commit (RED or GREEN) during w-task Phase 4. Updates state.yaml with checkpoint timestamp.

• w-codegraph

  Code-intelligence helper for w-task and w-fix — detects a CodeGraph index (.codegraph/), keeps it in sync, and answers context / impact / affected-test queries from the graph instead of grepping the tree. Degrades silently to git-grep when CodeGraph is unavailable.

• w-context-load

  Phase 0b helper for w-task — load module-aware context by reading module README + features/*.md + workflow-links, then write context.md. Generic version of dev-task's streaming-docs-aware context load.

• w-db-doc

  Phase 5 helper for w-task — write database/<NN>-<module>.md + sub-ERD .puml when DB changes occur. MANDATORY syncs the master ERD on every sub-ERD change — a stale master ERD is considered worse than none.

• w-doc-gate

  Phase 6 pre-PR gate — verify that every module touched in the current branch has a corresponding doc commit (module README / features / api.md / DB docs / master ERD). Blocks /w-pr if docs lag code. Replaces a post-merge sync hook by enforcing the invariant before PR creation.

• w-document-build-up

  Bootstrap streaming-docs-style documentation from an existing codebase. 4-phase state machine (Discover → Skeleton → ADR/OQ → Refinement) producing module READMEs, feature records, api.md, database schema docs, sub-ERDs, master ERD, ADR table, and OQ list. Run ONCE per project, BEFORE /w-setup, when

• w-feature-record

  Phase 5 helper for w-task — create or append features/<feature-name>.md inside the current module doc folder. Tracks per-feature history, design decisions, schema/API, diagrams, and constraints for future features.

• w-fix

  Lightweight workflow for bug fixes and small changes (1-3 files, <2h). Reads project config from .claude/workflow.yaml. Pass a GitHub issue URL, #N, or free description to start.

• w-impact-analyzer

  Phase 2 helper for w-task — auto-generate domain-specific impact.md sections (DB / GraphQL / queue / cache) by inspecting schema files referenced in workflow.yaml. Replaces hand-written generic Affected-Files-only impact.md with layer-aware analysis.

• w-oq-check

  Phase 0b helper for w-task — scan the project's Open Questions doc and surface OQs relevant to the current task. Flags blockers prominently. Generic version of streaming-oq-check.

• w-task

  Orchestrate a full feature dev workflow with browser and acceptance verification (intake → context → plan → impact → UI → TDD → browser-verify → docs → acceptance-verify → PR). Uses a CodeGraph index when available to explore and analyse impact cheaply, gates UI work on a localhost browser check via

• w-test-stubs

  Phase 4 helper for w-task — generate test file skeletons with layer-aware import boilerplate (unit / integration / graphql / bullmq / nestjs / nextjs) from impact.md, so TDD starts with structured RED, not blank files.

• workflow-setup

  One-time setup wizard that creates .claude/workflow.yaml — the project config consumed by dev-task, quick-fix, and all workflow skills. Run once per project before using any workflow skill.

Slash commands (8)

• /workflow-browser:f-setup
• /workflow-browser:feature-dev

  Guided feature development with codebase understanding and architecture focus

• /workflow-browser:prp-plan

  Create comprehensive feature implementation plan with codebase analysis and pattern extraction

• /workflow-browser:setup-dotclaude-preset-hooks

  Wire or unwire hooks for the installed dotclaude preset. Run when you want to enable or disable individual hooks in settings.json.

• /workflow-browser:w-pr

  Create a GitLab merge request for one repo (main workspace or a submodule) using glab CLI. Reads MR settings + per-repo default branch from .claude/workflow.yaml. Pass a task slug to use plan.md as MR body, --repo/--target to scope a submodule. Runs w-doc-gate first to enforce docs-with-code invaria

• /workflow-browser:w-reset

  Reset a w-task workflow back to phase 0, or wipe the task folder entirely. Reads state root from .claude/workflow.yaml.

• /workflow-browser:w-setup

  One-time setup wizard that creates .claude/workflow.yaml — the project config consumed by w-task, w-fix, and all workflow skills. Spawns code-explorer to survey project structure before asking questions, so suggestions are accurate. Run once per project before using any workflow skill.

• /workflow-browser:w-status

  Show the current w-task workflow state for one or all tasks without advancing it.

Subagents (10)

• code-architect

  Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order.

• code-explorer

  Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development.

• code-reviewer

  Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

• code-simplifier

  Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.

• figma-asset-fetcher

  Downloads every icon, image, vector and illustration referenced by a Figma spec from the Figma MCP asset endpoint into the project, and writes an asset manifest. Use before or during any Figma-driven UI implementation. Never generates or approximates an asset.

• figma-context-extractor

  Pulls design context, metadata, variables and screenshots from the official Figma MCP server and writes a compact, exact design spec to disk. Use whenever a task needs Figma data — the raw MCP payloads stay in this agent's context, the caller only gets a file path and a short summary.

• figma-design-system-mapper

  Maps Figma variables, text styles and components onto the project's existing design tokens and component library, and reports which Figma values have no equivalent. Use before implementing a Figma design so the implementer reuses real components instead of rebuilding them with hardcoded values.

• figma-visual-verifier

  Renders the implemented UI in a real browser, screenshots it, and compares it against the Figma reference screenshot to produce a concrete defect list (spacing, colour, font size, border, radius, background, icon, asset). Use after any Figma-driven UI implementation, before calling it done.

• planner

  Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.

• tdd-guide

  Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

Similar plugins