Audit and fix common accessibility issues in Angular templates and Angular Material components. Use when the user mentions Lighthouse, axe, screen readers, keyboard navigation, ARIA, asks to fix a11y issues in Angular HTML templates, or after any feature, bug fix, or refactor that changed Angular templates.
Scaffolds and extends Angular standalone feature MODULES under src/app/modules/{name} using Clean Architecture layering (presentation/application/core/infrastructure), a self-registering module providers function, route-level lazy loading, cross-navigation state caching, the facade pattern, and ports/adapters…
Domain-Driven Design for Angular/TypeScript: functional patterns with type aliases, readonly fields, pure rule functions, immutable value types, branded IDs, and ports as abstract classes. Use when creating or reviewing domain models, aggregates, rule functions, ports, bounded contexts, or domain events. Use when…
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress or "compress memory…
Scaffolds and extends .NET 10 Minimal API modules using self-registering IModule (reflection discovery) + hexagonal ports/adapters per module (Application/Core/Infrastructure), default EF Core CRUD persistence. Use when creating new .NET modules, adding endpoints/use-cases, or refactoring toward ports/adapters and…
Domain-Driven Design best practices for .NET 10 domain code. Use when creating or reviewing entities, value objects, aggregates, aggregate roots, repositories, domain services, bounded contexts, or domain events in C#. Use when refactoring anemic models toward rich domain logic, enforcing aggregate invariants, or…
Signal-first reactive state management for Angular. Bridge RxJS streams into cache-aware stores, keyed resources, mirrored state, and replayable history. Use when generating or modifying Angular code that uses flurryx for state management, or when scaffolding new feature modules that follow the flurryx facade pattern.
GDPR reference & code-audit checklist with FRANCE/CNIL focus. Use when reviewing or building features that collect/process/store personal data (consent, PII, authentication, forms, cookies, cookies/trackers, data-subject rights, retention, DPIA, cross-border transfers, breach notification). Multi-source verified facts…
Use this skill for any git work such as creating branches, staging changes, writing commit messages, pushing branches, or preparing pull requests. Delegates git execution to the git-specialist agent.
Use whenever you add, edit, rename, or delete any harness artifact — a skill, agent, command, rule, or instruction — in either .claude/ or .opencode/. Replicate the equivalent change in the other harness with the correct frontmatter and registration translation, so the two trees stay in parity.
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
Guides writing and maintaining Claude Code skills with progressive disclosure and DRY principles. Use when creating a new skill, editing/adding content to an existing skill, restructuring or splitting skills, or asking "is this skill too large?" Encodes: 3-level disclosure (description + body + reference files)…
Use this skill before any planning, design, architecture, or refactor work when critical decisions are not yet closed. Resolve those decisions with evidence before producing a plan or implementation.
Make compaction safe for fully autonomous multi-phase work. The agent prepares durable state so auto-compaction never requires user input and never breaks flow.
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
Test-driven development via strict RED-GREEN-REFACTOR cycle. Build event-sourced aggregates and domain logic with passing tests before any production code. Optional: outer-loop acceptance tests (Application layer, ATDD) for explicit use-case specification. Mandatory: 80%+ coverage, narrow + wide test layers…
Manages translation entries in Transloco JSON files. Use when adding, updating, or organizing i18n translation keys in Angular projects using Transloco.
Use ONLY when the user explicitly asks to create/use a worktree, isolated worktree, parallel feature branch, or avoid branch collision; immediately create an isolated OpenCode worktree for that task. Do not trigger for ordinary feature work.