cks

Slash commands available via the CKS plugin. All commands use the `/cks:` prefix.

Adopt CKS into an existing codebase mid-development — scans git history, generates CLAUDE.md, creates feature entry at sprint phase, detects secrets

Run all 5 phases autonomously — discover → design → sprint → review → release. No interruption.

Export board state (features, sessions, notes, activity) as a committed markdown summary

Launch the CKS Kanban board — visual dashboard for your project lifecycle

Scaffold project — .claude/, CLAUDE.md, .prd/, rules, deploy config

Browser automation — open websites, fill forms, click buttons, take screenshots, extract data, configure external portals

Auto-generate a CHANGELOG.md entry from git history

Research a topic, library, or API and save a persistent context brief to .context/

Debug anything — trace app runtime errors or diagnose CKS skill/agent/command issues

Stop asking — diagnose and act

Deploy project to configured Railway environment with health checks

Generate a DESIGN.md — plain-text design system for AI agents (Stitch, v0, Lovable, Cursor)

Phase 2: Design — UX research, API contract, screen generation (Stitch MCP), component specs

Phase 1: Discovery — structured requirements gathering with the 11 Elements

Generate or update project documentation — API docs, architecture, component docs, onboarding guide

Run a full project health diagnostic — env vars, TODOs, tests, PRD state, git hygiene

End of day — summarize today's work into a dated DEVLOG entry with state and next steps

Build the Process Evaluator feature — complete process card generation from text input

Build error resolver — diagnose and fix build/compile/runtime errors fast

Quick action command — commit, PR, dev, build, start. PRD-aware: guides you through the lifecycle.

Show all available CKS commands and usage guide

Phase 0: Ideation — brainstorm, refine, and stress-test a project idea

Project enabler — idea to scaffolded project

Run pre-launch readiness checklist before deployment — adapts gates to maturity stage

View and query CKS lifecycle logs — filter by feature, phase, severity, date

Analyze codebase and produce structured docs in .prd/codebase/

Migrate project state files to match current CKS plugin version

Monetization cost analysis — tech stack costs and unit economics

Monetization discovery — gather business context

Monetization model evaluation — evidence-based tier scoring

Generate monetization assessment report

Monetization market research

Generate monetization roadmap and PRD handoff

Run full monetization evaluation: discover → research → cost → evaluate → report → roadmap

Create a new feature and start the 5-phase lifecycle — discover → design → sprint → review → release

Auto-advance to the next logical step in the workflow

Token optimization — configure cost-saving defaults and audit context usage

Show project progress and route to the next action

Refactor a feature, layout, component, or pattern with safety checks and verification

Phase 5: Release Management — environment promotion (Dev → Staging → RC → Production)

Remotion video development — build, debug, and optimize programmatic videos in React

Deep multi-hop research on any topic — recursive investigation with configurable sources

Run a retrospective — analyze what worked, extract learnings, propose CLAUDE.md updates

Adherence audit — checks codebase against .claude/rules/ and reports per-rule compliance

Phase 4: Sprint Review & Retrospective — feedback, retro, iteration decision

R-P-I sub-cycle status — show Research/Plan/Implement stage, quality gates, and artifact inventory

Security scan — audit app code AND pipeline config for vulnerabilities

Full SEO audit — on-page, technical, schema, content

Simplify recent code changes for clarity and maintainability while preserving behavior

End a work session — runs adherence check, captures learnings, updates CLAUDE.md if needed

Begin a work session — loads full operating context (CLAUDE.md, rules, PRD state, git) and validates guardrails are in place

Phase 3: Sprint Execution — plan, build, review, QA, UAT, merge

Morning standup — recap last DEVLOG entry, cross-reference current state, suggest next action

Project status overview — git, build, PRD lifecycle, and code health

Standalone TDD workflow — RED/GREEN/REFACTOR cycle, usable anytime (not phase-locked)

Run full test suite with pass/fail summary and optional coverage

Strip project-specific content from .claude/ files to make them starter-ready

Sub-agent definitions for specialized tasks. Each `.md` file defines one agent with its role, tools, triggers, and constraints.

