From critic
Run multi-agent fiction review on a chapter. Dispatches reviewer tools in parallel, runs cross-review, synthesizes into readable critique. Use when the user asks to review, critique, or get feedback on a chapter.
npx claudepluginhub jdpedrie/critic --plugin criticThis skill uses the workspace's default tool permissions.
The vault path for all tool calls is: ${user_config.vault_path}
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
The vault path for all tool calls is: ${user_config.vault_path}
Run a structured multi-agent review of the specified chapter using the critic MCP tools.
$ARGUMENTS should be a chapter name (e.g., "chapter-01") or a chapter filename.
Call ALL FOUR review tools in parallel using the Agent tool:
review-analytical with the chapter namereview-immersive with the chapter namereview-structural with the chapter namereview-adversarial with the chapter nameWait for all four to complete.
Present a brief summary to the user:
Then ask: "Run cross-review, skip to synthesis, or re-run a specific reviewer?"
Call the cross-review tool twice in parallel:
Present:
Then ask: "Synthesize, or discuss specific points first?"
Call the synthesize tool with:
reviews: JSON object mapping role names to their review JSON stringsrebuttals: JSON object mapping pair names to their rebuttal JSON strings (if cross-review was run)The synthesize tool returns a JSON object with a markdown field containing the full human-readable report.
Present the markdown report directly in conversation. This is the primary output.
Offer the user these options:
update-memory tool)