Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
geospatial-visualization
Master geographic and mapping visualizations with GeoViews. Use this skill when creating interactive maps, visualizing point/polygon/line geographic data, building choropleth maps, performing spatial analysis (joins, buffers, proximity), working with coordinate reference systems, or integrating tile providers and basemaps.
majiayu000/claude-skill-registry 163
-
log-aggregation-configurator
Set up centralized logging with ELK, Loki, or Splunk for log management
majiayu000/claude-skill-registry 163
-
beam-debug-issue-tasks
Debug failed/issue tasks from Beam.ai using Langfuse traces. Load when user says "debug issue tasks", "check failed tasks", "why did task fail", "task errors", "debug agent", or needs to investigate task failures.
majiayu000/claude-skill-registry 163
-
mcp-feishu
当用户提供飞书 MCP URL 并请求配置时触发。自动同时配置到 Claude Code 和 Cursor，简化团队成员的环境设置流程。
majiayu000/claude-skill-registry 163
-
fvtt-sockets
This skill should be used when implementing multiplayer synchronization, using game.socket.emit/on, creating executeAsGM patterns for privileged operations, broadcasting events between clients, or avoiding common pitfalls like race conditions and duplicate execution.
majiayu000/claude-skill-registry 163
-
publish
Publish a new version of klaude-code to PyPI. This skill handles version bumping, changelog updates, git tagging, and package publishing. Use when the user wants to release a new version.
majiayu000/claude-skill-registry 163
-
code-review-skill
Use to review code implementations for quality, correctness, and best practices
majiayu000/claude-skill-registry 163
-
new-node
Create new workflow nodes for the Workscript engine or refactor existing nodes. Generate complete, production-ready node implementations following the single-edge return pattern. Use when creating new nodes, developing custom integrations, building data manipulation nodes, refactoring existing nodes, or implementing workflow capabilities.
majiayu000/claude-skill-registry 163
-
mastra-skills
Use when building or working with Mastra agents - establishes best practices for agent development, tool creation, and workflow orchestration
majiayu000/claude-skill-registry 163
-
gitlab-ci-job-configuration
Use when defining GitLab CI jobs, configuring scripts, setting up environments, or managing job dependencies. Covers job structure and execution options.
majiayu000/claude-skill-registry 163
-
python-data-reviewer
WHEN: Pandas/NumPy code review, data processing, vectorization, memory optimization
WHAT: Vectorization patterns + Memory efficiency + Data validation + Performance optimization + Best practices
WHEN NOT: Web framework → fastapi/django/flask-reviewer, General Python → python-reviewer
majiayu000/claude-skill-registry 163
-
overthrow-architecture
Overthrow mod architecture patterns, naming conventions, and project structure
majiayu000/claude-skill-registry 163
-
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
majiayu000/claude-skill-registry 163
-
review-git-changes
Analyzes and refactors code changes in the current git working tree (staged, unstaged, or recent commits). Ensures changes follow best practices, coding standards, and maintain code quality. Use when the user asks to "review my git changes", "check what I changed", "refactor my changes", "ensure my changes are clean", or "review before commit".
majiayu000/claude-skill-registry 163
-
extracting-session-data
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
majiayu000/claude-skill-registry 163
-
code-scoring
Provides quantitative rubrics and criteria for scoring code quality on a 1-10 scale. Use when reviewing code, performing code audits, establishing quality baselines, comparing implementations, or providing objective code feedback.
majiayu000/claude-skill-registry 163
-
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
majiayu000/claude-skill-registry 163
-
detr-peer-simulation
Simulate DETR p2p networking layer message passing outside Substrate defaults.
majiayu000/claude-skill-registry 163
-
logging-config-agent
Configures logging systems, log aggregation, and log analysis pipelines
majiayu000/claude-skill-registry 163
-
qa-agent-testing
QA harness for agentic systems: scenario suites, determinism controls, tool sandboxing, scoring rubrics, and regression protocols covering success, safety, latency, and cost.
majiayu000/claude-skill-registry 163
-
cli-todo-ui
Build modern, interactive terminal-based todo applications with beautiful UI/UX using Python's Textual framework. Use when building CLI todo apps, task managers, or interactive terminal interfaces that require menu-driven flows, visual polish (colors, icons, tables), keyboard shortcuts, mouse support, and professional developer experience. Ideal for hackathons and rapid prototyping of terminal UIs.
majiayu000/claude-skill-registry 163
-
advanced
Claude Code mastery for power users. Build agents, MCP servers, publish plugins.
Use when: user wants to create agents, build integrations, or publish plugins.
majiayu000/claude-skill-registry 163
-
transcribe-audio
Transcribes video audio using WhisperX, preserving original timestamps. Creates JSON transcript with word-level timing. Use when you need to generate audio transcripts for videos.
majiayu000/claude-skill-registry 163
-
ccpm-debugging
Systematic debugging with defense-in-depth approach (symptoms → immediate cause → root cause → systemic issues → prevention). Auto-activates when user mentions "error", "failing", "broken", "debug", "bug", "issue" or when /ccpm:verify runs. Uses Observe → Hypothesize → Test → Confirm → Fix → Verify → Document workflow. Updates Linear with findings and automatically logs blockers that require external fixes. Traces root causes instead of patching symptoms. Integrates with ccpm-code-review to verify fixes pass all gates before marking complete. Suggests binary search for intermittent issues and five-whys analysis for complex problems.
majiayu000/claude-skill-registry 163