AEO and GEO specialist for AI search visibility

Bootstrap Phase 2 — generates CLAUDE.md, .prd/, .claude/rules/, .context/, MCP config, and deploy config from scan context and kickstart artifacts.

Bootstrap Phase 1 — scans codebase, detects stack, runs guided intake with pre-filled answers from scan results.

Auto-generates CHANGELOG.md entries from git history with conventional commit categorization

Simplifies code for clarity and maintainability while preserving exact behavior. Reviews recent changes for unnecessary complexity.

Cost analysis agent — builds unit economics models, calculates margins, and produces cost breakdown from raw pricing research

Cost research agent — researches real-world pricing for AI/ML inference, infrastructure, third-party services, communication APIs, and orchestration platforms

Database migration agent — generates schema changes, validates migrations, tests rollbacks. Integrates with Sprint Phase 3 when data model changes detected.

Diagnoses app runtime errors and CKS plugin issues — traces code paths, reads logs, identifies root causes

Autonomous multi-hop research specialist. Recursively investigates topics across configurable sources, discovers sub-topics, cross-references findings, and produces structured intelligence reports with confidence scoring. Use when deep strategic research is needed — not for quick coding reference lookups.

Phase 5: Release Management agent — manages environment promotion (Dev → Staging → RC → Production), validates quality gates, runs health checks

Generates a full DESIGN.md — plain-text design system for AI agents (Stitch, v0, Lovable, Cursor) from website URL, brand file, or guided Q&A.

Generates project documentation from codebase analysis — API docs, architecture, component docs, onboarding guide. Triggered by /cks:docs or auto-invoked post-sprint and pre-release.

Quick action runner — commit, PR, dev, build, start across all languages. PRD-aware.

Project health diagnostic — env vars, TODOs, tests, PRD state, git hygiene, dependency audit

Kickstart Phase 4 — brand identity extraction. Colors, typography, voice, UI preferences from Canva, website, or guided Q&A.

Kickstart Phase 5 — design artifact generation. Produces ERD, schema.sql, PRD, API contract, architecture decisions, and feature roadmap from intake context.

Kickstart Phase 6 — project scaffolding and .claude/ personalization. Feeds design artifacts into /bootstrap to wire up the development ecosystem.

Kickstart Phase 0 — idea brainstorming and refinement. SCAMPER, 5 Whys, How Might We, angle variations, stress-testing. Dual-purpose: kickstart Phase 0 or standalone brainstorming.

Kickstart Phase 1+1b — guided intake Q&A and project composition. Gathers domain, users, data model, integrations. Identifies sub-projects and build order.

Kickstart lifecycle orchestrator — sequences ideation, intake, research, monetize, brand, design, and handoff phases

Pre-launch readiness checker — runs the full shipping checklist and reports blocking issues by maturity stage before deployment.

Detects CKS version gaps and migrates project state files to match current plugin version.

Monetization discovery agent — scans codebase, gathers business context via interactive questions, produces .monetize/context.md

Monetization evaluation agent — evidence-based tier evaluation of models against context, research, cost, and compliance data. Builds optimal monetization stack with assumption chains.

Monetization report agent — combines all artifacts into an honest, evidence-based business case with assumption chains, compliance analysis, and confidence grades

Market research agent — queries Perplexity API or WebSearch for competitor pricing, market sizing, conversion benchmarks, and comparable exits

No-code/low-code automation specialist — builds, debugs, migrates, and optimizes workflows across n8n, Make.com, Workato, and Zapier. Platform-adaptive: detects or asks which platform, then uses appropriate MCP tools and documentation.

UX/UI design agent — generates screens via Stitch MCP, creates component specs, manages design iteration and review

Phase 1: Discovery agent — gathers all 11 Elements using AskUserQuestion, researches codebase, produces structured CONTEXT.md

Lightweight implementation worker — executes a single task group from a sprint plan. Dispatched by prd-executor team lead.

