GitHub collection

shinpr/claude-code-workflows

Imported from GitHub — is this yours?

106 skills imported from this repository.

View on GitHub
683 103 MIT
Claude Skill

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

LLM Mart

Claude Skill

coding-principles

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

LLM Mart

Claude Skill

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

LLM Mart

Claude Skill

external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design sys

LLM Mart

Claude Skill

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

LLM Mart

Claude Skill

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

LLM Mart

Claude Skill

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

LLM Mart

Claude Skill

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

LLM Mart

Claude Skill

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs

LLM Mart

Claude Skill

recipe-build

Execute materialized task files in autonomous execution mode

LLM Mart

Claude Skill

recipe-design

Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval

LLM Mart

Claude Skill

recipe-diagnose

Investigate problem, verify findings, and derive solutions

LLM Mart

Claude Skill

recipe-front-adjust

Adjust an already-implemented UI in-session with verification against the design source

LLM Mart

Claude Skill

recipe-front-build

Execute materialized frontend task files in autonomous execution mode

LLM Mart

Claude Skill

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

LLM Mart

Claude Skill

recipe-front-plan

Create frontend work plan from design document and obtain plan approval

LLM Mart

Claude Skill

recipe-front-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill

recipe-fullstack-build

Execute materialized fullstack task files with layer-aware agent routing

LLM Mart

Claude Skill

recipe-fullstack-implement

Orchestrate full-cycle implementation across backend and frontend layers

LLM Mart

Claude Skill

recipe-implement

Orchestrate the complete implementation lifecycle from requirements to deployment

LLM Mart

Claude Skill

recipe-plan

Create work plan from design document and obtain plan approval

LLM Mart

Claude Skill

recipe-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill

recipe-update-doc

Update existing design documents (Design Doc / PRD / ADR) with review

LLM Mart

Claude Skill

requirement-convergence

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

LLM Mart

Claude Skill

subagents-orchestration-guide

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

LLM Mart

Claude Skill

test-implement

Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.

LLM Mart

Claude Skill

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

LLM Mart

Claude Skill

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

LLM Mart

Claude Skill dev-skills

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

LLM Mart

Claude Skill dev-skills

coding-principles

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

LLM Mart

Claude Skill dev-skills

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

LLM Mart

Claude Skill dev-skills

external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design sys

LLM Mart

Claude Skill dev-skills

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

LLM Mart

Claude Skill dev-skills

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

LLM Mart

Claude Skill dev-skills

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

LLM Mart

Claude Skill dev-skills

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

LLM Mart

Claude Skill dev-skills

requirement-convergence

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

LLM Mart

Claude Skill dev-skills

test-implement

Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.

LLM Mart

Claude Skill dev-skills

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

LLM Mart

Claude Skill dev-skills

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

LLM Mart

Claude Skill dev-workflows

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

LLM Mart

Claude Skill dev-workflows

coding-principles

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

LLM Mart

Claude Skill dev-workflows

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

LLM Mart

Claude Skill dev-workflows

external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design sys

LLM Mart

Claude Skill dev-workflows

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

LLM Mart

Claude Skill dev-workflows

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

LLM Mart

Claude Skill dev-workflows

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs

LLM Mart

Claude Skill dev-workflows

recipe-build

Execute materialized task files in autonomous execution mode

LLM Mart

Claude Skill dev-workflows

recipe-design

Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval

LLM Mart

Claude Skill dev-workflows

recipe-diagnose

Investigate problem, verify findings, and derive solutions

LLM Mart

Claude Skill dev-workflows

recipe-implement

Orchestrate the complete implementation lifecycle from requirements to deployment

LLM Mart

Claude Skill dev-workflows

recipe-plan

Create work plan from design document and obtain plan approval

LLM Mart

Claude Skill dev-workflows

recipe-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill dev-workflows

recipe-update-doc

Update existing design documents (Design Doc / PRD / ADR) with review

LLM Mart

Claude Skill dev-workflows

requirement-convergence

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

LLM Mart

Claude Skill dev-workflows

subagents-orchestration-guide

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

LLM Mart

Claude Skill dev-workflows

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows-frontend

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

LLM Mart

Claude Skill dev-workflows-frontend

coding-principles

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

LLM Mart

Claude Skill dev-workflows-frontend

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

LLM Mart

Claude Skill dev-workflows-frontend

external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design sys

LLM Mart

Claude Skill dev-workflows-frontend

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

LLM Mart

Claude Skill dev-workflows-frontend

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

LLM Mart

Claude Skill dev-workflows-frontend

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows-frontend

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

LLM Mart

Claude Skill dev-workflows-frontend

recipe-diagnose

Investigate problem, verify findings, and derive solutions

LLM Mart

Claude Skill dev-workflows-frontend

recipe-front-adjust

Adjust an already-implemented UI in-session with verification against the design source

LLM Mart

Claude Skill dev-workflows-frontend

recipe-front-build

Execute materialized frontend task files in autonomous execution mode

LLM Mart

Claude Skill dev-workflows-frontend

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

LLM Mart

Claude Skill dev-workflows-frontend

recipe-front-plan

Create frontend work plan from design document and obtain plan approval

LLM Mart

Claude Skill dev-workflows-frontend

recipe-front-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill dev-workflows-frontend

recipe-update-doc

Update existing design documents (Design Doc / PRD / ADR) with review

LLM Mart

Claude Skill dev-workflows-frontend

requirement-convergence

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

LLM Mart

Claude Skill dev-workflows-frontend

subagents-orchestration-guide

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

LLM Mart

Claude Skill dev-workflows-frontend

test-implement

Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.

