ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cloud-cost-management
Optimize and manage cloud costs across AWS, Azure, and GCP using reserved instances, spot pricing, and cost monitoring tools.
majiayu000/claude-skill-registry 163
-
Traversing Citation Networks
Smart backward and forward citation following via Semantic Scholar, with relevance filtering and deduplication
majiayu000/claude-skill-registry 163
-
Inversion Exercise
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
majiayu000/claude-skill-registry 163
-
docusaurus-deployer
This skill should be used when deploying a Docusaurus site to GitHub Pages. It automates the configuration, building, and deployment process, handling GitHub Pages setup, environment configuration, and CI/CD automation. Includes local validation before GitHub Actions triggering.
majiayu000/claude-skill-registry 163
-
rls-policy-consolidator
Consolida múltiples políticas RLS permisivas redundantes en Supabase. Usa cuando hay varias policies del mismo rol/acción, warnings de múltiples permissive policies, o tarea 2.1 del PLAN_MEJORAS.md.
majiayu000/claude-skill-registry 163
-
Deploying to Production
Automates GitHub repository creation and Vercel deployment for Next.js websites. Use when deploying new websites, pushing to production, setting up CI/CD pipelines, or when the user mentions deployment, GitHub, Vercel, or going live.
majiayu000/claude-skill-registry 163
-
RAN Optimizer
Comprehensive RAN optimization with swarm coordination, cognitive consciousness, and 15-minute closed-loop autonomous cycles. Use when optimizing RAN performance, implementing self-healing networks, deploying swarm-based optimization, or enabling cognitive RAN consciousness.
majiayu000/claude-skill-registry 163
-
onnx-converter
Onnx Converter - Auto-activating skill for ML Deployment.
Triggers on: onnx converter, onnx converter
Part of the ML Deployment skill category.
majiayu000/claude-skill-registry 163
-
fn-args-deps
Enforce the fn(args, deps) pattern: functions over classes with explicit dependency injection
majiayu000/claude-skill-registry 163
-
cold-start-optimizer
Provides guidance on reducing Lambda cold start times through binary optimization, lazy initialization, and deployment strategies. Activates when users discuss cold starts or deployment configuration.
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
-
setup-cdk-templates
Use when creating CLAUDE.md files or .claude/ directories - detects project type, generates appropriate templates, and scaffolds Claude configuration with commands and hooks
majiayu000/claude-skill-registry 163
-
julien-wordpress-structure-validator
This skill validates WordPress FSE (Full Site Editing) theme structure including templates hierarchy, page associations, theme.json configuration, block styles, featured images usage, file permissions, and UpdraftPlus backup configuration. Use when auditing a WordPress site, after creating/modifying templates, before production deployment, or when troubleshooting backup issues.
majiayu000/claude-skill-registry 163
-
why-verify-risk
学習目的で、あらゆる提案変更に WHY / VERIFY / RISK とロールバックを必ず付ける（コード・コマンド・AWS手順）。WHYは「選択肢→特徴→結論（最適案）」で統一する。
majiayu000/claude-skill-registry 163
-
k8s-security-policies
Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.
majiayu000/claude-skill-registry 163
-
data-notebook-refiner
Standards for high-quality Jupyter Notebooks. Focuses on readability, reproducibility, and educational value.
majiayu000/claude-skill-registry 163
-
design-principles
Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use this skill when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimalist with taste. Every pixel matters.
majiayu000/claude-skill-registry 163
-
adk-deployment-specialist
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
majiayu000/claude-skill-registry 163
-
update-dependent-tasks
Automatically unblock tasks when dependencies are satisfied
majiayu000/claude-skill-registry 163
-
atmos-auth
Use when authenticating with AWS via Atmos. Covers ATMOS_PROFILE setup, SSO login, and how Atmos automatically assumes the correct identity per stack. Use for authentication setup, SSO login issues, and permission errors.
majiayu000/claude-skill-registry 163
-
peft
Parameter-efficient fine-tuning with LoRA and Unsloth. Covers LoraConfig,
target module selection, QLoRA for 4-bit training, adapter merging, and
Unsloth optimizations for 2x faster training.
majiayu000/claude-skill-registry 163
-
adk-deployment-specialist
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
majiayu000/claude-skill-registry 163
-
tutorial-5
Manage D&D 5e character progression with XP tracking, automatic leveling, HP increases, proficiency bonus progression, and spell slot advancement. This skill should be used when conducting combat encounters with character advancement, awarding experience points after victories, or managing character level-ups in the training arena.
majiayu000/claude-skill-registry 163
-
enforcing-type-safety
Enforces type safety in TypeScript/Python implementations. Any/any types strictly prohibited. Use when processing API responses, integrating external libraries, or implementing data validation. Supports strict mode configuration and type guard implementation.
majiayu000/claude-skill-registry 163