Implementation team lead — reads the sprint plan, splits work into task groups, dispatches parallel executor-workers, consolidates SUMMARY.md

Full-lifecycle orchestrator — drives the 5-phase cycle (discover → design → sprint → review → release) with iteration loop support. Dispatches specialized agents in sequence.

Planning agent — takes discovery CONTEXT.md and produces PRD document, execution PLAN.md, and roadmap updates

Refactoring coordinator — phases work into impact analysis, parallel execution workers, and verification. Ensures behavior is preserved.

Research agent — investigates codebase architecture, technology options, and implementation approaches to inform planning

Verification team lead — dispatches parallel test workers for unit/integration/E2E, consolidates results into VERIFICATION.md

Remotion video specialist — builds and debugs programmatic videos in React

Post-ship learning analyst — analyzes completed work to extract conventions, patterns, gotchas, and velocity metrics. Proposes CLAUDE.md updates based on high-confidence findings. Creates compound improvement across development cycles.

Phase 3 [3d]: Code Review agent — reviews changes for correctness, conventions, security, and design spec adherence

Adherence audit — scans codebase against .claude/rules/ and reports per-rule compliance with grades

Security scanning agent — OWASP Top 10 checks, secrets detection, dependency audit, auth review, config audit. Integrates with Sprint [3d] code review and Release [5c] quality gate.

SEO strategist for rank-and-rent local lead generation sites

End-of-day journalist — gathers git activity, PRD state, and session learnings to compose a dated DEVLOG entry. Summarizes what happened, current state, and next steps for tomorrow's standup.

Session context loader — reads project state, guardrails, learnings, git context, and displays session brief

Phase 4: Sprint Review coordinator — builds sprint summary from artifacts, collects user feedback, runs retrospective, manages backlog refinement, and makes the iteration decision (release / iterate design / iterate sprint / re-discover).

Morning standup — reads DEVLOG, cross-references project state, suggests where to pick up

Test-driven development specialist — runs RED/GREEN/REFACTOR cycles. Writes failing tests first, implements minimal code to pass, then refactors with green tests as safety net. Standalone — works anytime, not phase-locked.

Token optimization auditor — analyzes context budget, MCP servers, compaction strategy, and recommends cost savings

Web accessibility essentials (WCAG 2.1 AA) for production applications. Use when: building UI components, reviewing designs, adding forms, implementing navigation, checking color contrast, or preparing for production launch. Covers the 80/20 of accessibility that catches most issues.

Answer Engine Optimization and Generative Engine Optimization expertise

REST API and interface design conventions for production applications. Use when: designing API endpoints, creating route handlers, defining request/response schemas, handling API errors, adding pagination, versioning APIs, or reviewing API architecture.

Auto-generates API documentation from codebase analysis. Detects endpoints, schemas, authentication patterns, and produces OpenAPI specs or markdown docs. Runs post-sprint or pre-release. Use when: "generate API docs", "document endpoints", "create OpenAPI spec", "API documentation", "document this API", "swagger docs", or when the project has API endpoints that need documentation.

Authentication and authorization patterns for production applications. Use when: adding user login, signup, password reset, social login, role-based access, session management, JWT tokens, OAuth2, MFA, or any auth-related feature. Also use when reviewing auth security.

Bootstrap an existing codebase for the CKS lifecycle — scans the project, runs guided intake, generates CLAUDE.md, and initializes .prd/ state. Use when: "bootstrap", "set up", "initialize", "configure for this project", "generate CLAUDE.md", "scan my codebase", or any variation of setting up CKS tooling in an existing project.

Simplifies code for clarity and maintainability while preserving exact behavior. Use when: refactoring for readability, reviewing complex code, after a feature works but feels heavy, during code review when complexity is flagged, or when consolidating scattered logic.

Researches a topic, library, or API using available tools (Context7, Firecrawl, WebSearch) and produces a persistent context brief in .context/ that informs future coding sessions. Use when the user wants to pre-research a technology before coding with it.

Non-negotiable agent operating behaviors for vibecoding — surfaces assumptions, manages confusion, pushes back on bad patterns, enforces simplicity, maintains scope discipline, and verifies with evidence. Use when: any agent starts work, quality degrades, agent cuts corners, agent over-engineers, or agent makes silent assumptions.