LLM Mart

Claude Skill dev-workflows-frontend

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows-frontend

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

LLM Mart

Claude Skill dev-workflows-fullstack

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

LLM Mart

Claude Skill dev-workflows-fullstack

coding-principles

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

LLM Mart

Claude Skill dev-workflows-fullstack

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

LLM Mart

Claude Skill dev-workflows-fullstack

external-resource-context

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design sys

LLM Mart

Claude Skill dev-workflows-fullstack

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

LLM Mart

Claude Skill dev-workflows-fullstack

implementation-approach

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

LLM Mart

Claude Skill dev-workflows-fullstack

integration-e2e-testing

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows-fullstack

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-build

Execute materialized task files in autonomous execution mode

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-design

Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-diagnose

Investigate problem, verify findings, and derive solutions

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-front-adjust

Adjust an already-implemented UI in-session with verification against the design source

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-front-build

Execute materialized frontend task files in autonomous execution mode

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-front-plan

Create frontend work plan from design document and obtain plan approval

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-front-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-fullstack-build

Execute materialized fullstack task files with layer-aware agent routing

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-fullstack-implement

Orchestrate full-cycle implementation across backend and frontend layers

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-implement

Orchestrate the complete implementation lifecycle from requirements to deployment

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-plan

Create work plan from design document and obtain plan approval

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-review

Design Doc compliance and security validation with optional auto-fixes

LLM Mart

Claude Skill dev-workflows-fullstack

recipe-update-doc

Update existing design documents (Design Doc / PRD / ADR) with review

LLM Mart

Claude Skill dev-workflows-fullstack

requirement-convergence

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

LLM Mart

Claude Skill dev-workflows-fullstack

subagents-orchestration-guide

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

LLM Mart

Claude Skill dev-workflows-fullstack

test-implement

Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.

LLM Mart

Claude Skill dev-workflows-fullstack

testing-principles

Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.

LLM Mart

Claude Skill dev-workflows-fullstack

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

LLM Mart

Agents (83)

Claude Agent

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal te

Claude Agent

codebase-analyzer

Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.

Claude Agent

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

Claude Agent

design-sync

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

Claude Agent

document-reviewer

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

Claude Agent

integration-test-reviewer

Verifies changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use PROACTIVELY after test implementation completes, or when "test review/skeleton verification" is mentioned. Returns quality reports with failing items and fix instructio

Claude Agent

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

Claude Agent

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

Claude Agent

quality-fixer-frontend

Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.

Claude Agent

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

Claude Agent

requirement-analyzer

Collects compact scope and cost evidence for requirement confirmation while the user and orchestrator retain requirements, Structural Scale, and document-routing decisions. Use when new requirements, scope, or implementation extent must be confirmed.

Claude Agent

scope-discoverer

Discovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse engineering/existing code analysis/scope discovery" is mentioned.

Claude Agent

security-reviewer

Reviews implementation for security compliance against an authoritative Design Doc or Work Plan. Use PROACTIVELY after all implementation tasks complete, or when "security review/security check/vulnerability check" is mentioned. Returns structured findings with risk classificatio

Claude Agent

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

Claude Agent

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

Claude Agent

task-executor-frontend

Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investi

Claude Agent

task-executor

Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implemen

Claude Agent

technical-designer-frontend

Creates a scoped frontend ADR batch or one Design Doc from confirmed UI requirements and decision-relevant repository evidence. Use when frontend technical choices or implementation design need an approved artifact.

Claude Agent

technical-designer

Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.

Claude Agent

ui-analyzer

Gathers decision-relevant UI facts from recorded external resources and the existing codebase. Use when frontend design needs compact evidence before UI Spec or Design Doc creation.

Claude Agent

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

Claude Agent

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Claude Agent

work-planner

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

Claude Agent

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal te

Claude Agent

codebase-analyzer

Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.

Claude Agent

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

Claude Agent

design-sync

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

Claude Agent

document-reviewer

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

Claude Agent

integration-test-reviewer

Verifies changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use PROACTIVELY after test implementation completes, or when "test review/skeleton verification" is mentioned. Returns quality reports with failing items and fix instructio

Claude Agent

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

Claude Agent

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

Claude Agent

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

Claude Agent

requirement-analyzer

Collects compact scope and cost evidence for requirement confirmation while the user and orchestrator retain requirements, Structural Scale, and document-routing decisions. Use when new requirements, scope, or implementation extent must be confirmed.

