Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
batch-report-generator
Generate GenuVerity fact-check reports from structured input (Gemini research output). Use /batch-report to process research into HTML reports. Optimized for token efficiency - expects pre-researched sources.
majiayu000/claude-skill-registry 163
-
container-debugging
Debug Docker containers and containerized applications. Diagnose deployment issues, container lifecycle problems, and resource constraints.
majiayu000/claude-skill-registry 163
-
starwards-ci-debugging
Debug Starwards GitHub Actions CI failures - analyze logs for ESLint/TypeScript/E2E/Docker errors, identify root causes, and apply fixes locally before pushing
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
-
cross-platform-guardian-wcygan-dotfiles
majiayu000/claude-skill-registry 163
-
btdp-groups-api
Expert in managing GCP Groups (Google Cloud Identity and Azure AD) via the Groups API. **Use this skill whenever the user mentions 'groups', 'group members', 'add to group', or 'remove from group'.** Handles listing members (with file-based approach for large groups), adding/removing members, and checking membership. Uses ADM token authentication. **DO NOT use for ServiceNow groups.**
majiayu000/claude-skill-registry 163
-
google-cloud-configs
Google Cloud Platform configuration templates for BigQuery ML and Vertex AI training with authentication setup, GPU/TPU configs, and cost estimation tools. Use when setting up GCP ML training, configuring BigQuery ML models, deploying Vertex AI training jobs, estimating GCP costs, configuring cloud authentication, selecting GPUs/TPUs for training, or when user mentions BigQuery ML, Vertex AI, GCP training, cloud ML setup, TPU training, or Google Cloud costs.
majiayu000/claude-skill-registry 163
-
pr-merge
Safely merge GitHub pull requests using comprehensive pre-merge validation. Use this skill when the user asks to merge a PR, complete a PR workflow, or check if a PR is ready to merge. Validates CI/CD status, reviews, and conflicts before merging with the appropriate strategy.
majiayu000/claude-skill-registry 163
-
cache-strategies
Caching patterns, TTL management, eviction policies for Redis implementations. Use when implementing cache-aside, write-through, write-back patterns, TTL management, or cache invalidation strategies.
majiayu000/claude-skill-registry 163
-
agent-platform-engineer
Expert platform engineer specializing in internal developer platforms, self-service infrastructure, and developer experience. Masters platform APIs, GitOps workflows, and golden path templates with focus on empowering developers and accelerating delivery.
majiayu000/claude-skill-registry 163
-
upgrading-dotnet
Upgrade .NET projects to newer versions. Use when upgrading TargetFramework in csproj/vbproj/fsproj files, migrating between .NET versions, configuring global.json, pinning SDK versions, updating CI/CD pipelines for .NET, or troubleshooting .NET upgrade issues.
majiayu000/claude-skill-registry 163
-
when-developing-ml-models-use-ml-expert
Specialized ML model development, training, and deployment workflow
majiayu000/claude-skill-registry 163
-
call-brief-framework
Use to structure concise call briefs with objectives, agendas, and role assignments.
majiayu000/claude-skill-registry 163
-
alert-management
Implement comprehensive alert management with PagerDuty, escalation policies, and incident coordination. Use when setting up alerting systems, managing on-call schedules, or coordinating incident response.
majiayu000/claude-skill-registry 163
-
collision-zone-thinking
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?" Use when conventional approaches feel inadequate and you need breakthrough innovation by forcing unrelated concepts together.
majiayu000/claude-skill-registry 163
-
k8s-clusters-julianobarbosa-claude-code-skills-c4ec3a34
majiayu000/claude-skill-registry 163
-
gitlab-cicd-pipeline
Design and implement GitLab CI/CD pipelines with stages, jobs, artifacts, and caching. Configure runners, Docker integration, and deployment strategies.
majiayu000/claude-skill-registry 163
-
k8s-security
Kubernetes and OpenShift security assessment, hardening, and compliance. Use this skill when:
(1) Auditing cluster or workload security posture
(2) Implementing Pod Security Standards/Admission
(3) Configuring RBAC roles and permissions
(4) Setting up NetworkPolicies for zero-trust
(5) Managing Secrets securely (encryption, external secrets)
(6) Scanning images for vulnerabilities
(7) Implementing OCP SecurityContextConstraints
(8) Compliance checking (CIS benchmarks, SOC2, PCI-DSS)
(9) Security incident investigation
(10) Hardening cluster components
majiayu000/claude-skill-registry 163
-
wolf-adr
Architecture Decision Records index with searchable topics and phase-based organization (120+ ADRs from 50+ phases)
majiayu000/claude-skill-registry 163
-
bun-fs-helpers
Pure Bun-native filesystem utilities from @sidequest/core/fs. Use when you need command-injection-safe filesystem operations, prefer Bun over node:fs, or want token-efficient fs helpers. All functions use Bun.spawn, Bun.file(), or Bun.write() - no node:fs dependencies.
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
-
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
-
gcp-operations
This skill should be used when the user asks to "check logs", "view Cloud Run logs", "deploy a service", "check service status", "manage secrets", "add a secret", "list services", "check what's running", or mentions GCP, Google Cloud, Cloud Run, Secret Manager, or deployment. Provides commands and guidance for operating Local Pulse services on Google Cloud Platform.
majiayu000/claude-skill-registry 163
-
using-core
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
majiayu000/claude-skill-registry 163