Browse reusable Agent Skills, each with a clear purpose and practical guidance.
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.
Always-on code-review persona. Reviews code for logic errors, edge cases, state management bugs, error propagation failures, and intent-vs-implementation mismatches.
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.
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.
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.
Always-on code-review persona. Reviews code for premature abstraction, unnecessary indirection, dead code, coupling between unrelated modules, and naming that obscures intent.
Work heavyweight framework or library tasks with planning-first research, selective deep analysis, and rigorous handoff
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.
Review performance lanes with GitHub-scale tactics not owned by Vercel React rules: cohort segmentation, repeated-unit budgets, interaction-level INP, memory tagging, degradation contracts, browser trace proof, and production dashboards.