craft

This skill should be used when the user asks to "plan chunks", "break this down", "plan the implementation", or when a story has status planning and needs implementation details before building. Required before any story can be implemented. Transforms story sparks into detailed chunk-by-chunk implementation plans with full technical specifics, file lists, and risk analysis. Supports parallel planning of multiple stories via batch mode.

Adhoc workflow for small targeted changes to existing behavior or appearance, without the full story ceremony. Use when the orchestrator encounters a bug with a clear root cause and surgical solution, OR a small enhancement to something already built (a different icon, wording, spacing, color). Triggers on: 'fix this', 'this is broken', 'the alignment is off', 'that button doesn't work', 'quick fix', 'patch this', 'tweak this', 'change the icon', 'adjust the wording', post-story corrections, or any situation where the write gate blocks a small targeted change. Acts NOW - deferred work belongs in the notebook. Do NOT use for new features, design exploration, or changes requiring creative spark.

This skill should be used when the user asks to "brainstorm", "explore options", "get creative", "what if we...", or selects "Let's get creative" during story or cycle creation. Also appropriate when the user describes a vague feature idea without clear direction. Generates 2-3 creative options with trade-offs, visual direction for UI stories, and wireframes.

Use this skill when the user wants to discover, define, or refine their product's aesthetic identity. Triggers on "what should this feel like?", "help me figure out the vibe", "something feels off visually", "I want it to feel like [X]", "define the visual language", or when a project has no established design direction. This is the art director skill - it helps users articulate something they can feel but can't name. Also handles quick cohesion checks when the orchestrator needs one during cycle planning.

This skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly establishes a project-wide pattern like "from now on all forms should use this approach". Formalizes approved decisions into locked standards that the system enforces going forward. Not needed for story-scoped decisions — only for project-wide patterns.

This skill should be used when validate-chunk reports errors or failures, when the user asks to "fix these errors", "resolve validation issues", "refine this chunk", or when specific build, lint, or type errors need surgical fixes. Makes precise, targeted edits to resolve specific validation issues without over-engineering.

This skill should be used when validate-chunk reports test failures specifically, when the user says "tests are failing", "figure out what's wrong with the tests", "fix the failing tests", or when test assertions don't match expected output after chunk implementation. Triages whether the test or the implementation is wrong and fixes the correct one.

Enforcement layer for chunk and story validation. Invokes the chunk-validator agent (haiku), enforces the verdict, routes failures to refine-chunk or test-fix, captures CLI learnings. The orchestrator invokes this skill — never the agent directly.

This skill should be used when a story has been captured but content direction is unresolved - the spark describes WHAT to build structurally but not WHAT goes in it. Reads the story spark, splits it into Resolved (structurally clear) vs. Assumed (would have to guess) content dimensions, and surfaces each assumption for the human to confirm, correct, or expand. Also classifies implementation risk tags (has-variants, has-data-pipeline, has-animation, has-touch-targets, diverges-from-existing) so plan-chunks translates them into acceptance criteria that name the implementation mechanism. Captures answers into

Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, take snapshots, or triage a live app.

Request write permission from the user before making file changes. MUST be invoked before any write attempt when the write gate is closed. Creates scoped approval via AskUserQuestion + TaskCreate, opens the write gate, and closes it when work is done. Triggers: write hook blocks an edit, agent is about to write files outside .craft/, agent needs to modify project source files. This skill requires user approval 100% of the time - never bypass AskUserQuestion.