Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
LLM Judge Patterns
Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles
majiayu000/claude-skill-registry 163
-
frontend-specialists
majiayu000/claude-skill-registry 163
-
setup-errors
Configure error handling infrastructure with custom error types and global handler. Use when adding error handling to a project. Triggers on "setup errors", "add errors", "error handling", "error infrastructure".
majiayu000/claude-skill-registry 163
-
nielsen-user-control
Proporciona a usuarios control total sobre sus acciones con opciones de deshacer y salir. Use cuando diseñe flujos de navegación, acciones destructivas, o cualquier operación que el usuario pueda querer revertir.
majiayu000/claude-skill-registry 163
-
process-commit
PRを作成する前に分割commitが必要な時に自動的に呼び出す必要があるスキルです
majiayu000/claude-skill-registry 163
-
n8n-development-skill
majiayu000/claude-skill-registry 163
-
fluff-detector
Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.
majiayu000/claude-skill-registry 163
-
Backtesting Analysis
Comprehensive guidance for interpreting backtest results and detecting overfitting (project)
majiayu000/claude-skill-registry 163
-
git-helper
Generate git commit messages and help with git workflows
majiayu000/claude-skill-registry 163
-
kubernetes-operations
Kubernetes and OpenShift cluster operations, maintenance, and lifecycle management. Use this skill when:
(1) Performing cluster upgrades (K8s, OCP, EKS, GKE, AKS)
(2) Backup and disaster recovery (etcd, Velero, cluster state)
(3) Node management: drain, cordon, scaling, replacement
(4) Capacity planning and cluster scaling
(5) Certificate rotation and management
(6) etcd maintenance and health checks
(7) Resource quota and limit range management
(8) Namespace lifecycle management
(9) Cluster migration and workload portability
(10) Monitoring and alerting configuration
(11) Log aggregation setup
(12) Cost optimization and resource rightsizing
majiayu000/claude-skill-registry 163
-
system-design-draft
Draft a practical system design for a feature. Use when a mid-level developer needs a starting architecture.
majiayu000/claude-skill-registry 163
-
evernote-sdk-patterns
Advanced Evernote SDK patterns and best practices.
Use when implementing complex note operations, batch processing,
search queries, or optimizing SDK usage.
Trigger with phrases like "evernote sdk patterns", "evernote best practices",
"evernote advanced", "evernote batch operations".
majiayu000/claude-skill-registry 163
-
org-chart-generator
Generate organizational hierarchy charts from CSV, JSON, or nested data. Supports multiple layouts, department coloring, and PNG/SVG/PDF export.
majiayu000/claude-skill-registry 163
-
geb-protocol
项目架构约定：通过 Root/Folder/File 三层极简元数据（_dir.md + I/O/Pos 注释）
让 AI 在任意位置自定位。
**AI 创建文件夹时自动触发**：hook 会生成 _dir.md 模板，AI 填写 Input/Output/Pos。
majiayu000/claude-skill-registry 163
-
web-components-architecture
Build web components using Custom Elements v1 API with Declarative Shadow DOM, attribute-driven state, handleEvent pattern, and zero DOM selection. Use when creating custom elements, extending built-in HTML elements, or implementing component-based architecture. NO querySelector, NO innerHTML, NO external libraries - pure web platform APIs only.
majiayu000/claude-skill-registry 163
-
lsp-management
LSP server recommendations, .lsp.json configuration, installation guides, and troubleshooting for Language Server Protocol in Claude Code
majiayu000/claude-skill-registry 163
-
competitor-alternatives
When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables.
majiayu000/claude-skill-registry 163
-
arcanea-scene-craft
Master scene construction - the building blocks of story. Openings that hook, middles that build, endings that propel. Turn every scene into a compelling unit of narrative.
majiayu000/claude-skill-registry 163
-
example-presentation-automation
Update the weekly rolling presentation with JIRA progress data. Use this skill when asked to "update the presentation", "add weekly slides", "create presentation slides", or prepare slides for team meetings. Covers Google Slides API operations, template slide IDs, proper slide duplication workflow, and content formatting guidelines for the Orient Task Force rolling presentation.
majiayu000/claude-skill-registry 163
-
skills-heal
Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references
majiayu000/claude-skill-registry 163
-
postgresql
PostgreSQL DBA skill for schema design review, indexing, query tuning (EXPLAIN/ANALYZE), vacuum/autovacuum, concurrency/locking, partitioning, backup/restore, replication/HA, and safe migrations. Use for tasks like diagnosing slow queries, designing indexes and constraints, and operating Postgres in production.
majiayu000/claude-skill-registry 163
-
firmware-analyst
Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering. Masters firmware extraction, analysis, and vulnerability research for routers, IoT devices, automotive systems, and industrial controllers. Use PROACTIVELY for firmware security audits, IoT penetration testing, or embedded systems research.
majiayu000/claude-skill-registry 163
-
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume.
majiayu000/claude-skill-registry 163
-
implementing-mlops
Strategic guidance for operationalizing machine learning models from experimentation to production. Covers experiment tracking (MLflow, Weights & Biases), model registry and versioning, feature stores (Feast, Tecton), model serving patterns (Seldon, KServe, BentoML), ML pipeline orchestration (Kubeflow, Airflow), and model monitoring (drift detection, observability). Use when designing ML infrastructure, selecting MLOps platforms, implementing continuous training pipelines, or establishing model governance.
majiayu000/claude-skill-registry 163