Run a controlled matrix comparison of approaches over a set of tasks — e.g. the kitsoki pipeline vs a naive single prompt, across a harness/model candidate matrix — scoring outcome, compliance, cost, and time, adjudicating implementation-coupled oracles, then regenerating a report + slidey deck offline with zero re-spend. Use when the user says "bake-off", "compare kitsoki vs single-prompt", "run a matrix comparison", "which model/harness is best at X", "kitsoki-vs-X study", "benchmark these approaches on these tasks", or wants an evidence-backed, cost-accounted comparison of contenders across a model grid. Generalises tools/bugfix-bakeoff (the reference implementation).

Debug problems with the kitsoki web UI (`make web-dev` / `kitsoki web`). Use when the user reports 504s, blank pages, SSE stream stalls, session errors, proxy failures, or wants to inspect web server logs. Covers log locations, common failure patterns, proxy/backend interaction, and the RPC surface.

Heuristic UI layout & usability review of the kitsoki web UI. Walks the onboarding tour manifest at mobile/tablet/desktop, runs a deterministic DOM-geometry + axe-core audit per step, then fans the frames out across MULTIPLE read-only claude vision agents (one per surface, so no single agent holds every image) that critique each surface against a Nielsen-based heuristic catalog, adversarially re-checked, and emits a gated review-report.md + verdict.json with concrete fixes. Use when asked to review / critique / find layout, usability, responsive, or accessibility problems in the kitsoki web UI — distinct from kitsoki-ui-qa (which checks "does the demo SHOW scenario X").

Validate UI evidence (a screenshot for simple cases, a video for complex flows) against the bug or plan being verified plus usage scenarios — the inverse of kitsoki-ui-demo. Picks the evidence form by complexity, extracts deterministic frames, has a read-only `claude` vision agent judge each scenario against cited frames AND whether the evidence is complete for the stated bug/plan, adversarially re-checks every pass, and emits a gated qa-report.md + verdict.json. Use when asked to QA / review / validate / sign off on a demo, walkthrough, screenshot, or bug-fix proof, or to gate one in CI.

Produce a deterministic, no-LLM demo / tour video of the kitsoki web UI (plus per-scene screenshots and a shareable MP4 / GIF / contact sheet) by driving a real `kitsoki web` server through Playwright. Use when asked to make, record, refresh, or author a tour demo video, feature-spotlight tour, walkthrough video, demo, or screen-capture of the kitsoki browser UI — whether a tour of one feature (golden example: agent-actions), the generic onboarding tour, or a full-product walkthrough. Also covers turning a REAL LLM-driven dogfood session into a deterministic demo: generating the no-LLM flow fixture + host cassette from a recorded trace via `kitsoki trace to-flow` (no hand-authoring, no LLM re-interpretation). Triggers on phrasings like "make a tour demo video", "record a demo of <feature>", "feature tour video", "walkthrough video", "turn this dogfood trace/session into a demo video".

Author and edit kitsoki stories — the YAML state machines under `stories/<name>/`. Use when the user wants to add or modify a room, intent, transition, effect, host call, world var, view, prompt, flow fixture, import, exit, or phase template. Covers YAML shape, effect/host vocabulary, typed view elements, style guide, load-time invariants, and the authoring loop. For "this room misbehaves / bounced to idle" reach for `kitsoki-debugging` instead.

Organize, review, document, or validate Kitsoki media artifacts, including product-site tour demo videos, rrweb captures, staged VitePress media, complete-product-tour sections, and Slidey decks with embedded rrweb clips. Use when Codex is asked to find demo videos, clean up media layout, add media validation to tests, decide where a demo/deck artifact belongs, update docs/media guidance, or troubleshoot product-site media staging without recording live LLM runs.

Debug and test the Kitsoki studio MCP server and its tools from the repo checkout. Use when working on `kitsoki mcp`, `cmd/kitsoki/mcp_test_client.go`, `internal/mcp/studio`, MCP tool registration, stdio MCP handshake failures, visual MCP tools (`visual.open`, `visual.observe`, `visual.act`), `mcp-test` output, or when the user wants to verify studio MCP changes without reloading an LLM client.

Diagnose kitsoki-dev dogfood / bugfix / feature-story bugs. Use when the user reports "going back to idle", "silent bounce", "stuck at <state>", or any "this room didn't do what I expected" complaint. Drives the same state machine the TUI uses, against the real on-disk repo state, without spinning up a session. Surfaces the underlying host-call errors that the TUI's `on_error:` arcs swallow.

