generating-rest-apis
Generate complete REST API implementations from OpenAPI specifications or database schemas. Use when generating RESTful API implementations. Trigger with phrases like 'generate REST API', 'create RESTful API', or 'build REST endpoints'.
securing-code
Enforces secure coding practices. Required after all code implementations to run CodeGuard security check. Covers input validation, secrets management, and OWASP countermeasures.
notion-spec-to-implementation
Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking to guide development from requirements to completion.
flyswatter
Bug triage, root cause analysis, and systematic repair. Activates on '/flyswatter', 'debug', 'fix', 'bug', 'not working', or 'troubleshoot'. Handles all 3 stages: Intake/Diagnosis, Solution Design, Implementation/Closeout.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
react-writing-plans
Use when you have a spec, PRD, or requirements for a React frontend feature requiring multiple components, stores, or API integrations, before writing any code. Creates concise implementation plans that reference architecture contracts.
design-phase
Use when needing to plan and design a product before writing implementation code. Sets up a standalone Design OS workspace.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
subagent-driven-development
Use when executing implementation plans composed of independent tasks within the current session.
build
Use when executing implementation plans with independent tasks in the current session.
Agent Architect
AI Agent architecture design assistant. Used to design Agent architectures for specific scenarios, recommending suitable reasoning modes, memory strategies, tool combinations, and multi-agent collaboration schemes. Input a scenario description and receive architecture recommendations, mode suggestions, and implementation guidance.
spec-to-code-compliance
Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.
solo-plan
Explore codebase and create spec + phased implementation plan with file-level task breakdown. Use when user says "plan this feature", "create implementation plan", "write a spec", "battle plan", or describes a feature/bug/refactor. Zero questions — researches code instead. Do NOT use for idea validation (use /validate) or execution (use /build).
shaping
Use when planning features, designing changes, or scoping work before implementation. Use when user says plan, design, think through, shape, or how should we approach. Use before building anything non-trivial in a brownfield codebase.
workflow-plan
Creates structured implementation plans from feature descriptions. Reads the codebase, identifies patterns and conventions, and produces a detailed plan document in docs/plans/. Use when asked to "plan a feature", "create a plan", "write a spec", or "plan implementation".
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
using-git-worktrees
Use when starting feature work that needs isolation from the current workspace or before executing implementation plans - creates isolated Git worktrees with smart directory selection and safety verification.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
SLO Implementation
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.
analytics-tracking
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
Linear Implement
Execute an implementation plan for a single Linear issue — write code, run checks, and update Linear with results.
senior-dotnet
World-class C# and .NET development skill for enterprise applications, ASP.NET Core web APIs, and cloud-native systems. Expertise in .NET 8, Entity Framework Core, ASP.NET Core Identity, Blazor, and microservices architecture. Includes project scaffolding, dependency management, security implementation, and performance optimization.
competitive-agents
Orchestrate competing agents to generate higher-quality plugin implementations. Use when user says "compete", "competitive agents", "dual generate", "에이전트 경쟁", "플러그인 배틀", or wants two agents to compete on a generation task.
review-changes
Code review of current git changes, compare to related plan if exists, identify bad engineering, over-engineering, or suboptimal solutions. Use when user asks to review changes, check git diff, validate implementation quality, or assess code changes.
executing-plans
Execute an approved implementation plan in a separate session with checkpoint reviews. Use after writing-plans when the user wants batched progress updates before more work continues.
jms-prd-review — PRD review gatekeeper
Critically review a PRD against its source prompt before implementation
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
forge-review-implementation
Use when implementation is done for current scope and a hypercritical comparison against plan acceptance criteria is needed before verification.
Algolia Search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning. Use when: adding search to an app, Algolia, InstantSearch, Search API, search functionality.
Vector Database Engineer
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar
review
Multi-perspective code review using parallel agents. Consolidates findings by severity for user approval. Use when implementation is complete (/execute finished), user says "review", "code review", or "check the code", before creating a PR, or after significant changes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
90-04-review
Run a composite, layered code review. Use when a coordinator needs to evaluate implementation quality before passing the quality gate. Stacks a 6-pass base rubric with optional language, architecture, and spec-divergence layers. Produces a tk review ticket with score and changes_requested.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
design-system
Collaborative design system creation using Atomic Design methodology. Produces a specification artifact with philosophy, tokens, and component hierarchy. Activate when creating a design system, defining visual language, specifying UI tokens, or planning component architecture before implementation begins.
Audit Readiness
Comprehensive audit readiness assessment and preparation program. USE THIS SKILL when the user asks about IPO readiness, audit preparation, first-time audit, audit remediation, SOC readiness, financial statement readiness, audit gap analysis, audit maturity, data room preparation, mock audit, dry run, audit-ready operations, auditor selection, or preparing for any external audit engagement. Produces a maturity assessment, gap analysis, remediation plan, and implementation timeline working backward from the target date.
Digital Product Inventor
Systematic framework for inventing, designing, pricing, and building digital product offers from an existing archive of tools, agents, doctrines, and skills. Use when turning a tool or capability into a sellable product, designing a new digital offer from scratch, going vertical into a new industry with an existing capability, building a product line from an AI agent stack, or creating a launch-ready product with a landing page, pricing strategy, and implementation plan. Combines deep client/market analysis, product architecture design, pricing strategy, landing page generation, and Google Drive delivery into one unified workflow.
20-04-post-merge-hygiene
Post-merge cleanup — document implementation, write post-mortem, update docs, close tickets, clean worktrees and branches.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict-avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing features for parallel development, establishing file ownership boundaries, or managing integration between parallel work streams.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code