Database schema design, migration discipline, and data modeling for production applications. Use when: designing database tables, creating migrations, choosing between SQL and NoSQL, adding indexes, defining relationships, or reviewing data architecture.

Debug anything — trace app runtime errors or diagnose CKS skill/agent/command issues. Language-agnostic diagnostic approach using code tracing and strategic logging. Use when: "debug", "why is this broken", "trace this error", "why did CKS do that", "what went wrong", "this isn't working", "unexpected behavior", "diagnose", or any variation of debugging app code or CKS plugin internals.

Multi-hop recursive research agent — takes a topic and does deep, iterative investigation across configurable sources (Perplexity, Context7, Firecrawl, WebSearch, HuggingFace, aHref, Mintlify). Unlike context-research (single-hop coding briefs), this skill produces strategic intelligence reports with confidence scores, source comparisons, and contradiction flagging. Use when: "research", "deep dive", "investigate", "analyze market", "competitive analysis", "compare technologies", "tech evaluation", "what are the options for", "how does X compare to Y", "who are the competitors", or any variation of strategic/market/technology research. Do NOT use for quick coding reference lookups — that's context-research.

DESIGN.md generation — creates plain-text design system documents that AI agents (Stitch, v0, Lovable, Cursor) read to generate consistent UI. Extracts brand identity from websites, Canva kits, or guided Q&A and produces a standardized 9-section DESIGN.md. Use when: "design system", "DESIGN.md", "generate design tokens", "brand to design system", "UI consistency", "design language", or when the user wants AI tools to produce visually consistent interfaces.

Environment separation and configuration management for production applications. Use when: setting up dev/staging/production environments, managing environment variables, configuring secrets, adding feature flags, or deploying across environments.

Classify failures into structured categories and select recovery recipes. Use when: diagnosing errors, sprint failures, QA failures, build errors, test failures, MCP issues, branch conflicts, or any failure that needs classification before repair. Enables "recovery before escalation" pattern.

Domain guardrail rules — generated at bootstrap time based on detected stack. Produces scoped .claude/rules/ files for security, testing, database, and docs.

Creative brainstorming and idea refinement expertise — SCAMPER, 5 Whys, How Might We, comparison matrices, angle variation, and stress-testing. Use this skill when brainstorming project ideas, refining vague concepts, comparing competing directions, or stress-testing an idea before committing. Trigger on: "brainstorm", "ideate", "refine my idea", "compare ideas", "stress-test", "I have a vague idea", "help me think through", "which idea is better", or any variation of creative exploration before building.

Drives incremental development through thin vertical slices. Use when: implementing features, building new functionality, executing sprint tasks, or when the agent tries to build everything at once. Enforces one-feature-at-a-time discipline with test-verify-commit cycles.

Project enabler — takes a raw idea and transforms it into a fully scaffolded project with research-backed design artifacts (ERD, schema.sql, PRD, API contract, architecture) and a personalized .claude/ ecosystem. Integrates deep market research via Perplexity API and monetization strategy via /monetize. Use this skill whenever the user pitches a new project idea, wants to start a project from scratch, says "kickstart", "new project idea", "I have an idea", "let's build", "project enabler", or any variation of going from idea to implementation-ready. Always use this skill before /bootstrap when starting from zero.

Language-specific coding rules — generated at bootstrap time based on detected stack

Migrate CKS project state files across plugin versions. Detects version gaps, applies structural changes to .prd/, .learnings/, .monetize/, .context/ directories and state files. Use when: "migrate", "upgrade", "version mismatch", "state migration", "update project state", or when session-start hook reports a version gap.

Business monetization evaluation and strategy — analyzes projects or business descriptions using evidence-based tier evaluation (Strong/Possible/Weak) with explicit assumption chains, legal/compliance gating, and user-reviewed market research. Produces an honest business case where every revenue figure traces back to cited sources and stated assumptions. Use this skill whenever: evaluating monetization options, pricing strategy, revenue models, business model analysis, or when the user says "monetize", "revenue model", "pricing strategy", "how to make money", "business model", "open source monetization", "SaaS pricing", "freemium strategy", or any variation of business monetization planning. Also trigger when the user asks about competitor pricing, market sizing, or go-to-market strategy.

