Showing 59191–59220 of 60156 skills
Run Claude Code headlessly as an isolated CI harness against any Anthropic Messages-compatible endpoint (local engine, gateway or hosted API) or a Claude subscription token. Covers credential isolation, stream-json transcripts, tool-call assertions, multi-turn scenarios, and endpoint/model compatibility diagnosis.
air-gapped/skills
Audit AND tune Linux/GPU inference hosts — read-only host snapshot (CPU power state, C-states, NUMA topology, PCIe link state, GPU settings, kernel boot params, sysctl, ulimits, IRQ affinity, container runtime), optional pinned-host↔GPU memcpy bench (torch + numactl), and per-lever cheat-sheets to flip settings (governor, EPP, cpuidle, persistence, ECC, hugepages, intel_iommu, NCCL env, tuned-adm profiles, per-chassis Dell BIOS references plus Supermicro/HPE BIOS-preset and iLO power-mode pointers). Sits beneath any inference framework (vLLM, sglang, TensorRT-LLM) — about the host, not the framework.
air-gapped/skills
Survey an RKE2 community cluster against an embedded compatibility registry of 20 stack components and produce a verdict for upgrade-readiness, drift-review, and version-skew questions. Components: RKE2, Rancher, Harvester, Cilium, Tetragon, cert-manager, Kyverno, KEDA, Argo CD, Harbor, Traefik, Rook, Ceph, OpenEBS, GitLab, ECK, Zalando postgres-operator, Grafana Mimir, NVIDIA GPU Operator, rancher-logging. Works air-gapped — compatibility data lives in `references/compat/`. Surveys run via `kubectl` + `helm` + `pluto` + the apiserver `apiserver_requested_deprecated_apis` metric from the operator's workstation. Community editions only — Prime/EE-gated content is ignored. NOT for installing components, NOT for executing upgrades, NOT for tracking per-cluster running state (the registry is methodology, not inventory).
air-gapped/skills
Package applications for OpenShift deployment: container images (UBI, arbitrary UID, multi-stage builds), packaging formats (Helm, Kustomize, Operators, OLM v1), CI/CD (Tekton, ArgoCD, Shipwright, Conforma), security (SCC, PSA, supply chain, image signing, secrets), operations (Routes, probes, scaling, monitoring, storage), disconnected/air-gapped patterns, and critical gotchas. Also when an app "works on Kubernetes but fails on OpenShift" (SCC denied, random/arbitrary UID, permission errors). Covers OCP 4.14-4.22. NOT for cluster installation or infrastructure management.
air-gapped/skills
Triage and fix the Microsoft Secure Boot 2011→2023 UEFI certificate rotation across Dell PowerEdge / iDRAC9 bare metal, Ubuntu/Linux servers, and Harvester HCI / KubeVirt guest VMs. All three 2011 CAs expired (two in June 2026, Windows Production PCA 2011 on 2026-10-19) — but UEFI firmware ignores certificate expiry, so nothing stopped booting; the real risks are forward-compat once a 2023-only-signed shim arrives (already true on aarch64) plus a dbx/revocation freeze. Routes to the per-platform fix: iDRAC BIOS-staged keys applied on reboot (Dell), fwupd-free manual `db` append self-authenticating via the existing 2011 KEK (Linux), and the Harvester virt-launcher OVMF floor (v1.6.0) with ephemeral-vs-persistent NVRAM triage (VMs). Covers the PK→KEK→db trust chain, the missing generic 2023 KEK payload, backup/rollback, and audit via mokutil / efi-readvar / racadm bioscert / Redfish.
air-gapped/skills
Use when reverse engineering tools are missing, not working, or need configuration. Installation guides for radare2 (r2), Ghidra, GDB, QEMU, Frida, binutils, and cross-compilation toolchains. Keywords - "install radare2", "setup ghidra", "r2 not found", "qemu missing", "tool not installed", "configure gdb", "cross-compiler"
aiskillstore/marketplace
Debugs REST and GraphQL APIs: unexpected status codes or bodies, auth failures (401/403, OAuth, API keys), schema mismatches, rate limits, pagination, and webhooks. Use when a request works in Postman but not in code, an integration test fails, or a callback misbehaves; not for UI rendering or DB tuning.
