shipkit-get-skills
Discover and install skills and plugins from the Claude Code ecosystem
shipkit-dev-plan
Breaks a framework spec into implementation steps with file ownership, dependencies, and phase gates. Outputs a plan compatible with shipkit-dev-team for parallel execution. Use after running shipkit-dev-spec.
shipkit-semantic-qa
Semantic QA — define inputs/criteria, generate test scripts, Claude judges API outputs or UI screenshots against quality criteria. Triggers: 'semantic qa', 'quality check', 'visual qa', 'judge outputs', 'QA suite'.
shipkit-implement-independently
Spawn an independent implementation agent in an isolated git worktree. Creates parallel work that can be merged back via PR. Use when you want to implement something independently in the background.
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
shipkit-get-mcps
Discover and install MCP servers for enhanced Claude capabilities
shipkit-why-project
Use when defining project vision and strategic direction. Triggers: 'why this project', 'define vision', 'project goals', 'what are we building'.
shipkit-qa-visual
Visual QA with dual artifacts: maintains a user-confirmed UI goals document (pages × personas × goals), then generates and runs Playwright tests against those goals. Auto-installs Chromium, runs headlessly, captures screenshots.
shipkit-spec
Use when user describes a feature to build. Triggers: 'spec this', 'create specification', 'define requirements', 'I want to build'.
shipkit-verify
Verify and fix — review changes across 12 quality dimensions, auto-fix critical issues, loop up to 4 times. Use after a chunk of work or before commit.
shipkit-ux-audit
Use when auditing implemented UI for missing UX patterns. Triggers: 'audit UX', 'check UX', 'missing patterns', 'UX gaps'.
shipkit-preflight
Aggregates project context and audits production readiness against a comprehensive SaaS checklist. Routes to prerequisite skills when context is missing.
shipkit-claude-md
Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.
shipkit-lint-relentlessly
Relentlessly fix lint and formatting errors until the codebase is clean — repeatedly runs linters and applies fixes in a loop. Use for code cleanup, PR preparation, style fixes, or whenever you need to make lint pass.
shipkit-feedback-bug
Process user feedback into investigated bug specs with root cause analysis. Triggers: 'triage feedback', 'process bug reports', 'user testing feedback'.
Shipkit Engineering Definition
Define the technical approach — mechanisms, design decisions, stack direction, and component structure for building the product. Triggers: 'engineering approach', 'how to build this', 'technical design', 'mechanisms'.
shipkit-framework-integrity
Validates Shipkit framework integrity before release. Checks for broken references, manifest/disk sync, installer validity, hook references, cross-skill dependencies, documentation accuracy, and Claude Code changelog compatibility. Auto-fetches latest changelog and flags deprecated patterns, unknown hook events, and feature adoption gaps. Uses caching to skip unchanged files. Use when preparing releases or after refactoring.
shipkit-goals
Derive measurable success criteria from the solution blueprint. Triggers: 'success criteria', 'how do we measure', 'goals', 'stage gates'.
shipkit-codebase-index
Generate project index for faster codebase navigation. Triggers: 'index codebase', 'create index', 'map project'.
shipkit-data-contracts
Use when validating data shapes across layers or checking type alignment. Triggers: 'validate contracts', 'check types', 'data shape mismatch'.
shipkit-dev-team
Orchestrates Shipkit framework development using Agent Teams. Creates coordinated teams from dev plans for parallel implementation, review, and release. Use when a framework change is big enough for team execution.
shipkit-dev-review
Reviews framework changes for design quality, pattern consistency, Claude Code (CC) compatibility, and Skill Value Test compliance. Goes beyond structural integrity to catch design issues. Use after implementing framework changes, before release.
shipkit-communications
Use when a user wants to visualize or present Shipkit content as HTML. Triggers: 'create presentation', 'visualize this', 'HTML report'.
shipkit-master
Autonomous orchestrator that assesses project state, decides what to do next, and routes user requests to appropriate shipkit skills. Auto-loaded via session-start hook.
shipkit-architecture-memory
Two modes: (1) Solution Architect — proposes complete architecture from product definition, stack, and specs. (2) Decision Logger — logs individual architecture decisions. Triggers: 'propose architecture', 'log decision', 'architecture choice'.
