Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
snapshot-testing
Use Verify for snapshot testing in .NET. Approve API surfaces, HTTP responses, rendered emails, and serialized outputs. Detect unintended changes through human-reviewed baseline files.
majiayu000/claude-skill-registry 163
-
skills-clausfonnesbech-agentic-framework
majiayu000/claude-skill-registry 163
-
gitlab-ci-basics
Manage gitlab ci basics operations. Auto-activating skill for DevOps Basics.
Triggers on: gitlab ci basics, gitlab ci basics
Part of the DevOps Basics skill category. Use when working with gitlab ci basics functionality. Trigger with phrases like "gitlab ci basics", "gitlab basics", "gitlab".
majiayu000/claude-skill-registry 163
-
coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
majiayu000/claude-skill-registry 163
-
intent-capture
Capture user intent through guided conversation. Exploratory phase with high degrees of freedom.
majiayu000/claude-skill-registry 163
-
state-management
State Management - React Query, Zustand, MMKV. Use when managing application state.
majiayu000/claude-skill-registry 163
-
ci-cd-pipeline-builder
CI/CD Pipeline Builder
majiayu000/claude-skill-registry 163
-
google-adk-python
Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.
majiayu000/claude-skill-registry 163
-
docs-seeker
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
majiayu000/claude-skill-registry 163
-
bmad-wds-icons
Generate icon sets and individual icons matching design system
majiayu000/claude-skill-registry 163
-
x-research
Research topics, users, and gather context from X (Twitter)
majiayu000/claude-skill-registry 163
-
babysit
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
majiayu000/claude-skill-registry 163
-
docs-seeker
Search internet for technical documentation using llms.txt standard (context7.com) and parallel exploration. ALWAYS use when user asks "how to use X library", "documentation for Y", "docs for Z", needs latest docs for any library/framework, or mentions "context7", "llms.txt". Searches official docs, GitHub repos via Repomix, and uses parallel Explorer agents.
majiayu000/claude-skill-registry 163
-
tmux
tmux terminal multiplexer. Use for terminal sessions.
majiayu000/claude-skill-registry 163
-
kata-plan-milestone-gaps
Create phases to close all gaps identified by milestone audit. Triggers include "plan milestone gaps", "plan gaps".
majiayu000/claude-skill-registry 163
-
career-biographer
AI-powered career biographer that conducts empathetic interviews, extracts structured career narratives, and transforms professional stories into portfolios, CVs, and personal brand assets. This skill should be used when users want to document their career journey, create professional portfolios, generate CVs, or craft compelling career narratives.
majiayu000/claude-skill-registry 163
-
af-tdd-workflow
Follow the TDD Red-Green-Refactor cycle during feature implementation. Use when implementing features test-first, converting BDD scenarios to failing tests, or following the delivery phase implementation pattern.
majiayu000/claude-skill-registry 163
-
motherduck-build-cfa-app
Design a MotherDuck-backed customer-facing analytics app. Use when building embedded or product analytics for external users and the decision depends on per-customer isolation, backend routing, service-account boundaries, read scaling, or Hypertenancy-style patterns.
majiayu000/claude-skill-registry 163
-
team-frontend-debug
Frontend debugging team using Chrome DevTools MCP. Dual-mode -- feature-list testing or bug-report debugging. Covers reproduction, root cause analysis, code fixes, and verification. CSV wave pipeline with conditional skip and iteration loops.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-storage-list
List storage resources or files in a bucket. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
merge-all
Merge all open PRs into main with testing between each
majiayu000/claude-skill-registry 163
-
project-learnings-sequenzia-agent-alchemy
Captures project-specific patterns and anti-patterns into the project's CLAUDE.md. Loaded by other skills (bug-killer, feature-dev, etc.) when they discover project-specific knowledge worth encoding for future sessions.
majiayu000/claude-skill-registry 163
-
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
majiayu000/claude-skill-registry 163
-
notebookLM
NotebookLM用YAMLやスライドを生成。ドキュメント職人の腕の見せ所。Use when user mentions NotebookLM, YAML, slides, or presentations. Do NOT load for: implementation work, code fixes, reviews, or deployments.
majiayu000/claude-skill-registry 163