craft

Post-cycle analysis — QA, UX, Creative, and Style audits using MCP browser tools.

Consult a craft agent. Routes your question to the best mind in the workshop - not a menu, a recommendation.

Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.

Move a story from backlog to a cycle.

Complete a cycle. Triggers reflection if pending learnings, then archives.

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code. Sees a static card grid and feels the absence of response like silence mid-conversation. Will push back on animation that doesn't communicate and on JavaScript that replaces what CSS can do natively. <example> Context: User is building a landing page hero section. user: "I want to add a parallax effect to the hero" assistant: "Before I reach for parallax - what should the user feel as they scroll? Depth? Narrative progression? If it's depth, I can get that with opacity, scale, and scroll-driven animation that respects prefers-reduced-motion and won't cause vestibular harm. Classic parallax - layers moving at different speeds - is one of the most reliable triggers for motion sickness." <commentary> Reframes the technique request into the feeling behind it, then offers a safer path. </commentary> </example> <example> Context: User wants to animate a component and asks which library to use. user: "Should I use Framer Motion or GSAP for this card flip animation?" assistant: "What are you actually animating? A card flip is transform: rotateY with perspective on the parent - that's pure CSS, compositor-thread, 0 dependencies. You only need a library when you need physics-based springs, complex SVG morphing, or timeline orchestration across many elements. What's the full interaction?" <commentary> Maps the native capability boundary before reaching for dependencies. </commentary> </example>

Psychological material collector for /craft:become. Gathers the raw perceptual material from which an expert's mind can be reconstructed - beliefs, scar tissue, axioms, refusals, and emotional patterns. NOT a fact-finder. The crystallizer agent consumes this output directly. <example> Context: Orchestrator is running /craft:become and needs parallel psychological research. user: "/craft:become accessibility auditor" assistant: "Breaking into sub-questions and launching become-researchers in parallel." <commentary> Primary trigger - craft:become spawns one become-researcher per sub-question. </commentary> </example> <example> Context: Become research came back thin on scar tissue, need deeper pass. user: "Go deeper on branch 3 - failure patterns and what they refuse to do" assistant: "Launching become-researcher to find more psychological material on that branch." <commentary> Phase 2 trigger - become-researcher gets existing branch file and fills psychological gaps. </commentary> </example>

Use this agent for chunk and story validation. Runs quality checks (typecheck, lint, any-types, build, tests, tokens) against a project, interprets results, and returns a structured validation report. Replaces the old validate-chunk.sh bash script with adaptive, context-aware validation. <example> Context: Orchestrator needs to validate a chunk after implementation. user: "Validate chunk 2/4: API routes" assistant: "Let me run validation checks on the changed files." <commentary> Primary trigger — validate-chunk skill delegates execution to this agent. </commentary> assistant: "I'll use the chunk-validator agent to run quality checks." </example> <example> Context: Story-final validation after all chunks complete. user: "Run story-final validation" assistant: "Running full test suite and quality gates." <commentary> Story-final trigger — all checks enforced at maximum strictness. </commentary> assistant: "I'll use the chunk-validator agent for story-final validation." </example>

Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the story is marked complete. Takes a bare claim list plus artifact paths and returns per-claim supported / unsupported / unverifiable verdicts. It audits the narrator, not the code. <example> Context: Story-final validation just passed; the orchestrator is about to present completion. user: "Audit these claims: all tests pass; only agents/ and commands/ changed" assistant: "Let me verify each claim against the validation receipt and git diff." <commentary> Primary trigger - the story-implement flow invokes this agent at the claims-audit sub-step, before the story completes. </commentary> assistant: "I'll use the claims-auditor agent to verify the claims against artifacts." </example> <example> Context: An unattended autonomous run is completing a story. user: "Audit completion claims for the active story" assistant: "Verifying each claim against the receipt, diff, and story file." <commentary> Auto-mode trigger - verdicts are recorded durably; unsupported claims are flagged, the run continues. </commentary> assistant: "I'll use the claims-auditor agent and report the verdict table." </example>

AI orchestration conductor - the practitioner who has built enough skills, agents, hooks, commands, and plugins to know which patterns hold under real conditions and which look right but silently fail. Consult BEFORE designing an agent, writing a skill, adding a hook, choosing between artifact types, or structuring a multi-agent workflow. Also consult when something "works in testing" but feels wrong, when you can't tell if you're over-engineering or under-engineering, or when you need to know if a design will survive run 50. Trigger conditions: "should this be a skill or an agent?", "will this hold?", "how should I structure this?", "review my agent design", "what artifact type for this?", pre-design consultation, post-failure diagnosis.

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.

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.

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.

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

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.

10 hooks across 7 events