Claude Agent

scope-discoverer

Discovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse engineering/existing code analysis/scope discovery" is mentioned.

Claude Agent

security-reviewer

Reviews implementation for security compliance against an authoritative Design Doc or Work Plan. Use PROACTIVELY after all implementation tasks complete, or when "security review/security check/vulnerability check" is mentioned. Returns structured findings with risk classificatio

Claude Agent

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

Claude Agent

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

Claude Agent

task-executor

Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implemen

Claude Agent

technical-designer

Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.

Claude Agent

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Claude Agent

work-planner

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

Claude Agent

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal te

Claude Agent

codebase-analyzer

Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.

Claude Agent

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

Claude Agent

design-sync

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

Claude Agent

document-reviewer

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

Claude Agent

integration-test-reviewer

Verifies changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use PROACTIVELY after test implementation completes, or when "test review/skeleton verification" is mentioned. Returns quality reports with failing items and fix instructio

Claude Agent

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

Claude Agent

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

Claude Agent

quality-fixer-frontend

Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.

Claude Agent

requirement-analyzer

Collects compact scope and cost evidence for requirement confirmation while the user and orchestrator retain requirements, Structural Scale, and document-routing decisions. Use when new requirements, scope, or implementation extent must be confirmed.

Claude Agent

security-reviewer

Reviews implementation for security compliance against an authoritative Design Doc or Work Plan. Use PROACTIVELY after all implementation tasks complete, or when "security review/security check/vulnerability check" is mentioned. Returns structured findings with risk classificatio

Claude Agent

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

Claude Agent

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

Claude Agent

task-executor-frontend

Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investi

Claude Agent

technical-designer-frontend

Creates a scoped frontend ADR batch or one Design Doc from confirmed UI requirements and decision-relevant repository evidence. Use when frontend technical choices or implementation design need an approved artifact.

Claude Agent

ui-analyzer

Gathers decision-relevant UI facts from recorded external resources and the existing codebase. Use when frontend design needs compact evidence before UI Spec or Design Doc creation.

Claude Agent

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

Claude Agent

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Claude Agent

work-planner

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.

Claude Agent

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal te

Claude Agent

codebase-analyzer

Collects compact repository evidence for scope confirmation, technical option selection, complete design, and verification. Use before Design Doc creation when repository facts can change scope, reuse, contracts, cost, or proof.

Claude Agent

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

Claude Agent

design-sync

Detects conflicts across multiple Design Docs and provides structured reports. Use when multiple Design Docs exist, or when "consistency/conflict/sync/between documents" is mentioned. Focuses on detection and reporting only, no modifications.

Claude Agent

document-reviewer

Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.

Claude Agent

integration-test-reviewer

Verifies changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use PROACTIVELY after test implementation completes, or when "test review/skeleton verification" is mentioned. Returns quality reports with failing items and fix instructio

Claude Agent

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

Claude Agent

prd-creator

Creates PRD and structures business requirements. Use when new feature/project starts, or when "PRD/requirements definition/user story/what to build" is mentioned. Defines user value and success metrics.

Claude Agent

quality-fixer-frontend

Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.

Claude Agent

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

Claude Agent

requirement-analyzer

Collects compact scope and cost evidence for requirement confirmation while the user and orchestrator retain requirements, Structural Scale, and document-routing decisions. Use when new requirements, scope, or implementation extent must be confirmed.

Claude Agent

scope-discoverer

Discovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse engineering/existing code analysis/scope discovery" is mentioned.

Claude Agent

security-reviewer

Reviews implementation for security compliance against an authoritative Design Doc or Work Plan. Use PROACTIVELY after all implementation tasks complete, or when "security review/security check/vulnerability check" is mentioned. Returns structured findings with risk classificatio

Claude Agent

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

Claude Agent

task-decomposer

Converts an approved Work Plan into the fewest executable implementation task files. Use when work plans are approved and task materialization is needed.

Claude Agent

task-executor-frontend

Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investi

Claude Agent

task-executor

Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implemen

Claude Agent

technical-designer-frontend

Creates a scoped frontend ADR batch or one Design Doc from confirmed UI requirements and decision-relevant repository evidence. Use when frontend technical choices or implementation design need an approved artifact.

Claude Agent

technical-designer

Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.

Claude Agent

ui-analyzer

Gathers decision-relevant UI facts from recorded external resources and the existing codebase. Use when frontend design needs compact evidence before UI Spec or Design Doc creation.

Claude Agent

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

Claude Agent

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivat

Claude Agent

work-planner

Creates implementation-focused work plans from approved Design Docs. Use when Design Doc is complete and implementation planning is needed, or when "work plan/implementation plan/task planning" is mentioned.