Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dry-philosophy
Don't Repeat Yourself (DRY) and Never Reinvent the Wheel (NRtW) - core b00t
principles. Use existing libraries, leverage Rust via PyO3 instead of duplicating
logic in Python, and contribute to upstream projects rather than fork privately.
majiayu000/claude-skill-registry 163
-
ops-responder
Respond to incidents and apply remediations - restart services, scale resources,
clear caches, update configurations, rollback deployments, apply fixes, verify
remediation success, document actions taken, track remediation history.
majiayu000/claude-skill-registry 163
-
commit-message-generator
Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification. Invoke when user mentions "commit", "staged", "committing", or asks for help with commit messages.
majiayu000/claude-skill-registry 163
-
minikube-local-development
Complete guide for local Kubernetes development with Minikube: installation, configuration, image management, addons, networking, and troubleshooting for efficient local development workflows.
majiayu000/claude-skill-registry 163
-
devops-role-skill
Professional DevOps engineering skill for creating CI/CD pipelines, implementing
infrastructure as code, managing environments, and establishing monitoring and
observability across all deployment stages.
majiayu000/claude-skill-registry 163
-
cortex-operations
Operate the Agent Hive Cortex orchestration engine. Use this skill when running Cortex commands, analyzing project dependencies, finding ready work, understanding the orchestration system, or troubleshooting Cortex issues.
majiayu000/claude-skill-registry 163
-
video-editing-advisor
Video editing expert covering cutting techniques, pacing, color grading, and post-production workflows
majiayu000/claude-skill-registry 163
-
role
Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with specific roles. Supports single or multiple roles.
majiayu000/claude-skill-registry 163
-
audit-investigation
Use when investigating config file discrepancies during audit. Spawns config agents in waves to compare template standards against actual files. READ-ONLY analysis - agents report findings but make no changes.
majiayu000/claude-skill-registry 163
-
fundamentals-analysis
Analyzes a company's fundamental performance, growth drivers, and risks using verified financial data and text evidence. Use this when asked to research a stock's business model, revenue segments, or quarterly performance.
majiayu000/claude-skill-registry 163
-
cross-platform-guardian-wcygan-dotfiles
majiayu000/claude-skill-registry 163
-
kubekey
Manage Kubernetes clusters with KubeKey: check installation, install KubeKey, create clusters, scale nodes, upgrade clusters, and view configurations. Use when working with Kubernetes cluster deployment, management, or when the user mentions KubeKey, kk, or Kubernetes cluster operations.
majiayu000/claude-skill-registry 163
-
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
majiayu000/claude-skill-registry 163
-
adr-roadmap
Generate phased implementation roadmaps from Architecture Decision Records
majiayu000/claude-skill-registry 163
-
tk-find
Search across Tasuku tasks, notes, learnings, and decisions. Use when user says /tk:find or asks to search, find, or look for something in tasks.
majiayu000/claude-skill-registry 163
-
anime-js
Use when implementing Disney's 12 animation principles with Anime.js library
majiayu000/claude-skill-registry 163
-
analyzing-funding-landscape
Analyzes venture capital, investment trends, funding rounds, investor strategies, M&A activity, and funding patterns in specific markets or industries. Use when the user requests funding analysis, VC landscape research, investment trend analysis, or wants to understand investor activity and funding dynamics.
majiayu000/claude-skill-registry 163
-
delaying-tasks
Schedule a delayed or interval-based action with minimal heartbeats. Use to wait before running a check (e.g., GH Actions, PR status, CI pipeline) or to poll on a bounded interval. Trigger on: "wait", "delay", "poll", "check later", "retry after", "schedule check".
majiayu000/claude-skill-registry 163
-
arc-runner-troubleshooting
Troubleshoot ARC (Actions Runner Controller) runners on Rackspace Spot Kubernetes. Diagnose stuck jobs, scaling issues, and cluster access. Activates on "runner", "ARC", "stuck job", "queued", "GitHub Actions", or "CI stuck".
majiayu000/claude-skill-registry 163
-
fto-analyst
Autonomous Freedom to Operate analysis agent. Identifies blocking patents, assesses infringement risk, and recommends mitigation strategies for product commercialization.
majiayu000/claude-skill-registry 163
-
infrastructure-guidelines
Infrastructure guidelines for A4C-AppSuite. Covers idempotent Supabase SQL migrations with RLS policies, Kubernetes deployments for Temporal workers, CQRS projections with PostgreSQL triggers, and AsyncAPI contract-first event design. Emphasizes safety, idempotency, and SQL-first development.
majiayu000/claude-skill-registry 163
-
pubmed-export-citations
majiayu000/claude-skill-registry 163
-
savecontext
This skill should be used when the user asks to "save context", "remember this decision", "track my progress", "checkpoint my work", "resume where I left off", "continue from last session", "persist state across sessions", "prepare for compaction", "restore from checkpoint", "switch sessions", or when starting work and needing to check for existing sessions. Also triggers on compound workflows like "wrap up session", "wrap up and checkpoint", "end of day checkpoint", "resume fully", "pick up where I left off and show status", "checkpoint with tags", "log work and checkpoint", "tag and checkpoint", "prepare for handoff", "handoff to another agent".
majiayu000/claude-skill-registry 163
-
working-with-llms
Mandatory workflow for creating LLM-facing content. Follow the 4-step process (objective → draft → verify → adjust) before writing any prompt, skill, tool description, or system instruction. Triggers on requests to create or revise skills, prompts, agent workflows, or any content that will be sent to an LLM repeatedly.
majiayu000/claude-skill-registry 163