Shipkit — AI-assisted product development framework for Claude Code. Skills, agents, and workflows for shipping MVPs fast.
Skill Claude Code
Internal reviewer — assesses strategic artifact coherence. Checks vision/why alignment, goal completeness, stage realism. The Direction coherence-review gate, dispatched by the engine (via shipkit-direction), not for direct use.
Skill Claude Code
Internal reviewer — assesses planning artifact alignment. Checks definitions agree, specs cover roadmap, no gaps. A per-unit reviewer invoked by a caller (the engine in steered mode or a direction/planning caller), not for direct use.
Skill Claude Code
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.
Skill Claude Code
Audits production systems for scale readiness — observability, performance, reliability, and operational maturity. For teams with traction preparing to grow.
Skill Claude Code needs its repo
Semantic QA — define inputs/criteria, generate test scripts, Claude judges outputs or screenshots against criteria. Also scores a built app's fidelity (completeness + essence) against captured intent. Triggers: 'semantic qa', 'quality check', 'visual qa', 'judge outputs', 'QA suite', 'fidelity scorecard', 'score…
Skill Claude Code
Build a spec'd + planned feature to done — the BUILD entry point. Drives the plan to a ground-truth bar via the orchestration engine (autonomous). Triggers: 'ship it', 'ship this', 'build this', 'run the build', 'build the plan'.
Skill Claude Code
Prioritize which specs to write first from product + engineering definitions. Triggers: 'spec roadmap', 'what to spec first', 'prioritize features', 'spec backlog'.
Skill Claude Code
Use when user describes a feature to build. Triggers: 'spec this', 'create specification', 'define requirements', 'I want to build'.
Skill Claude Code
Define project stage, scope constraints, and graduation criteria. Set mode configures the stage; evaluate mode assesses readiness for human approval.
Skill Claude Code
Generate and maintain code-anchored test case specifications. Use when setting up test coverage, reviewing what to test, or before team implementation.
Skill Claude Code
Use when user needs to think through decisions, explore trade-offs, or challenge assumptions. Triggers: 'think with me', 'help me decide', 'what am I missing?', 'devil's advocate', 'pre-mortem'.
Skill Claude Code needs its repo
Install or update Shipkit via npx. Detects existing installations, archives them safely, and intelligently merges user content with new version.
Skill Claude Code
Use when there are manual tasks the user must complete. Triggers: 'create task', 'track TODO', 'user needs to', 'manual step required'.
Skill Claude Code
Use when auditing implemented UI for missing UX patterns. Triggers: 'audit UX', 'check UX', 'missing patterns', 'UX gaps'.
Skill Claude Code
Use when defining project vision and strategic direction. Triggers: 'why this project', 'define vision', 'project goals', 'what are we building'.
Skill Claude Code
Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: