wizard

Use when the meta-builder routes to kind=discipline. Generates a discipline spell with the rule, excuses table, warning signs, and hard gates.

Use when the user wants to capture a repeatable task as a reusable spell, or asks "how do I build a workflow / skill / framework for X"

Use when the meta-builder routes to kind=subagent. Generates a spell that dispatches one or more subagents to do work in parallel or in isolation.

Use when the meta-builder routes to kind=workflow. Generates a workflow spell with explicit stages, checkpoints, and loop-back conditions.

Use when composing multiple spells into a chain that runs end-to-end (e.g. brainstorm -> plan -> execute -> verify).

Use when browsing what spells are available - bundled seeds, your personal library, or both. Filter by kind, audience, or update status.

Use when the user invokes /capture-this-chat or /build-spell --from-transcript. Reads a transcript and produces a context dictionary plus a draft SKILL.md, which hands off to building-a-spell at Stage 2.

Use when conducting any interview-style flow with a user (building a spell, refining one, gathering requirements). Picks depth, filters questions by relevance, matches against known shapes, and detects mid-stream pivots.

Use during try-it for kind=discipline spells. Orchestrates baseline + with-skill comparison via the discipline-mode tester to prove the rule actually changes behavior under rationalization pressure.

Use when an existing spell needs improvement based on usage. Captures what changed, re-runs the tester (mandatory), bumps the version, and saves.

Use when exporting a spell for someone else to use. Produces a portable file in either Wizard format or strict (upstream-compatible) format.

Use when starting any conversation - establishes how to find and use Wizard skills and spells, including the 1% rule

Use when shipping any non-trivial dev feature - chains brainstorm, plan, step-by-step execution, and verification before shipping

Use when doing serious research on any topic - chains literature scan, parallel research, structured review, and citation verification

Use when scoping a new feature - produces problem statement, 3-5 candidate approaches, and a recommendation with explicit alternative

Use when executing a written implementation plan - per step read, change, verify, mark done; loop back on failure

Use when turning a feature spec into a step-by-step implementation plan - file-level changes, order, checkpoints, and risks

Use when requesting feedback on work, an idea, or behavior - in a way that maximizes the chance of useful answers

Use when planning a personal or work trip - lodging, transport, daily plan, packing

Use when summarizing an article, paper, transcript, or doc - with verbatim quotes for the most important claims

Use when something is broken, failing, or not behaving as expected (any domain - software, gadget, process, plan)

Use when drafting any email - replies, cold outreach, asks, status updates, thank-yous

Use when turning raw interview notes into themes - produces themes, verbatim quotes, and decisions or hypotheses

Use when starting research on a new topic - produces a one-page map of the canonical 5-10 sources and the major positions

Use when researching N independent topics, companies, or candidates - dispatches one subagent per topic and aggregates results

Use when producing a publishable or shareable literature review - chained workflow from scope to written review with verification

Use when about to cite a source, statistic, or quote - forces verification against the actual source before the claim leaves your hands

Use when a problem feels too big or vague to start - decomposes it into pieces you can actually work on

Use when about to recommend or commit to a decision - forces naming an alternative considered and the reason it lost

Use when picking up a new topic, tool, or skill - structured plan that gets you to first useful output fast

Use when picking between options - produces a recommendation with explicit alternative considered and reason rejected

Use when prepping for any work meeting (1:1, customer call, interview, review) - 60-second-readable brief

Use when researching a company before a meeting, interview, sale, partnership, or investment

Use when replying to feedback on your work (review comments, manuscript revisions, design critique, criticism)

Use when about to declare any piece of work done, complete, shipped, or finished - in any domain

Use when finishing a piece of work - the closing pass that prevents a "done" piece from coming back at you a week later

Use when drafting a recurring stakeholder update (weekly status, monthly report, project update)