Loading...
Loading...
Found 113 Skills
Scans code against 17 named design smells and produces a structured diagnostic report. Use when reviewing a PR for design quality, evaluating unfamiliar code against a comprehensive checklist or when the user asks for a red flags scan. Not for diagnosing why code feels complex (use complexity-recognition) or evaluating whether a PR maintains design trajectory (use code-evolution).
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Build a section-by-section claim–evidence matrix (`outline/claim_evidence_matrix.md`) from the outline and paper notes. **Trigger**: claim–evidence matrix, evidence mapping, 证据矩阵, 主张-证据对齐. **Use when**: 写 prose 之前需要把每个小节的可检验主张与证据来源显式化（outline + paper notes 已就绪）。 **Skip if**: 缺少 `outline/outline.yml` 或 `papers/paper_notes.jsonl`。 **Network**: none. **Guardrail**: bullets-only（NO PROSE）；每个 claim 至少 2 个证据来源（或显式说明例外）。
Use before committing code - validates Drupal coding standards, SOLID/DRY principles, security practices, and CSS standards
Generates dead code detection configurations for loom plan verification. Provides language-specific commands, fail patterns, and ignore patterns for Rust, TypeScript, Python, Go, and JavaScript. Use when adding code quality checks to acceptance criteria or truths fields in loom plans. Dead code detection catches incomplete wiring by identifying code that exists but is never called.
Pre-PR review pipeline — runs security, API audit, and scope check agents in parallel. Read-only, no changes. Use before creating PRs or after completing a phase of work.
Use this skill when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (GitHub sticky comment, new comment, or local file) and routes output accordingly.
Analiza cambios staged en git para detectar bugs, vulnerabilidades de seguridad, malas prácticas, y genera descripciones detalladas de commits con mensaje en formato Conventional Commits. Usa este skill siempre que el usuario quiera revisar cambios antes de commitear o pushear, analizar un diff staged, detectar bugs o malas prácticas en código que está por commitear, generar un mensaje o descripción de commit, o hacer code review previo al commit. Se activa con frases como "revisá mis cambios staged", "analiza mi commit", "qué bugs tiene lo que cambié", "generame el mensaje de commit", "review antes de push", "detecta errores en mis cambios", "haceme un análisis antes de commitear", o "necesito una descripción para mi commit". NO usar para: code review de archivos sueltos sin contexto de commit, configurar linters, escribir tests, debugging de producción, o crear código nuevo. Este skill es específicamente para el momento previo al commit.
Clarity pre-deployment validation — syntax checking, deprecated keyword detection, sender check analysis, error propagation review, and test verification.
Validates SKILL.md files against Claude Code skill best practices. Checks conciseness, description quality, progressive disclosure, workflow structure, and common anti-patterns. Use when reviewing or auditing skills before shipping.
Check or verify whether a Skill complies with best practice specifications, covering naming conventions, directory structure, metadata integrity, temporary file cleanup, and dependency format validation. It provides detailed checklists, automatic repair suggestions, and report templates, and also supports integrity checks and automatic repair of skill library documentation. It is suitable for quality verification after creating or modifying a Skill
Run after making Docyrus API changes to catch bugs, performance issues, and code quality problems. Use when implementing or modifying code that uses Docyrus collection hooks (.list, .get, .create, .update, .delete), direct RestApiClient calls, query payloads with filters/calculations/formulas/childQueries/pivots, or TanStack Query integration with Docyrus data sources. Triggers on tasks involving Docyrus API logic, data fetching, mutations, or query payload construction.