plate

Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

Constitutional source of truth for reusable Plate architecture and public API design. Use when introducing or changing reusable public APIs, runtime/service boundaries, builder or factory patterns, extension registration contracts, naming/layering rules, or performance-sensitive architecture.

Work heavyweight framework or library tasks with planning-first research, selective deep analysis, and rigorous handoff

Always-on code-review persona. Reviews code for premature abstraction, unnecessary indirection, dead code, coupling between unrelated modules, and naming that obscures intent.

Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes.

Fetches and analyzes GitHub issues to surface recurring themes, pain patterns, and severity trends. Use when understanding a project's issue landscape, analyzing bug patterns for ideation, or summarizing what users are reporting.

Remove a feature completely with no backward compatibility. Use when the user says "hard cut", "rip it out", "delete it", "unship", "kill this feature", or wants dead code removed instead of deprecated. Delete the surface, callers, tests, docs, comments, fallbacks, and stubs.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Create a self-contained GPT Pro or external-review prompt with full repo context, current state, evidence, and pointed review questions because the reviewer has no local file access.

Performs archaeological analysis of git history to trace code evolution, identify contributors, and understand why code patterns exist. Use when you need historical context for code changes.

Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.

Gathers comprehensive documentation and best practices for frameworks, libraries, or dependencies. Use when you need official docs, version-specific constraints, or implementation patterns.

Evaluates whether proposed technical approaches in planning documents will survive contact with reality -- architecture conflicts, dependency gaps, migration risks, and implementability. Spawned by the document-review skill.

Mine external editor repositories for portable editor-behavior tests with ClawSweeper-style discipline: multi-pass exhaustive inventory, confidence scoring, framework-specific skip reasons, Slate/Plate coverage mapping, license-aware invariant extraction, and copy/refactor/create decisions.

Turn an editor-test-harvester report into one lane-specific execution plan, e.g. process every Slate v2 candidate from a harvest through slate-plan without executing implementation.

Create or update Plate docs with conversational voice, lane-aware structure, explicit ownership, and code-backed accuracy. This is the source of truth for Plate docs style and workflow. Use for plugin pages, guides, install docs, serialization docs, API docs, and specs — anywhere both humans and agents need a clear, readable source of truth.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.

Always-on code-review persona. Reviews code for logic errors, edge cases, state management bugs, error propagation failures, and intent-vs-implementation mismatches.

Use after an execution slice to reassess whether the current tactic still serves the user's north star, then keep course, pivot, replan, or stop. Designed for long-running loops where the agent should keep moving unless a real blocker or completed lane exists.

React component architecture for creating composable, accessible components with data attributes. Use when creating/updating composable components, not for higher-level feature/page components.

Reviews planning documents for internal consistency -- contradictions between sections, terminology drift, structural issues, and ambiguity where readers would diverge. Spawned by the document-review skill.

Final review pass to ensure code is as simple and minimal as possible. Use after implementation is complete to identify YAGNI violations and simplification opportunities.

Triage and process the Slate v2 issue ledger with OpenClaw-style sweep discipline: archive-first discovery, duplicate proof, small-fix gates, exact claim rules, maintainer-safe issue output, and gitcrawl API refreshes.

Operate Clawpatch for semantic feature mapping, automated review, explicit finding fixes, revalidation, reports, and state recovery.