mouadja02/skills
Builds generative AI applications on Amazon Bedrock. Use when invoking models (Converse vs InvokeModel), building RAG with Knowledge Bases, creating Bedrock Agents, applying Guardrails, deploying to AgentCore, or migrating a Bedrock Agent (including inline agents) to an AgentCore Harness. Also for prompt caching, quota health checks and throttling diagnosis, cost attribution, chunking strategies, migrating between Claude model generations, choosing models (Claude, Llama, Nova, Titan), AgentCore Payments (x402, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required), and troubleshooting Bedrock errors such as ThrottlingException or AccessDeniedException. NOT for custom model training, Rekognition, or Comprehend.
mouadja02/skills
Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.
av/skills
Orchestrate AI coding agents (Claude Code, Codex, OpenCode) in isolated sandboxes using the @ai-hero/sandcastle SDK. Use when the user needs to (1) run agents AFK in Docker/Podman containers, (2) build multi-agent pipelines with plan-execute-review patterns, (3) run parallel agents on separate worktrees, (4) create iterative agent loops with maxIterations, (5) extract structured output from agent runs, (6) set up sandcastle in a new or existing project, or (7) write prompt files with template args and shell expressions.
av/skills
Retrieves current weather conditions and forecasts for any location worldwide
cisco-ai-defense/skill-scanner
Find and remove stale git worktrees across one or many repositories: prune records of worktrees whose folder is gone, report every linked worktree with its idle days, uncommitted changes and pull/merge request state (GitHub, cnb.cool, GitLab), and remove clean ones the user confirms (idle by default, with an explicit recent-only exception), keeping their branches unless the request is merged or closed. Use when the user asks, in any language, to clean up, list, audit or prune git worktrees, or when a sidebar such as Orca shows too many worktrees. Not for deleting branches without worktrees, cleaning build caches, or removing whole repositories.
Adonis0123/adonis-skills
Provides AWS CloudFormation patterns for Auto Scaling including EC2, ECS, and Lambda. Use when creating Auto Scaling groups, launch configurations, launch templates, scaling policies, lifecycle hooks, and predictive scaling. Covers template structure with Parameters, Outputs, Mappings, Conditions, cross-stack references, and best practices for high availability and cost optimization.
giuseppe-trisciuoglio/developer-kit
Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships. Use when modeling least-privilege access, cross-account assumptions, service roles, or reusable IAM stacks that other CloudFormation templates consume.
giuseppe-trisciuoglio/developer-kit
Provides advanced AWS CLI patterns for managing EC2, Lambda, S3, DynamoDB, RDS, VPC, IAM, and CloudWatch. Generates bulk operation scripts, automates cross-service workflows, validates security configurations, and executes JMESPath queries for complex filtering. Triggers on "aws cli help", "aws command line", "aws scripting", "aws automation", "aws batch operations", "aws bulk operations", "aws cli pagination", "aws multi-region", "aws profiles", "aws cli troubleshooting".
giuseppe-trisciuoglio/developer-kit
Provides a structured 8-phase workflow for resolving GitHub issues in Claude Code. Covers fetching issue details, analyzing requirements, implementing solutions, verifying correctness, performing code review, committing changes, and creating pull requests. Use when user asks to resolve, implement, work on, fix, or close a GitHub issue, or references an issue URL or number for implementation.
giuseppe-trisciuoglio/developer-kit
Provides comprehensive patterns for deploying Next.js applications to production. Use when configuring Docker containers, setting up GitHub Actions CI/CD pipelines, managing environment variables, implementing preview deployments, or setting up monitoring and logging for Next.js applications. Covers standalone output, multi-stage Docker builds, health checks, OpenTelemetry instrumentation, and production best practices.
giuseppe-trisciuoglio/developer-kit
Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty.
open-gitagent/opengap
Scan authorized Claude, Codex, or OpenCode session logs for recurring correction themes, reconstruct real tasks, and measure whether a selected Skill improves the actual output in a blinded no-Skill versus explicitly-loaded comparison. Use when someone asks for an agent brain scan, wants to know which Skills materially help their own work, or asks to test a Skill against their real sessions.
getedgehq/skills
服务器安全审计与加固。扫描 SSH、防火墙、端口暴露、文件权限、暴力破解等安全问题,生成报告并提供一键修复。当用户说服务器安全、安全审计、安全检查、安全加固时使用
majiayu000/spellbook
Infrastructure as Code with Terraform/OpenTofu. Points to Anton Babenko's terraform-skill and HashiCorp's own Terraform skills, and keeps the foundation's discipline (state and secrets, plan review, scans, deploy gate). Trigger to create modules, configure backends, write idiomatic HCL, or audit infrastructure.
christopherlouet/claude-base
Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or formatting-only repetition; protect facts and source anchors; queue only useful visual evidence; preserve uncertain originals; and benchmark efficiency and fidelity separately.
