Loading...
Loading...
Found 149 Skills
Verify cross-component wiring: exports are imported AND used, real data flows through connections, output shapes match input expectations. Use after /feature-implement, before /feature-validate, or standalone on any codebase. Use for "check integration", "verify wiring", "are components connected", "integration check", or "/integration-checker". Do NOT use for unit test failures, linting, or single-file correctness issues.
Generate a project-specific CLAUDE.md by analyzing the current repository's code, build system, and architecture. 4-phase pipeline: SCAN, DETECT, GENERATE, VALIDATE. Auto-detects language/framework and enriches output with domain-specific conventions (e.g., go-sapcc-conventions for sapcc Go repos). Use for "generate claude.md", "create claude.md", "init claude.md", "bootstrap claude.md", "make claude.md". Do NOT use for improving an existing CLAUDE.md (use claude-md-improver instead).
Real-time communication patterns with WebSocket, Socket.io, Server-Sent Events, and scaling strategies
REST API design with resource naming, pagination, versioning, and OpenAPI spec generation
Application security covering input validation, auth, headers, secrets management, and dependency auditing
Parallel 3-reviewer code review orchestration: launch Security, Business-Logic, and Architecture reviewers simultaneously, aggregate findings by severity, and produce a unified BLOCK/FIX/APPROVE verdict. Use when reviewing PRs with 5+ files, security-sensitive changes, new features needing broad coverage, or when user requests "parallel review", "comprehensive review", or "full review". Do NOT use for single-file fixes, documentation-only changes, or when systematic-code-review (sequential) is sufficient.
Tracked lightweight execution with composable rigor flags for tasks between a typo fix and a full feature. Plan + execute with optional --discuss, --research, and --full flags to add rigor incrementally. Use for "quick task", "small change", "ad hoc task", "add a flag", "extract function", "small refactor", "fix bug in X". Do NOT use for multi-component features, architectural changes, or anything needing wave-based parallel execution — those are Simple+ tier.
Perses plugin testing: CUE schema unit tests with percli plugin test-schemas, React component tests, integration testing with local Perses server, and Grafana migration compatibility testing. Use for "test perses plugin", "perses plugin test", "perses schema test". Do NOT use for dashboard validation (use perses-lint).
Critique-and-rewrite enforcement loop for voice fidelity. Validates generated content against negative prompt checklists and forces revision until it passes. Use when content has been generated in a target voice, voice output feels off, long-form content risks voice drift, or before final delivery of voice content. Use for "validate voice", "check voice", "voice feels wrong", "voice drift", or "rewrite for voice". Do NOT use for initial voice generation, voice profile creation, or content that has no voice target.
Sync local changes to GitHub in one command: detect state, branch, commit, push, create PR. Use when user wants to push work to GitHub, create a PR, or sync a feature branch. Use for "push my changes", "create a PR", "sync to GitHub", "open pull request", or "ship this". Do NOT use for reviewing PRs (use /pr-review), cleaning up after merge (use pr-cleanup), or CI checks (use ci).
Phase-gated git commit workflow with validation, staging, and CLAUDE.md compliance enforcement. Use when creating commits, staging changes, or when PR workflows need standardized commits. Triggers: "commit changes", "save work", "create commit", or internal skill invocation from PR workflows. Do NOT use for merge commits, rebases, amends, cherry-picks, or emergency rollbacks requiring raw git speed.
Identify and fix common testing mistakes across unit, integration, and E2E test suites. Use when tests are flaky, brittle, over-mocked, order-dependent, slow, poorly named, or providing false confidence. Use for "test smell", "fragile test", "flaky test", "over-mocking", "test anti-pattern", or "skipped tests". Do NOT use for writing new tests from scratch (use test-driven-development), refactoring architecture (use systematic-refactoring), or performance profiling without a specific test quality symptom.