Single authority for your AI-config artifacts: modular standards (core + skill/agent/hook/plugin/instruction-files) with right-sized lifecycles for each, two-tier guard + md-format enforcement hooks, shared judge agents, vendored eval harness, and an on-demand docs-currency check (sync-docs).
Skills 22 in the Claude listing
Create agent Create a brand-new Claude Code subagent (registered agent .md) from scratch. Create hook Design and author a Claude Code hook for event automation or enforcement. Create skill Create a brand-new Agent Skill from scratch. Improve agent Raise an existing subagent's quality against a measurable criterion WITHOUT changing its delegation behavior or return contract. Improve instructions Raise the quality of a project's instruction files (CLAUDE.md, AGENTS.md, references) WITHOUT changing what they commit to. Improve skill Raise an existing skill's quality against a measurable criterion WITHOUT changing its intended behavior. Restructure skill Reorganize skill architecture — split one skill into several, merge overlapping skills, or move content between SKILL.md, references, and scripts. Retire agent Safely delete, deprecate, or archive an existing Claude Code subagent. Retire skill Safely delete, deprecate, or archive an existing Agent Skill. Review agent Read-only audit of an existing Claude Code subagent — never modifies it. Review hook Read-only audit of Claude Code hook configuration and scripts — never modifies them. Review instructions Read-only audit of a project's instruction files (AGENTS.md, CLAUDE.md, .claude/rules) — never edits them. Review skill Read-only audit of an existing Agent Skill — it never modifies the skill under review. Revise agents md User-invoked pass that re-derives a project's Claude-native instruction layout — a surface AGENTS.md plus path-scoped .claude/rules/ — as a projection of the installed skill set and the actual codebas Scaffold plugin Scaffold a new Claude Code plugin and wire its components. Setup instructions Bootstrap a project's instruction files from scratch — a surface AGENTS.md plus path-scoped .claude/rules/ derived from the installed skills and the actual code. Skill creation Entry point and router for ALL work on Agent Skills. Sync docs On-demand currency check: diffs meta-dev's standards and lifecycles against current official Claude Code docs and routes drift through the update lifecycles. Update agent Change an existing agent's behavior — its prompt, tools, model, or preloaded skills — for new requirements. Update instructions Change a project's instruction-file content — AGENTS.md, CLAUDE.md, and .claude/rules/ — and re-scope a rule when its area outgrows it. Update skill Extend or change an EXISTING skill's behavior to meet new requirements. Validate plugin Read-only validation and audit of a Claude Code plugin or marketplace — never modifies what it inspects. 