TIKAZI/TIKAZ-AI-Skills
A test skill with prompt injection patterns
cisco-ai-defense/skill-scanner
Document development environment requirements for team consistency and AI agent understanding during PRD v0.6 Architecture. Triggers on requests to define environment setup, document tooling, create dev setup guide, or when user asks "what tools do I need?", "environment setup", "dev environment", "CLI requirements", "project setup", "onboarding setup". Consumes TECH- (stack selections), ARC- (architecture decisions). Outputs ENV- entries for development, CI/CD, and infrastructure environments. Feeds v0.7 Build Execution.
mattgierhart/PRD-driven-context-engineering
Busabase AirApp-first email inbox-zero operator for reviewing unread mail, drafting replies, approving archive/mark-read/send actions, and executing only explicitly approved mailbox changes across configured accounts. Use when the user invokes $kelly-email, asks to process unread email, configure an email account, generate or review an approval batch, execute approved email decisions, or reach inbox zero.
mr-kelly/skills
Run a Busabase-backed job-search outreach desk with a bundled Hono App-in-Skill deployable to AirApp. Use when the user invokes $kelly-jobhunt or /kelly-jobhunt, wants to turn a resume into a structured profile and a typeset PDF, wants to find target companies and their contact addresses instead of applying through a job board, wants one tailored application email drafted per company, or wants to review and approve each send. Four subcommands - setup, profile, research, send - plus the desk itself. One company receives exactly one email; mailbox credentials live in the Busabase Vault and never reach browser code.
mr-kelly/skills
Search Scio for source-backed facts, explanations and references. Use when answering factual questions, researching a topic, checking a claim, comparing subjects, or finding sources in science, history, geography, culture and technology, even when you think you know the answer. Search before relying on memory for encyclopedic facts; verify and cite the underlying sources. Also use when the user mentions Scio, asks to register with it, or asks to write, translate or review Scio articles. Do not use for pure code edits, calculations, creative writing or rewriting supplied text unless external facts are needed. For library API syntax and version-specific setup, use official documentation or a documentation skill.
evisoft/scio.md
Architecture and decision guidance for enterprise-grade, database-agnostic natural-language-to-SQL over client-owned Postgres, MSSQL, MySQL, Oracle, Snowflake, and BigQuery warehouses at hundreds-of-databases / tens-of-thousands-of-tables scale. Load when designing, reviewing, or debugging text-to-SQL, NL2SQL, schema linking, catalog/metadata harvesting, semantic-layer routing, SQLGlot qualify/transpile/lineage, EXPLAIN (TYPE VALIDATE), BigQuery dry run, LSH value indexes, candidate reranking, repair loops, confidence gating, refusal policy, or read-only execution sandboxes; or when someone quotes a Spider accuracy number, proposes grammar-constrained decoding as an anti-hallucination fix, treats SQLGlot as a validator, or asks to point an LLM at an uncurated 10k-table warehouse. Covers Spider 2.0, BIRD, BIRD-CRITIC, BEAVER, CHESS, CHASE-SQL, MCS-SQL, XiYan-SQL, ReFoRCE, LinkedIn SQL Bot, dbt MetricFlow, Cube, Cortex Analyst, STEF, xgrammar, and Calcite.
opensite-ai/opensite-skills
reticlehq/reticle
PDM(Python Development Master)专业技能助手,提供完整的Python包管理和项目管理指导。 当用户询问以下内容时使用此技能: - PDM安装、项目初始化、依赖管理(add/remove/update) - pyproject.toml配置、PEP 621元数据 - PDM命令(pdm init, pdm add, pdm install, pdm lock, pdm publish等) - 虚拟环境配置、Python版本管理 - PDM插件开发、脚本编写(tool.pdm.scripts) - 依赖解析错误、构建配置问题 - 从Pipenv/Poetry/requirements.txt迁移到PDM - CI/CD集成、IDE配置(VS Code/PyCharm) - PDM高级用法(hooks、环境变量、集中式缓存) - 项目结构设计、最佳实践 - pdm.lock锁定文件管理 - 发布到PyPI、自定义索引配置 - Python/PDM安装(系统无Python时的引导安装) - conda环境与PDM协同使用 - monorepo多包项目管理 - PEP 723内联脚本、workspace原生支持 - uv后端集成、Docker容器化部署
xinetzone/SpecWeave