Application monitoring, logging, and observability for production applications. Use when: setting up error tracking, adding logging, creating health endpoints, configuring alerting, preparing for production, or when debugging production issues.

No-code automation specialist — builds, debugs, migrates, and optimizes workflows across n8n, Make.com, Workato, and Zapier. Platform-adaptive: asks which platform then tailors approach, tools, and documentation. Use when: "build workflow", "n8n", "make.com", "automation", "no-code", "zapier", "workato", "webhook", "integrate", "workflow", or any variation of automation building.

Performance optimization and Core Web Vitals for production applications. Use when: optimizing page load, measuring Core Web Vitals, reducing bundle size, fixing N+1 queries, optimizing images, adding caching, running Lighthouse audits, or when users report slowness.

Product Requirement Document creation and feature lifecycle management — 5-phase cycle from discovery through design, sprint execution, review, and release management with a living roadmap. Use this skill whenever: creating a new feature, starting a new piece of work, building a PRD, planning implementation, discussing requirements, updating the project roadmap, checking project progress, or when the user says "new feature", "add feature", "I want to build", "let's plan", "create a PRD", "what's the roadmap", "what's next", "update progress", "discover this feature", or any variation of feature planning and tracking. Also trigger when the user references existing PRDs, wants to modify scope, reprioritize work, or asks about project status.

Product maturity stage management — defines quality gates for Prototype, Pilot, Candidate, and Production stages. Use when: starting a new project, during discovery phase, before deployment, when deciding what to test or secure, when promoting between environments, or when the user asks 'is this ready for production'.

Best practices for Remotion — programmatic video creation in React. Use this skill whenever working with Remotion code: compositions, animations, timing, sequencing, audio, captions, 3D, charts, transitions, fonts, GIFs, Lottie, FFmpeg, or rendering. Trigger on: "remotion", "video composition", "react video", "animation timeline", "programmatic video", "render video", "@remotion/", "useCurrentFrame", "interpolate", "spring", "Sequence", "AbsoluteFill", or any variation of building videos with React.

Self-learning retrospective agent — analyzes what worked and what didn't after shipping, extracts conventions, patterns, and gotchas, tracks velocity metrics, and proposes CLAUDE.md updates. Creates compound improvement: every ship cycle makes the next one better. Use when: "retro", "retrospective", "what did we learn", "session review", "improve workflow", "what went wrong", "analyze this session", or automatically after /cks:ship completes. Also triggers on: "update conventions", "what patterns are we using", "track velocity".

Research-Plan-Implement sub-cycle methodology for the CKS feature lifecycle. Defines the R-P-I sequence within each phase, quality gates between stages, artifact contracts, and iteration-aware refresh. Use when: checking R-P-I status, enforcing research-before-planning gates, validating plan-before-implementation gates, refreshing stale research on iteration loops, or when the user says "rpi", "research plan implement", "quality gates", "artifact handoff", "what stage am I in", "why is planning blocked", or any variation of R-P-I sub-cycle management.

Security hardening and OWASP Top 10 prevention for production applications. Use when: reviewing security, handling user input, managing secrets, configuring authentication, setting up HTTPS, adding CSP headers, auditing dependencies, or preparing for production deployment.

Local SEO expertise for rank-and-rent sites without GBP

Pre-launch readiness checklist for production deployment. Use when: preparing to deploy, promoting to production, running release quality gates, or when the user asks 'are we ready to launch'. Covers code quality, security, performance, accessibility, infrastructure, and documentation gates.

Test-driven development discipline and testing strategy for production applications. Use when: writing tests, fixing bugs, implementing features, running test suites, choosing what to test, or when the agent skips testing. Enforces RED-GREEN-REFACTOR cycle and the Prove-It Pattern for bug fixes.

11 hooks across 5 events