Use when a task needs shared repository knowledge, project memory recall, durable documentation updates, knowledge routing, trust/safety checks, correction or consolidation of stale docs, crystallizing reusable lessons, or validation of the knowledge core.…
Use for frontend/UI build, change, redesign, polish, review, or Figma/screenshot implementation when visual quality, product-appropriate design taste, UX, responsive behavior, accessibility, component composition, or design-system consistency matters. Pair…
Use when a task asks for deep research, current external information, source-backed comparison, claim verification, source quality assessment, adversarial-source screening, repository/tool/practice evaluation, or saving researched findings into the knowledge…
Use this skill when the user asks you to implement, fix, refactor, test, review, or finish software changes that are more than a tiny mechanical edit. Use for vague coding requests like "make it work" when scope, evidence, debugging, security, or completion…
Use when temporary task state, delegation payload, cold-start resume packet, review/debug brief, or compaction snapshot must be handed to another agent, workspace, subagent, reviewer, or future session. Do not use for durable project facts, raw transcript…
Use when creating, changing, reviewing, securing, or evaluating an agent skill; deciding whether behavior belongs in a skill; designing skill trigger boundaries, bundled resources, frontmatter, eval prompts, split/merge decisions, or skill…