Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
hugging-face-space-deployer
Create, configure, and deploy Hugging Face Spaces for showcasing ML models. Supports Gradio, Streamlit, and Docker SDKs with templates for common use cases like chat interfaces, image generation, and model comparisons.
majiayu000/claude-skill-registry 163
-
speckit-specify-zh
中文功能规范创建工具，用于将自然语言功能描述转换为结构化的功能规范文档。支持自动生成分支名称、创建Git分支、初始化规范文件和质量验证。触发词包括："speckit规范"、"功能规范"、"创建规范"、"功能描述转换"、"speckit-specify"。当用户需要将功能想法转换为结构化规范时使用此技能。
majiayu000/claude-skill-registry 163
-
automation-script-generator
繰り返し作業の自動化スクリプト生成スキル。Shell、Python、PowerShell、Node.jsスクリプトを生成。ファイル操作、データ処理、API連携、CI/CD、バックアップ、監視、レポート生成を自動化。
majiayu000/claude-skill-registry 163
-
vLLM Slack Summary
Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team
majiayu000/claude-skill-registry 163
-
universal-zadorian-search-engineer
majiayu000/claude-skill-registry 163
-
decision-analysis
Decision modeling using decision tables, weighted scoring matrices, and decision trees. Structures complex decisions with clear criteria, alternatives evaluation, and outcome prediction.
majiayu000/claude-skill-registry 163
-
multi-stage-pipeline
Create multi-stage Azure Pipelines with deployment gates and approvals. Use when implementing complex deployment pipelines with multiple environments.
majiayu000/claude-skill-registry 163
-
gcs-bucket-config
Gcs Bucket Config - Auto-activating skill for GCP Skills.
Triggers on: gcs bucket config, gcs bucket config
Part of the GCP Skills skill category.
majiayu000/claude-skill-registry 163
-
sr-cardoso-ops
Operacoes e deploy do Sr Cardoso (Cloud Run, Firestore rules/indexes, env vars, scripts, Docker). Use quando configurar ambiente, rodar deploy, revisar infra GCP ou rotinas de setup.
majiayu000/claude-skill-registry 163
-
decision-framework
Walk through decisions using a 3-part framework (first-principles, cost/benefit, second-order effects). Use when choosing between options, evaluating trade-offs, or making high-stakes decisions.
majiayu000/claude-skill-registry 163
-
td-decision-forest
Decision forest ensemble classifier for robust predictions
majiayu000/claude-skill-registry 163
-
external-dns
Comprehensive guide for configuring, troubleshooting, and implementing External-DNS across Azure DNS, AWS Route53, Cloudflare, and Google Cloud DNS. Use when implementing automatic DNS management in Kubernetes, configuring provider-specific authentication (managed identities, IRSA, API tokens), troubleshooting DNS synchronization issues, setting up secure production-grade external-dns deployments, optimizing performance, avoiding rate limits, or implementing GitOps patterns with ArgoCD.
majiayu000/claude-skill-registry 163
-
admin-infra-hetzner
Deploys infrastructure on Hetzner Cloud with ARM64 or x86 servers.
Cost-effective European cloud with excellent price/performance ratio.
Use when: setting up Hetzner Cloud infrastructure, deploying ARM64 servers (CAX), x86 servers (CX/CPX), looking for affordable alternative to OCI.
Keywords: hetzner, hcloud, ARM64, CAX, CX, CPX, infrastructure, server setup, european cloud
majiayu000/claude-skill-registry 163
-
infra-adoption
Discover and adopt existing infrastructure - analyze Terraform structure, AWS profiles, and custom agents
to generate faber-cloud configuration and migration plan
majiayu000/claude-skill-registry 163
-
notebooks-back-end
Use when working with DuckDB databases, Makefiles, or building/deploying notebooks. Triggers on DuckDB queries, database creation, Makefile editing, make targets (build, data, etl), GitHub Actions workflows, CI/CD, and creating new notebook repositories.
majiayu000/claude-skill-registry 163
-
bash-audit
Comprehensive security and quality audit for shell scripts (bash, sh, zsh) using defensive programming principles and ShellCheck static analysis. Use when user asks to audit, review, check, lint, validate, or analyze shell scripts for security vulnerabilities, bugs, errors, defensive programming compliance, or best practices. Also triggers for improving script quality, finding script errors or issues, checking portability problems (macOS vs Linux), validating error handling, fixing shellcheck warnings, reviewing legacy automation scripts before release, setting up CI/CD linting infrastructure, configuring pre-commit hooks, understanding ShellCheck error codes, suppressing false positives, or ensuring script portability and quality.
majiayu000/claude-skill-registry 163
-
jomonsho-incident-triage
本番インシデントの調査データを収集する。
majiayu000/claude-skill-registry 163
-
iam-policy-creator
Iam Policy Creator - Auto-activating skill for AWS Skills.
Triggers on: iam policy creator, iam policy creator
Part of the AWS Skills skill category.
majiayu000/claude-skill-registry 163
-
advanced-kubernetes
Custom Resource Definitions (CRDs) extend Kubernetes API with custom object types. Operators are controllers that manage these custom resources using domain-specific logic.
majiayu000/claude-skill-registry 163
-
array-techniques
Master essential array techniques including two pointers, sliding window, and prefix sums for efficient problem solving with O(n) patterns.
majiayu000/claude-skill-registry 163
-
s3-lifecycle-config
S3 Lifecycle Config - Auto-activating skill for AWS Skills.
Triggers on: s3 lifecycle config, s3 lifecycle config
Part of the AWS Skills skill category.
majiayu000/claude-skill-registry 163
-
talk-to-experts
Consults a council of AI experts using multiple models in parallel. Activate when user says "ask the experts", "consult the experts", "get expert opinions", or requests multi-model expert opinions on complex decisions, architecture, or strategic questions.
majiayu000/claude-skill-registry 163
-
ci-health-check
Check CI/CD workflow status and troubleshoot failing checks in GitHub Actions
majiayu000/claude-skill-registry 163
-
managing-prompts
Creates, analyzes, updates, and optimizes prompts using Claude 4.5 best practices, guardrails, context management, and prompt engineering patterns. Use when user asks how to write effective prompts, explaining prompt engineering techniques, understanding Claude 4.5 best practices, describing prompt patterns and structures, creating new prompts, evaluating existing prompts for improvements, determining if current logic should be extracted to prompts, identifying outdated prompt techniques, optimizing context usage, implementing guardrails, or when user mentions "prompt engineering", "hallucinations", "context optimization", "prompt caching", "chain-of-thought", or asks if logic should become a prompt.
majiayu000/claude-skill-registry 163