Total 43,667 skills, Code Quality has 2036 skills
Showing 12 of 2036 skills
Application performance profiling and bottleneck identification — Node.js profiling, Chrome DevTools, flame graphs, memory leak detection, CPU profiling, React rendering performance. Activate on "profiling", "performance bottleneck", "flame graph", "memory leak", "slow app", "CPU profiling", "heap snapshot", "React re-renders", "EXPLAIN ANALYZE", "event loop lag", "clinic.js", "Core Web Vitals". NOT for infrastructure monitoring or observability (use logging-observability), load testing (use a load-testing skill), or database schema optimization.
Add, remove, or adjust Markuplint rules for specific files or elements. Analyzes violations, proposes scope-appropriate configuration changes, and confirms with the user.
Set up Markuplint in a project from scratch. Detects framework, creates config, runs initial lint, and guides the user through rule adoption with Bulk Suppressions support.
Guides you through migrating markuplint configuration from v4 to v5. Detects current versions, reviews the migration guide, interactively confirms breaking changes and new rules with the user, updates config files and tests. For Claude Code.
Reference knowledge for Markuplint HTML linter. Covers violation interpretation, CLI usage, config patterns, and documentation URLs. Auto-loaded when working with HTML linting.
Provides final code cleanup after task review approval. Removes debug logs, temporary comments, dead code, optimizes imports, and improves readability. Use when asked to clean up code, polish, finalize, tidy up, remove technical debt, or prepare code for completion after review. Not for refactoring logic or fixing bugs—focused solely on cosmetic and hygiene cleanup.
Use after run-plan completes to independently verify the implementation. Reads only the plan document and inspects the codebase from scratch — information-isolated from the execution context. Produces a structured review document with PASS/FAIL verdict. Triggers when the user says "review the work", "verify the implementation", "check if the plan was executed correctly".
Ultra-compressed PR review comments. One issue per line: Location • Problem • Fix. Remove preambles, prioritize signals. Supports Japanese. Trigger with "PR review please", "code review", "/review", "/genshijin-review". Candidate for automatic activation during pull request reviews.
Verifies that the implementation complies with the specs, design, and task plan. Produces verify-report.md. Trigger: /sdd-verify <change-name>, verify implementation, quality gate, validate change.
Investigates and analyzes an idea or codebase area before committing to changes. Pure research, no writes. Trigger: /sdd-explore <topic>, explore, investigate codebase, research feature, analyze before changing.
Language-agnostic SOLID principles and DDD tactical patterns. Trigger: Always loaded for non-documentation code changes via sdd-apply.
Identifies silent failures, inadequate error handling, and inappropriate fallback behavior in code. Zero tolerance for errors that occur without proper logging and user feedback. Triggers: When reviewing error handling, checking for silent failures, analyzing catch blocks. Examples: - "Review the error handling" -> audits all error handling in recent changes - "Check for silent failures" -> hunts for swallowed errors and empty catch blocks - "Analyze catch blocks in this PR" -> reviews every try-catch for adequacy - "Are there any hidden failures?" -> finds errors that get silently ignored