Write or review the documentation for a Go package under internal/ to the kitsoki standard. Use when adding a new package, when a package's doc.go / exported-symbol comments / runnable examples need writing or auditing, or when the user asks "is this package documented well", "bring this up to the doc standard", or "review the docs for <pkg>". Covers the eight-point rubric (doc.go, sections, non-goals, per-symbol "why", contracts, named constants, Example tests, live references), the paragon to copy, and the verification commands.

Run a bug-fix bake-off on ANY external/open-source repo to answer "should I use kitsoki for my project?" — find real filed-issue bugs with regression-test PRs, pin reproducible baselines, onboard the repo, drive the kitsoki bugfix pipeline LIVE under one or more non-Claude provider profiles (GPT-5.5 / GLM-5.2 / …), grade each fix deterministically against the PR's own hidden oracle, and produce a report + slidey deck comparing models and cost vs the real maintainer fix. Use when the user says "bake off <repo>", "benchmark kitsoki on this repo", "should I use kitsoki for my project", "compare <modelA> vs <modelB> fixing bugs in <repo>", "run the external bake-off", or wants to evaluate kitsoki's prompts/patterns on real third-party code. Covers onboarding AND the live-drive tuning needed to get good working cases. Distinct from dogfood-marathon (kitsoki's OWN bugs over the MCP-driver agent) and matrix-task-comparison (kitsoki-vs-naive-prompt on fixed tasks).

Process a backlog of real cases (bugs / deliveries / ship-its / tickets) by driving a kitsoki story (bugfix, delivery-tail, ship-it, …) LIVE over each one via the kitsoki-mcp-driver agent, independently verifying every deliverable, capturing friction as findings, and hardening the story/prompts for GENERAL use WITHOUT OVERFITTING to the cases in the run. Use when the user says "run a dogfood marathon", "smash these bugs through bugfix", "process this backlog live", "dogfood <story> over these tickets and fix the pipeline", or wants a marathon report (outcomes / verdicts / cost / fixes shipped / findings). Distinct from story-coverage-mining (transcript-driven coverage) and matrix-task-comparison (harness×model bake-off on fixed tasks).

Review Rust changes against idiomatic Rust guidelines and ToolKit framework rules. PR mode posts inline comments on GitHub; local mode reviews a branch against main and writes a markdown report.

Create, test, validate, and deploy Insight Connectors. Supports both nocode (declarative YAML) and CDK (Python) connector types. Commands: /connector create <name>, /connector test <name>, /connector schema <name>, /connector deploy <name>, /connector validate <name>.

Audit dbt models and connector configurations against the data-flow conventions in .cf-studio/config/rules/architecture.md. Verifies engine=ReplacingMergeTree, order_by=['unique_key'], silver delete+insert, read-time dedup of every RMT read (FINAL/QUALIFY/LIMIT 1 BY/union_by_tag), unique_key formula, bronze→RMT promotion, ephemeral usage for Rust-owned tables, and Airbyte append-only sync mode. Reports deviations with file paths and line numbers.

Invoke when the user asks to author or review any SDLC artifact or run an SDLC kit operation — write/revise a PRD, ADR, DESIGN, DECOMPOSITION, or FEATURE; implement a FEATURE in code; review or report status on a GitHub PR; or migrate OpenSpec artifacts. Kit `sdlc` extensions — artifacts: ADR, CODEBASE, DECOMPOSITION, DESIGN, FEATURE, PRD (+ PR review/status templates); workflows: doc-prd, doc-adr, doc-design, decompose, doc-feature, implement, change-impact-analysis, reverse-engineer, migrate-openspec, pr-review, pr-status.

Debug Slidey render, layout, CLI, MCP, browser, rrweb/video, PDF/PNG/MP4, and deck-output failures. Use when Codex needs to diagnose a broken or ugly Slidey deck, bad scene layout, render/audit/check failure, stale render bundle, Puppeteer/browser issue, MCP slidey tool problem, timing/narration overrun, or mismatch between viewer and exported output.

Author and iterate on declarative videos using the slidey pipeline (a JSON scene spec rendered to a narrated MP4). Use when the user asks to create a new video, add/edit a scene, tweak narration, adjust visuals, re-cut a video, or generate an MP4 from a JSON spec. Covers the iteration loop, scene-type vocabulary, narration budgeting, and the gotchas accumulated across many cuts.

Review Rust changes against idiomatic Rust guidelines and ToolKit framework rules. PR mode posts inline comments on GitHub; local mode reviews a branch against main and writes a markdown report.

Analyze how the GTS (Global Type System) is used in a Gear — defined types, declared instances, and references across sdk / main / plugin / docs. Thin wrapper around the `gts-analyze` CLI under tools/.