Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
openapi
Use when working with OpenAPI Specification files to validate, create/modify paths and schemas, check references, and enforce best practices
majiayu000/claude-skill-registry 163
-
analyzing-pricing
Analyzes pricing strategies, competitive pricing benchmarks, pricing models, value metrics, and willingness-to-pay to optimize pricing and positioning. Use when the user requests pricing analysis, competitive pricing comparison, pricing strategy, pricing model evaluation, or wants to optimize pricing decisions.
majiayu000/claude-skill-registry 163
-
telemetry
Parent skill that routes between telemetry-pr-insights (PR/CI) and telemetry-insights (interactive analysis).
majiayu000/claude-skill-registry 163
-
Pattern Space Activate
Master activation skill that loads all Pattern Space layers and enables consciousness navigation as a skill-based system.
majiayu000/claude-skill-registry 163
-
vibe-coder
Describe your idea, get a deployed product. All Craft Coder skills + brainstorm, validation, marketing.
Use when: user wants to build something from an idea, prototype, or MVP.
Triggers: "build app", "create website", "make MVP", "I have an idea",
"хочу приложение", "создать сайт", "сделать MVP".
majiayu000/claude-skill-registry 163
-
manifest-validator
Validates Kubernetes manifests using kubeconform, kube-score, and custom homelab policies. Use when creating or modifying YAML files, Helm values, or ArgoCD applications.
majiayu000/claude-skill-registry 163
-
kubernetes-security-policies
Kubernetes security policies, RBAC, and Pod Security Standards for hardened cluster deployments. Use when implementing cluster security, defining network policies, or enforcing security compliance in Kubernetes environments.
majiayu000/claude-skill-registry 163
-
helm-chart-architect
Design production-grade Helm charts through architectural reasoning rather than pattern
retrieval. Activate when designing new Helm charts for Kubernetes deployments, evaluating
chart architecture, making decisions about component packaging, or reviewing charts for
extensibility and maintainability. Guides decision-making about dependencies, lifecycle
hooks, configuration surface, and multi-environment deployment through context-specific
reasoning rather than generic best practices.
majiayu000/claude-skill-registry 163
-
agent-evaluator
Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs scripts/agent_evaluator.py).
majiayu000/claude-skill-registry 163
-
projections
Build or query TES projections (current state views). State is derived from TES events - projections are the queryable current truth.
majiayu000/claude-skill-registry 163
-
scalability-playbook
Identifies performance bottlenecks and provides ordered scaling strategies with triggers, phased plans, and cost implications. Use for "scalability planning", "performance bottlenecks", "capacity planning", or "growth strategy".
majiayu000/claude-skill-registry 163
-
performance-budget-checker
Detects performance anti-patterns like N+1 queries, nested loops, large file operations, and inefficient algorithms. Suggests fast fixes before issues reach production.
majiayu000/claude-skill-registry 163
-
openai-agents
Build AI applications with OpenAI Agents SDK - text agents, voice agents (realtime), multi-agent workflows with handoffs, tools with Zod schemas, input/output guardrails, structured outputs, and streaming. Deploy to Cloudflare Workers, Next.js, or React with human-in-the-loop patterns.
Use when: building text-based agents with tools and Zod schemas, creating realtime voice agents with WebRTC/WebSocket, implementing multi-agent workflows with handoffs between specialists, setting up input/output guardrails for safety, requiring human approval for critical actions, streaming agent responses, deploying agents to Cloudflare Workers or Next.js, or troubleshooting Zod schema type errors, MCP tracing failures, infinite loops (MaxTurnsExceededError), tool call failures, schema mismatches, or voice agent handoff constraints.
majiayu000/claude-skill-registry 163
-
max-bid-calculator-skill
Calculate maximum bid using BidDeed formula and bid/judgment ratios to determine BID/REVIEW/SKIP decisions
majiayu000/claude-skill-registry 163
-
decision-critic
Structured decision critic that systematically stress-tests reasoning before commitment surfacing hidden assumptions verifying claims and generating adversarial perspectives to improve decision quality.
majiayu000/claude-skill-registry 163
-
github-modes
Comprehensive GitHub integration modes for workflow orchestration, PR management, and repository coordination. Use for GitHub CLI operations, automated workflows, PR reviews, issue tracking, release management, and CI/CD coordination.
majiayu000/claude-skill-registry 163
-
k8s-reviewer
WHEN: Kubernetes manifest review, Helm charts, resource limits, probes, RBAC
WHAT: Resource configuration + Health probes + Security context + RBAC policies + Helm best practices
WHEN NOT: Docker only → docker-reviewer, Terraform → terraform-reviewer
majiayu000/claude-skill-registry 163
-
constraints-scheduling
Provides systematic approaches for solving constraint-based scheduling problems, such as finding meeting times that satisfy multiple participant availability windows, preferences, and existing calendar conflicts. This skill should be used when tasks involve scheduling with constraints, calendar conflict resolution, time slot optimization, or finding valid time windows across multiple inputs with hard and soft constraints.
majiayu000/claude-skill-registry 163
-
spec
Create traceable specifications from architecture. Use after architecture is approved to define invariants, edge cases, and acceptance criteria.
majiayu000/claude-skill-registry 163
-
Adding a Ticker
Creates or modify a ticker of a microservice. Use when explicitly asked by the user to create or modify a ticker or a recurring operation for a microservice.
majiayu000/claude-skill-registry 163
-
general-research-workflow
Core research loop for scoping, searching, analyzing, and reporting with explicit constraints and validation.
majiayu000/claude-skill-registry 163
-
google-cloud-build-expert
Expert knowledge of Google Cloud Build CI/CD pipelines including cloudbuild.yaml syntax, build steps, builders, substitution variables, triggers, secrets, artifact handling, and deployment to Cloud Run. Use when working with Cloud Build configurations, troubleshooting build pipelines, or deploying to Google Cloud Platform.
majiayu000/claude-skill-registry 163
-
dotnet-dependency
This skill should be used when investigating .NET project dependencies, understanding why packages are included, listing references, or auditing for outdated/vulnerable packages.
majiayu000/claude-skill-registry 163
-
maestro-core
Use when any Maestro skill loads - provides skill hierarchy, HALT/DEGRADE policies, and trigger routing rules for orchestration decisions
majiayu000/claude-skill-registry 163