orkl

Assesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches.

Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.

Creates commits with conventional format and validation. Use when committing changes or generating commit messages.

Configures OrchestKit plugin settings, MCP servers, hook permissions, and keybindings. Use when customizing plugin behavior or managing settings.

Creates GitHub pull requests with validation. Use when opening PRs or submitting code for review.

OrchestKit doctor for health diagnostics. Use when running checks on plugin health, diagnosing problems, or troubleshooting issues.

explore — Deep codebase exploration with parallel agents. Use when exploring a repo, discovering architecture, finding files, or analyzing design patterns.

Manages OrchestKit usage analytics, learning preferences, and privacy settings. Use when reviewing patterns, pausing learning, or managing consent.

Fixes GitHub issues with parallel analysis. Use to debug errors, resolve regressions, fix bugs, or triage issues.

Complete git workflow patterns including GitHub Flow branching, atomic commits with interactive staging, merge and rebase strategies, and recovery operations using reflog. Essential patterns for clean history. Use when managing branches, defining branching strategy, or recovering git history.

OrchestKit skill directory with categorized listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.

Full-power feature implementation with parallel subagents. Use when implementing, building, or creating features.

Auto-updates GitHub issues with commit progress. Use when starting work on an issue, tracking progress during implementation, or completing work with a PR.

Read-side memory operations: search, recall, load, sync, history, visualize. Use when searching past decisions, loading session context, or viewing the knowledge graph.

Visualize planned changes before implementation. Use when reviewing plans, comparing before/after architecture, assessing risk, or analyzing execution order and impact.

Stores decisions and patterns in knowledge graph. Use when saving patterns, remembering outcomes, or recording decisions.

PR review with parallel specialized agents. Use when reviewing pull requests or code.

Assess platform upgrade readiness for Claude model and CC version changes. Use when evaluating upgrades.

Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.

Accessibility expert who audits and implements WCAG 2.2 compliance, screen reader compatibility, and keyboard navigation patterns. Focuses on inclusive design, ARIA patterns, and automated a11y testing. Auto Mode keywords - accessibility, a11y, WCAG, screen reader, keyboard navigation, ARIA, inclusive design, contrast, focus management

AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, OWASP LLM compliance. Use for safety audit, security audit, red team, guardrails, jailbreak, prompt injection, OWASP LLM, vulnerabilities, penetration testing, mcp security, tool poisoning.

Backend architect who designs REST/GraphQL APIs, database schemas, microservice boundaries, and distributed systems. Focuses on scalability, security, performance optimization, and clean architecture patterns. Activates for API design, database schema, microservice, backend architecture, REST, GraphQL, distributed systems, endpoint, route, model, migration, authentication, authorization, JWT, OAuth, rate limiting, middleware, service layer, repository pattern, dependency injection

Business analyst who builds ROI projections, cost-benefit analyses, risk assessments, and investment justifications to support product decisions with financial rationale. Activates for ROI, cost-benefit, risk assessment, investment justification, business case, budget, revenue impact, cost analysis, financial, payback period, NPV, IRR, TCO, revenue projection

CI/CD specialist who designs and implements GitHub Actions workflows, GitLab CI pipelines, and automated deployment strategies. Focuses on build optimization, caching, matrix testing, and security scanning integration. Auto Mode keywords - CI/CD, pipeline, GitHub Actions, GitLab CI, workflow, build, deploy, artifact, cache, matrix testing, release automation

Quality assurance expert who reviews code for bugs, security vulnerabilities, performance issues, and compliance with best practices. Runs linting, type checking, ensures test coverage, and validates architectural patterns. Auto Mode keywords: test, review, quality, lint, security, coverage, audit, validate, CI, pipeline, check, verify, type-check

Data pipeline specialist who generates embeddings, implements chunking strategies, manages vector indexes, and transforms raw data for AI consumption. Ensures data quality and optimizes batch processing for production scale. Activates for embeddings, chunking, vector index, data pipeline, batch processing, ETL, regenerate embeddings, cache warming, data transformation, data quality, vector rebuild, embedding cache

PostgreSQL specialist who designs schemas, creates migrations, optimizes queries, and configures pgvector/full-text search. Uses pg-aiguide MCP for best practices and produces Alembic migrations with proper constraints and indexes. Auto Mode keywords: database, schema, migration, PostgreSQL, pgvector, SQL, Alembic, index, constraint

Debug specialist who performs systematic root cause analysis on bugs, errors, exceptions, crashes, and failures. Uses scientific method to isolate issues, traces execution paths, analyzes logs and stack traces. Use when investigating broken functionality, debugging regressions, or analyzing flaky tests.