shipkit-test-cases
Generate and maintain code-anchored test case specifications. Use when setting up test coverage, reviewing what to test, or before test-relentlessly.
shipkit-dev-spec
Specs framework changes for the Shipkit repo — new skills, agents, hooks, refactors, or architecture changes. Forces design decisions before implementation. Outputs a structured spec to .claude/specs/. Use when planning any non-trivial framework change.
shipkit-dev-release
Manages Shipkit release process — version bump, validation, changelog, counts update, and pre-push checklist. Ensures nothing ships broken. Use when preparing a new Shipkit version for GitHub.
shipkit-project-context
Use when starting a new project or refreshing tech stack context. Triggers: 'scan project', 'what's my stack', 'refresh context', 'generate stack'.
shipkit-product-discovery
Use when defining users, personas, or user journeys. Triggers: 'who are users', 'create personas', 'user research', 'user stories'.
shipkit-detect
Unified detection skill that scans artifacts after skill completion and creates work queues for follow-up skills. System hook infrastructure - auto-triggered by router hook, not user-invocable.
shipkit-user-instructions
Use when there are manual tasks the user must complete. Triggers: 'create task', 'track TODO', 'user needs to', 'manual step required'.
shipkit-thinking-partner
Use when the user needs to think through decisions, explore trade-offs, or challenge assumptions before acting. Triggers: "think with me", "help me decide", "what am I missing?", "devil's advocate", "pre-mortem".
shipkit-plan
Use when a spec exists and user wants implementation steps. Triggers: 'how to implement', 'create plan', 'plan this', 'what are the steps'.
Shipkit Product Definition
Define what to build — the features, UX patterns, and differentiators that address discovered user needs. Triggers: 'product definition', 'what to build', 'features', 'solution design'.
shipkit-update
Install or update Shipkit via npx. Detects existing installations, archives them safely, and intelligently merges user content with new version.
shipkit-work-memory
Log session progress and save resume state. Infers state from the conversation and Git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
Shipkit Team
Create an agent team from an implementation plan to build features in parallel. Reads plan.json, decomposes tasks by file ownership, spawns implementer and reviewer teammates with quality gates. Use when ready to implement a plan with parallel team execution.
shipkit-integration-docs
Use when you need current API patterns for external services. Triggers: 'fetch docs', 'integration help', 'current API patterns', 'how to use [service]'.
shipkit-scout
Fetches latest Claude Code documentation, changelog, and GitHub issues to detect new features, breaking changes, and community patterns. Writes a structured scout report for downstream analysis. Use when checking what's new in Claude Code.
shipkit-cleanup-worktrees
List and clean up stale implementation worktrees created by /shipkit-implement-independently. Shows PR status and age for each worktree. Use when worktrees accumulate and need cleanup.
shipkit-dev-team-status
Shows current Agent Team status — active teammates, task progress, phase gates, and blockers. Reads team-state file and task list to produce a progress dashboard. Use during team execution to monitor progress.
shipkit-analyst
Maps Claude Code changes to Shipkit gaps. Reads scout report and audits all skills, agents, hooks, and settings against current CC capabilities. Identifies deprecated patterns, missing features, and update opportunities. Use after running shipkit-scout.
shipkit-scale-ready
Audits production systems for scale readiness — observability, performance, reliability, and operational maturity. For teams with traction preparing to grow.
shipkit-ideator
Brainstorms new skill opportunities, workflow improvements, and composition patterns based on analyst findings. Produces ranked opportunity cards with effort/impact scores and implementation sketches. Use after running shipkit-analyst.
Shipkit — Build Relentlessly (shipkit-build-relentlessly)
Build and compile relentlessly until success — keeps fixing build errors, type errors, and compilation failures in a loop. Use for migrations, setup, major refactors, or when you need to make it compile.
shipkit-test-relentlessly
Run tests relentlessly until all pass — keeps fixing failing tests in a loop until green. Use for TDD, fixing test failures, ensuring green builds, or when you need to make tests pass.
Shipkit Documenter
Document bugs, ideas, improvements, and decisions. Manages docs/development/manifest.json as the central registry.