tooling

ACTIVATE when creating a Claude Code plugin, writing plugin.json, marketplace.json, hooks.json, or structuring plugin directories. ACTIVATE for 'Claude plugin', 'plugin.json', 'marketplace.json', 'hooks.json', 'CLAUDE_PLUGIN_ROOT'. Covers: plugin directory structure, plugin.json/marketplace.json schemas, hooks.json format (matcher + hook types), CLAUDE_PLUGIN_ROOT portability, distribution best practices, validation commands. DO NOT use for: SKILL.md writing conventions (see npx-skills-conventions), general Claude Code usage.

ACTIVATE when integrating a new Docker image, writing docker-compose.yml services, or adding external tools to a Docker stack. ACTIVATE for 'docker-compose', 'Docker image', 'container setup', 'service integration'. Covers: mandatory RTFM checklist before writing any docker-compose line (volumes, ports, env vars, healthchecks, internal architecture), image inspection commands, common anti-patterns that cause silent failures. DO NOT use for: Dockerfile writing, CI/CD pipeline configuration, Kubernetes.

ACTIVATE when defining database schemas, writing queries, creating migrations, or implementing repositories with Drizzle ORM. ACTIVATE for 'Drizzle', 'pgTable', 'drizzle-kit', 'db.query', 'db.select', '$inferSelect', 'migration'. Covers: schema definition with pgTable, relations, type inference ($inferSelect/$inferInsert), Query API vs Select API vs raw SQL decision tree, repository pattern with toDomain/toPersistence, migration workflow (always drizzle-kit generate first, never manual journal). DO NOT use for: Doctrine/PHP queries (see php-sql-conventions), general SQL formatting.

ACTIVATE when creating SKILL.md files, writing frontmatter (name/description/version), structuring skill packages for discovery, or publishing to the Agent Skills ecosystem. ACTIVATE for 'SKILL.md', 'npx skills', 'skillkit', 'skill frontmatter', 'skill discovery'. Covers: SKILL.md frontmatter schema (name constraints, description as routing mechanism), progressive disclosure (metadata/body/references), directory structure, discovery mechanics (npx skills add, skills.sh, Claude Code), installation scopes, validation checklist. DO NOT use for: Claude plugin structure (see claude-plugin-conventions), general markdown writing.

ACTIVATE when configuring monorepo structure, cross-package imports, workspace scripts, or pnpm workspace protocol. ACTIVATE for 'pnpm workspace', 'workspace:*', 'monorepo', 'pnpm --filter', 'packages/shared'. Covers: workspace structure (packages/shared + apps/api + apps/web), workspace:* protocol, build order (shared first), filtering commands, shared vs per-package dependencies. DO NOT use for: individual package configuration, npm/yarn workspaces.

ACTIVATE when creating Zod schemas, inferring types, composing schemas, or integrating Zod with NestJS validation. ACTIVATE for 'Zod', 'z.object', 'z.infer', 'ZodValidationPipe', 'schema validation'. Covers: FooSchema naming convention, packages/shared location, schema composition (extend/pick/omit/merge), z.coerce for HTTP values, NestJS ZodValidationPipe integration, error formatting with safeParse+flatten. DO NOT use for: general TypeScript types (see ts-conventions), domain validation logic.