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition. Activates for demo, video, marketing, showcase, terminal recording, VHS, remotion, tutorial, screencast

Release and deployment specialist who manages production releases, rollback procedures, feature flags, and blue-green deployments. Focuses on zero-downtime deployments and incident response. Auto Mode keywords - deployment, release, rollback, blue-green, canary, feature flag, zero-downtime, production, rollout, incident

Technical writing and documentation expert. API docs, READMEs, technical guides, ADRs, changelogs, OpenAPI specs. Use for documentation, readme, api-docs, technical-writing, adr, changelog, openapi, swagger, doc-generation.

LLM evaluation specialist who runs structured eval datasets, computes quality metrics using DeepEval/RAGAS, tracks regression across model versions, and reports to Langfuse for tracing and scoring.

Event-driven architecture specialist who designs event sourcing systems, message queue topologies, and CQRS patterns. Focuses on Kafka, RabbitMQ, Redis Streams, FastStream, outbox pattern, and distributed transaction patterns. Auto Mode keywords - event sourcing, message queue, Kafka, RabbitMQ, pub/sub, CQRS, event-driven, async, saga, event store, outbox, CDC, Debezium

Performance engineer who optimizes Core Web Vitals, analyzes bundles, profiles render performance, and sets up RUM. Activates for performance, Core Web Vitals, LCP, INP, CLS, bundle size, Lighthouse, optimization, slow, latency, profiling, metrics, RUM, bundle, chunk, splitting, speed

Frontend developer who builds React 19/TypeScript components with optimistic updates, concurrent features, Zod-validated APIs, exhaustive type safety, and modern 2026 patterns. Activates for React, TypeScript, component, UI, frontend, optimistic updates, Zod, concurrent, TSX, hook, TanStack, Suspense, skeleton, form, validation, mutation, lazy loading, view transitions, scroll animations, PWA, charts, dashboard

Git operations specialist who manages branches, commits, rebases, merges, stacked PRs, and recovery operations. Ensures clean commit history and proper branching workflows. Auto Mode keywords - git, branch, commit, rebase, merge, stacked, recovery, reflog, cherry-pick, worktree, squash, reset

Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking, security groups, and cost optimization. Auto Mode keywords - infrastructure, Terraform, Kubernetes, AWS, GCP, Azure, VPC, EKS, RDS, cloud architecture, IaC

LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements function calling and streaming, and optimizes token costs with caching strategies. Activates for LLM, OpenAI, Anthropic, Ollama, prompt, function calling, streaming, token keywords.

Market research specialist who analyzes competitive landscapes, identifies market trends, sizes opportunities (TAM/SAM/SOM), and surfaces threats/opportunities to inform product strategy. Activates for market research, competitor, TAM, SAM, SOM, market size, competitive landscape keywords.

Metrics specialist who designs OKRs, KPIs, success criteria, and instrumentation plans to measure product outcomes and validate hypotheses. Activates for OKR, KPI, metrics, success criteria, instrumentation keywords.

Observability and monitoring specialist. Prometheus metrics, Grafana dashboards, alerting rules, distributed tracing, log aggregation, SLOs/SLIs. Use for monitoring, prometheus, grafana, alerting, tracing, opentelemetry, metrics, observability, logs, slo, sli.

Vision, audio, and video processing specialist who integrates GPT-5, Claude 4.5, Gemini 3, and Grok 4 for image analysis, transcription, and multimodal RAG. Activates for vision, image, audio, video, multimodal, whisper, tts, transcription, speech-to-text, document vision, OCR, captioning, CLIP, visual keywords.

