ychampion

Collapse multiple change sources into one caller-facing boolean so headless bootstraps know whether a downstream refresh is necessary.

After awaiting persistence work, update the shared budget state for each `tool_use_id` exactly once so no concurrent reader ever sees a half-committed decision.

Issue continuation nudges while the turn stays under budget, then halt once diminishing returns or the budget cap justify stopping.

Lazily extract referenced files for bundled skills so large prompts stay offline until needed.

Persist a cache-safe stop-hook context snapshot only for main session queries so later helpers can resume from stable state without fork pollution.

Sweep stale extension caches before activation, then fall back to a sticky manual-refresh flag if the live refresh fails.

Warm the authoritative cache path first, then fan out cache-only readers in parallel so derived loaders never race stale state.

Emit low-cost debug telemetry for skill-listing batches that records batch size, initial-vs-dynamic mode, and cumulative sent count without logging the payload body.

Use when answering any operator question about feedback, themes, bets, actions, briefs, or directives.

Use when urgent feedback (churn threat, outage, urgency >= 2) may warrant filing a GitHub issue.

Use when asked to fix the bug behind a bet or theme — hand off to the coder subagent and verify the result.

Use when asked to triage, run, or process new feedback — the full ingest → tag → cluster → bet → act pass.

Use when asked to write, update, or refresh the weekly product brief.

Use $morph-animation or Morph Animation to create an animated launch film, generate a motion-design video, make a kinetic typography video, animate a technical concept, create an animated explainer, create a programmatic product video, create an animated architecture diagram, make an animated announcement, create a launch opener, create a branded end card, or revise, critique, inspect, preview, and render an existing editable Morph Animation composition. Do not use for requests to record a website, demo a localhost application, revise a Morph screen recording, re-record a changed scene, capture a desktop, or edit an unrelated existing film; keep those requests outside Compose and preserve the current $morph Capture routing.

Create a self-guided clickable product demo, interactive website walkthrough, iframe-ready product tour, guided hotspot demo, branching application demo, or audience-specific interactive onboarding from a real local web application. Use only when the user explicitly invokes `$morph-interactive` or explicitly asks to use Morph Interactive; keep this separate from `$morph` video recording and `$morph-animation` motion design.

Install, configure, update, or verify Morph for Codex, Claude Code, Hermes Agent, OpenCode, or OpenClaw from the morph-public repository. Use when the user asks to set up Morph or connect its skill and MCP server. Do not use for creating or editing product stories.

Use $morph or Morph when the user asks to turn a product flow into a story, create a Story Pack, record this website, create a product demo, make a website walkthrough, demo a localhost app, scroll through a landing page, create a launch video, show how an application works, record browser steps, create a buyer video, make a social teaser, create an interactive demo, retell a product story for another audience, revise the latest demo, update only what changed, remember a verified directing preference, show or forget learned Morph preferences, run Critic, diagnose Morph, or verify the plugin. Do not use for audio-only work, voice memos, whole-desktop capture, native application recording, unrelated video editing, unsupported marketing claims without product evidence, generic source-code changes, or testing unrelated software.

Export Claude Code and Codex conversation history to Hugging Face as structured training data. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring codeclaw, reviewing PII/secrets in exports, or managing their dataset.

Export Claude Code conversation history to Hugging Face as structured training data. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring CodeClaw, reviewing PII/secrets in exports, or managing their dataset.

Use when converting verified product changes into concise public release notes.

Use when debugging a production-like issue where prior incidents, ownership, and test history may change the fix.

Autonomously research any technology, library, framework, or API. Discovers official documentation, extracts key information from authoritative sources, verifies across multiple pages, and generates a reusable Claude skill (SKILL.md) with installation, examples, and best practices.

Create, document, compose, update, review, sync, and audit React, Vue, and Svelte Storybook stories with controls, docs pages, docs-tagged story blocks, composition stories, diff-aware updates, play functions, visual diff hooks, design-token globals, provider decorators, and optional Chromatic scaffolding. Use when the task mentions Storybook, stories, `.stories.tsx`, `.stories.ts`, `.stories.svelte`, `.stories.mdx`, `argTypes`, `CSF`, `autodocs`, `parameters.docs.description`, `play()`, addon-a11y, Chromatic, visual regression, story health, story audit, preview decorators, providers, git diff story updates, Storybook component documentation, or syncing stories between frameworks. Do not use for generic UI design, framework-agnostic styling tasks, or non-Storybook component work.

Attach to the user's existing Chrome session through the official Chrome DevTools MCP server for live tab inspection, debugging, and interaction.