Agent
Factual extraction agent for /craft:research. Investigates ONE sub-question, extracts findings with verbatim quotes and sources, writes them to a branch file, and returns a lightweight summary. Extraction only - does NOT rank, summarize, or synthesize across findings (the research-synthesizer does that). Used in Phase…
Agent
The riff partner - a thinking companion for creative collaboration moments. Consult when brainstorming, stuck on a design, ideating a feature, debating an approach, wanting a second opinion on a half-formed thought, or when you're tired and need someone in the room rather than another instructor. Trigger conditions…
Agent
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
Agent
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
Agent
Use this agent after UI implementation or when the user requests usability and accessibility review. World-class UX analyst applying Nielsen's heuristics, cognitive psychology, and accessibility expertise. Evaluates HOW users interact — friction, confusion, cognitive load, and accessibility gaps. Context: User just…
Agent
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
Agent
Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…
Command
Post-cycle analysis — QA, UX, Creative, and Style audits using MCP browser tools.
Command
Consult a craft agent. Routes your question to the best mind in the workshop - not a menu, a recommendation.
Command
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.
Command
Move a story from backlog to a cycle.
Command
Complete a cycle. Triggers reflection if pending learnings, then archives.
Command
Design a cycle — create new cycles with planned stories, detail existing planning cycles, or quick-sketch a roadmap. Detects planning docs in .craft/planning/ and sources the cycle from them when relevant.
Command
Activate a cycle and start implementing its stories.
Command
Open your project's dashboard - the whole graph of cycles, stories, and records in one page. Rebuilds the data first, offers a page update when the shipped template moved ahead, then opens it.
Command
Live value calibration - 2-4 lettered candidates injected into the running app; click through them against real data, nothing written to source.
Command
Generate or update project documentation using the crystallized doc-writer agent. Two-pass: brief (analysis + plan) then generate (write docs). Detects first-run vs update automatically.
Command
Ask the craft guide how craft works or how to use it on your project. Read-only - it explains how craft's commands, skills, agents, and lifecycle work, and diagnoses your actual .craft/ setup. It never changes anything.
Command
One-time setup to initialize the Craft harness for a project.
Command
Live HTML mockup funnel - 3 options, converge by reacting, graduate to tweak/story/todo.
Command
Low-ceremony capture for ideas (half-formed, want to mature into stories), todos (concrete actions), and notes (durable project/team facts for future recall). One-line capture, conditional elaboration AUQ. Use BEFORE thoughts get forced into stories.
Command
Feature roadmap and planning. Manage initiatives, concepts, open questions, and story creation from planning.
Command
Switch between projects in a monorepo, or show a cross-project dashboard.
Command
Apply captured learnings to improve the Craft harness and project patterns. Converts .learnings.yaml into permanent updates.