Prioritization specialist who scores features using RICE/ICE/WSJF frameworks, analyzes opportunity costs, manages backlog ranking, and recommends what to build next based on value and effort. Activates for RICE, ICE, WSJF, prioritization, backlog, opportunity cost keywords.

Product strategy specialist who validates value propositions, aligns features with business goals, evaluates build/buy/partner decisions, and recommends go/no-go with strategic rationale. Activates for product strategy, value proposition, build/buy/partner, go/no-go

Expert prompt designer and optimizer. Chain-of-thought, few-shot learning, structured outputs, prompt versioning, A/B testing, cost optimization. Use for prompts, prompt-engineering, cot, few-shot, prompt design, prompt optimization, structured-output, a-b-testing, cost-optimization, prompt-testing, evaluation.

Python performance specialist who profiles, optimizes, and benchmarks Python applications. Focuses on memory optimization, async performance, database query optimization, caching strategies, and load testing. Activates for performance, profiling, memory leak, slow query, optimization, bottleneck, benchmark, latency, throughput, cProfile, memory_profiler, scalability, connection pool, cache, N+1

UI/UX designer specializing in rapid prototyping with Tailwind CSS. Creates design systems, component specifications, responsive layouts, and accessibility-compliant mockups that bridge design and implementation. Activates for UI, UX, prototype, Tailwind, design system, component, mockup

Release and versioning specialist who manages GitHub releases, milestones, changelogs, and semantic versioning. Handles release automation and project tracking. Auto Mode keywords - release, milestone, changelog, tag, version, semver, sprint, roadmap

Requirements specialist who transforms ambiguous ideas into clear PRDs, user stories with acceptance criteria, and scoped specifications ready for engineering handoff. Activates for PRD, user story, acceptance criteria, requirements, specification

Security specialist who scans for vulnerabilities, audits dependencies, checks OWASP Top 10 compliance, and identifies secrets/credentials in code. Returns actionable findings with severity and remediation steps. Auto Mode keywords - security, vulnerability, CVE, audit, OWASP, injection, XSS, CSRF, secrets, credentials, npm audit, pip-audit, bandit

Security layer auditor who verifies defense-in-depth implementation across 8 security layers, from edge to storage, ensuring comprehensive protection. Auto Mode keywords - security layer, defense-in-depth, security audit, 8 layers

System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written. Auto Mode keywords: system design, architecture review, scale, security review, implementation plan

Test specialist who analyzes code coverage gaps, generates unit/integration tests, and creates test fixtures. Uses MSW for API mocking and VCR.py for HTTP recording. Produces runnable tests with meaningful assertions. Activates for test, coverage, unit test, integration test, MSW, VCR, fixture

Processes UI annotations from agentation. Watches for new annotations, maps element paths to source code, implements fixes, and resolves annotations with summaries.

User research specialist who creates personas, maps user journeys, validates design decisions, and ensures features solve real user problems through data-driven insights and behavioral analysis. Auto-activates for user research, persona, user journey, usability, user testing, insights

Web research specialist using browser automation and Tavily API for competitive intelligence, market research, documentation capture, and technical reconnaissance. Activates for web research, scraping, competitor analysis, documentation capture, browser automation, web scraping, content extraction, tavily

Multi-agent workflow specialist who designs LangGraph pipelines, implements supervisor-worker patterns, manages state and checkpointing, and orchestrates RAG retrieval flows for complex AI systems. Auto-activates for LangGraph, workflow, supervisor, state, checkpoint, RAG, multi-agent

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, and React Aria component patterns. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, or accessible component libraries.

API design patterns for REST/GraphQL framework design, versioning strategies, and RFC 9457 error handling. Use when designing API endpoints, choosing versioning schemes, implementing Problem Details errors, or building OpenAPI specifications.

Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.

Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right architecture tier for project scope.

ASCII diagram patterns for architecture, workflows, file trees, and data visualizations. Use when creating terminal-rendered diagrams, box-drawing layouts, progress bars, swimlanes, or blast radius visualizations.

Assesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches.

Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.

OrchestKit orchestration wrapper for browser automation. Adds security rules, rate limiting, and ethical scraping guardrails on top of the upstream agent-browser skill. Use when automating browser workflows, capturing web content, or extracting structured data from web pages.

Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments patterns, language-specific checklists, and feedback templates. Use when reviewing PRs or standardizing review practices.

Creates commits with conventional format and validation. Use when committing changes or generating commit messages.

Configures OrchestKit plugin settings, MCP servers, hook permissions, and keybindings. Use when customizing plugin behavior or managing settings.

Creates GitHub pull requests with validation. Use when opening PRs or submitting code for review.

Database design and migration patterns for Alembic migrations, schema design (SQL/NoSQL), and database versioning. Use when creating migrations, designing schemas, normalizing data, managing database versions, or handling schema drift.

Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.

Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry policies, idempotency keys, token bucket rate limiters, or fault tolerance patterns.

OrchestKit doctor for health diagnostics. Use when running checks on plugin health, diagnosing problems, or troubleshooting issues.

Domain-Driven Design tactical patterns for complex business domains. Use when modeling entities, value objects, domain services, repositories, or establishing bounded contexts.

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

explore — Deep codebase exploration with parallel agents. Use when exploring a repo, discovering architecture, finding files, or analyzing design patterns.

Manages OrchestKit usage analytics, learning preferences, and privacy settings. Use when reviewing patterns, pausing learning, or managing consent.

Fixes GitHub issues with parallel analysis. Use to debug errors, resolve regressions, fix bugs, or triage issues.

Complete git workflow patterns including GitHub Flow branching, atomic commits with interactive staging, merge and rebase strategies, and recovery operations using reflog. Essential patterns for clean history. Use when managing branches, defining branching strategy, or recovering git history.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.

OrchestKit skill directory with categorized listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.

Full-power feature implementation with parallel subagents. Use when implementing, building, or creating features.

Auto-updates GitHub issues with commit progress. Use when starting work on an issue, tracking progress during implementation, or completing work with a PR.

Knowledge graph memory orchestration - entity extraction, query parsing, deduplication, and cross-reference boosting. Use when designing memory orchestration.

Read-side memory operations: search, recall, load, sync, history, visualize. Use when searching past decisions, loading session context, or viewing the knowledge graph.

Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse LLM tracing, and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.

Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling, and LLM inference. Use when improving page speed, debugging slow renders, optimizing bundles, reducing image payload, profiling backend, or deploying LLMs efficiently.

Visualize planned changes before implementation. Use when reviewing plans, comparing before/after architecture, assessing risk, or analyzing execution order and impact.

Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.

Use when assessing task complexity, before starting complex tasks, when stuck after multiple attempts, or reviewing code against best practices. Provides quality-gates scoring (1-5), escalation workflows, and pattern library management.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

Stores decisions and patterns in knowledge graph. Use when saving patterns, remembering outcomes, or recording decisions.

Responsive design with Container Queries, fluid typography, cqi/cqb units, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.

PR review with parallel specialized agents. Use when reviewing pull requests or code.

Right-sizes architecture to project scope. Prevents over-engineering by classifying projects into 6 tiers and constraining pattern choices accordingly. Use when designing architecture, selecting patterns, or when brainstorming/implement detect a project tier.

Security patterns for authentication, defense-in-depth, input validation, OWASP Top 10, LLM safety, and PII masking. Use when implementing auth flows, security layers, input sanitization, vulnerability prevention, prompt injection defense, or data redaction.

CC 2.1.16 Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.

Comprehensive testing patterns for unit, integration, E2E, pytest, API mocking (MSW/VCR), test data, property/contract testing, performance, LLM, and accessibility testing. Use when writing tests, setting up test infrastructure, or validating application quality.

Assess platform upgrade readiness for Claude model and CC version changes. Use when evaluating upgrades.

Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.

Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown, capturing documentation, or monitoring competitor changes.

42 hooks across 12 events