Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gcs-medarbejdere-data
Activates when querying employee and workplace safety data from GCS.
Use this skill for: Arbejdstilsynet inspections, work permits, safety violations,
workplace accidents, compliance rates, foreign workers, incident tracking.
Keywords: medarbejdere, employees, worker, arbejdstilsynet, inspection, tilsyn, safety, arbejdsmiljø, accident, ulykke, compliance
majiayu000/claude-skill-registry 163
-
react-native-performance
React Native performance optimization techniques. Use when optimizing app performance.
majiayu000/claude-skill-registry 163
-
ops-safety
当用户执行系统级命令（sysctl、iptables、systemctl、Docker 配置、数据库 DDL）或进行服务器运维操作时触发。提供运维安全规范。
majiayu000/claude-skill-registry 163
-
Agent Launcher
Launches specialized Claude agents for targeted tasks. Analyzes requirements, selects appropriate agent, and executes with optimized configuration.
majiayu000/claude-skill-registry 163
-
mcp-tools-catalog
Build docs/mcp-tools.md from the active MCP servers and available tool functions.
majiayu000/claude-skill-registry 163
-
crucible-outliner
Chapter-by-chapter outline generator for stories planned with the Crucible Structure. Use when a user has completed Crucible planning documents (thesis, strand maps, forge points, etc.) and wants to create detailed chapter outlines. Triggers on requests like "outline my book," "create chapter outline," "outline Book 1," "turn my Crucible plan into chapters," or when user has Crucible planning docs and wants to start writing. Works for single books or multi-book series.
majiayu000/claude-skill-registry 163
-
coupling-analysis-turbobeest-cursor-dev-system
OPTIONAL: Analyzes TaskMaster subtasks to determine if they are tightly coupled
(share code/models) or loosely coupled (independent modules). This analysis provides
RECOMMENDATIONS for implementation order only - it does NOT affect proposal creation.
All proposals are created 1-per-subtask regardless of coupling. Coupling analysis
only recommends whether to implement proposals sequentially (tight coupling) or in
parallel (loose coupling) to avoid merge conflicts.
Activation trigger: [ACTIVATE:COUPLING_ANALYSIS_V1] (optional)
majiayu000/claude-skill-registry 163
-
validation-expert
Comprehensive validation for Project Conductor using deep research for best practices. Use when user mentions "validate", "check quality", "review code", "test coverage", or before deployment.
majiayu000/claude-skill-registry 163
-
bigquery-ethereum-data-acquisition
Workflow for acquiring historical Ethereum blockchain data using Google BigQuery free tier. Empirically validated for cost estimation, streaming downloads, and DuckDB integration. Use when planning bulk historical data acquisition or comparing data source options for blockchain network metrics.
majiayu000/claude-skill-registry 163
-
streamlit-master-architect
Architect-level Streamlit development for building, refactoring, debugging, testing, and deploying Streamlit apps (single-page or multipage) with correct rerun/state/caching/fragments, AppTest-based testing, custom components v2, safe theming/CSS, security-by-default, and Playwright MCP end-to-end automation.
majiayu000/claude-skill-registry 163
-
frontend-design-assistant
Frontend design assistant for users with zero/low-code background. This skill should be used when users request creating web interfaces, landing pages, dashboards, or any frontend UI; when users ask about frontend terminology, design elements, or architecture concepts; when users want to understand CSS, layout, typography, or color choices. Emphasizes distinctive aesthetics over generic AI-generated designs, teaches concepts in context, and adapts to user skill level (pure HTML/CSS or React/Vue).
majiayu000/claude-skill-registry 163
-
kubernetes-specialist
Use when deploying or managing Kubernetes workloads requiring cluster configuration, security hardening, or troubleshooting. Invoke for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization.
majiayu000/claude-skill-registry 163
-
front-end-testing
DOM Testing Library patterns for behavior-driven UI testing. Framework-agnostic patterns for testing user interfaces. Use when testing any front-end application.
majiayu000/claude-skill-registry 163
-
input-validation-checker
Validate input validation checker operations. Auto-activating skill for Security Fundamentals.
Triggers on: input validation checker, input validation checker
Part of the Security Fundamentals skill category. Use when working with input validation checker functionality. Trigger with phrases like "input validation checker", "input checker", "input".
majiayu000/claude-skill-registry 163
-
eval-test-skill
Git branch cleanup utility. Lists and deletes branches that have been merged to main. Use when user wants to clean up old branches, delete merged branches, or tidy up their git repository.
majiayu000/claude-skill-registry 163
-
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
majiayu000/claude-skill-registry 163
-
working-with-reference-tables
Work with Reference Tables (static CSV lookup data) using OPAL to enrich datasets with descriptive information. Use when you need to map IDs to human-readable names, add static metadata from CSV uploads, or perform lookups without temporal considerations. Covers both explicit and implicit lookup patterns, column name matching, and when to choose Reference Tables vs Resources vs Correlation Tags.
majiayu000/claude-skill-registry 163
-
git-rebase-main
Safely rebase the current feature branch on top of the latest origin/main. Use when preparing a branch for PR, UAT, or release.
majiayu000/claude-skill-registry 163
-
meta-automation-architect
Use when user wants to set up comprehensive automation for their project. Generates custom subagents, skills, commands, and hooks tailored to project needs. Creates a multi-agent system with robust communication protocol.
majiayu000/claude-skill-registry 163
-
distributed-tracing
Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.
majiayu000/claude-skill-registry 163
-
qra
Extract Question-Reasoning-Answer pairs from text. Use --context for domain-focused extraction. Validates answers are grounded in source text.
majiayu000/claude-skill-registry 163
-
c-data-structures
Use when implementing data structures in C including arrays, linked lists, trees, and hash tables with manual memory management.
majiayu000/claude-skill-registry 163
-
django-application
Develop production-grade Django applications with models, views, ORM queries, authentication, and admin interfaces. Use when building web applications, managing databases with Django ORM, and implementing authentication systems.
majiayu000/claude-skill-registry 163
-
non-fiction-revision
Diagnose and guide revisions in non-fiction books. Use for non-fiction book revision, when arguments feel weak, evidence is outdated, readers report confusion, thesis is unclear, or book structure has problems. Keywords: non-fiction, revision, thesis, argument, evidence, structure.
majiayu000/claude-skill-registry 163