DevOps & Infra

akashrpatil Bundle

Escalate privileges from a low-privilege shell to root on Linux systems using kernel exploits, SUID binaries, capabilities, cron jobs, PATH hijacking, and misconfigured services. Use this skill during penetration tests after gaining initial access to a Linux host. Covers automated enumeration with LinPEAS, manual techniques, Docker/container escapes, and sudo abuse for complete privilege escalation.

akashrpatil Bundle

Detect and exploit Server-Side Request Forgery (SSRF) vulnerabilities to access internal services, cloud metadata endpoints, and restricted network resources. Use this skill when testing URL fetch features, webhook configurations, file imports, PDF generators, or any functionality that makes server-side HTTP requests. Covers blind SSRF, DNS rebinding, cloud metadata exploitation (AWS/GCP/Azure), and protocol smuggling for maximum impact.

fdhhhdjd Bundle

Skill to automate the full deployment process including build, test, and release steps

scytale-labs Bundle

Use when the user asks about TSA Cybersecurity Security Directives — pipeline (SD Pipeline-2021-01, -02), rail (SD-1580/82-2022-01), aviation (SD-1542/44-22, SD-1580-21-01), the four required cybersecurity measures (network segmentation, access control, continuous monitoring, patch management), Cybersecurity Implementation Plans (CIP), Cybersecurity Assessment Plans (CAP), or TSA reporting obligations to CISA. For US owners and operators of designated critical pipelines, freight/passenger railroads, and certain airports/aircraft operators.

geegewu Bundle

播客完整处理流程。RSS下载→转录→提炼核心文本→卡片渲染→社交文案。用户说"处理播客"、"播客流程"、"podcast pipeline"时触发。

shakeebshaan Skill

Audit a trading-strategy backtest for look-ahead bias, overfitting, unrealistic assumptions, and regime-dependence. Use this skill when reviewing backtest code, backtest results, equity curves, or considering whether to deploy a strategy live.

a17339529088 Bundle

在用户提及 GitHub 仓库、Issue、Pull Request、Actions、代码管理相关内容与操作时使用此技能。触发关键词包括：创建 issue、新建 PR、合并 PR、查看 issue、列出 PR、搜索仓库、创建仓库、fork 仓库、创建 release、上传 release asset、查看 workflow、触发 workflow、查看 run、取消 run、重新运行、查看 artifact、管理 secret、管理 variable、查看 commit、查看 check、创建 status、查看通知、标记已读、star 仓库、watch 仓库、创建 gist、查看 gist、创建部署、查看部署状态、管理团队、查看组织成员、创建 label、分配 assignee、创建 milestone、查看 branch、创建 branch、保护分支、查看文件内容、更新文件、创建 tag、创建 blob、创建 tree、更新 ref、搜索代码、搜索 issue、搜索用户、GitHub API、github 搜索、代码仓库、版本管理、持续集成、CI/CD。覆盖八大场景：(1) Issues——创建/获取/更新/锁定/评论/标签/分配/里程碑 (2) Pull Requests——创建/获取/更新/合并/审查/评论/文件变更 (3) Repos——获取/创建/fork/内容管理/分支/Release/文件上传 (4) Users——认证用户信息/用户资料/SSH Key/邮箱 (5) Search——搜索仓库/Issue/代码/Commit/用户/Topic (6) Actions——Workflow/Run/Job/Artifact/Secret/Variable (7) Orgs & Teams——组织/成员/团队管理 (8) Git Low-level——Blob/Tree/Commit/Ref/Tag 底层操作。不要在以下场景触发此技能：GitHub Enterprise Server 管理员 API、GitHub Apps Installation Token 管理、OAuth 浏览器授权流程、gh CLI 封装命令、GraphQL API 调用、Codespaces 管理、Billing 计费操作、Migration 迁移操作。

willwebster5 Bundle

Design multi-event behavioral detection rules using CrowdStrike NG-SIEM correlate() function. Use when building attack chain detections, correlating multiple events across time windows, or creating behavioral rules that detect complex threat patterns across AWS, EntraID, and CrowdStrike data sources.

taiki-yoshida Bundle

Scaffold and deploy remote MCP servers on Azure Functions using Microsoft.Azure.Functions.Worker.Extensions.Mcp (.NET isolated worker). Use when user wants to build an MCP server hosted on Azure Functions, mentions azure-functions-mcp-extension, wants to expose tools to Claude/Copilot via Azure backend, or needs to scaffold a remote MCP server with Azure.

taiki-yoshida Bundle

Integrate Azure OpenAI services including GPT Realtime API (gpt-realtime-1.5) for real-time audio conversations via WebRTC. Use when user wants to build voice/audio AI apps, integrate Azure OpenAI realtime API, create conversational AI with speech, or connect to gpt-realtime models.

scytale-labs Bundle

Use when the user asks about FedRAMP — the US government cloud authorization program, impact levels (Low/Moderate/High/LI-SaaS), NIST SP 800-53 control baselines, the System Security Plan (SSP), 3PAO assessment, JAB vs Agency authorization paths, the FedRAMP Marketplace, the ATO (Authority to Operate), or continuous monitoring obligations. For cloud service providers selling to US federal agencies.

0xsanei Skill

Evolve trading strategies through genetic algorithms and adversarial combat. No API keys, no cloud — pure Python + numpy.

0xsanei Skill

Evolve trading strategies through genetic algorithms and adversarial combat. Run Darwinian selection on BTC data to discover battle-tested strategies. No API keys, no cloud.

kirillklem Bundle

Audit and speed up a slow module, code path, query, batch job, pipeline, or request handler. Trigger when the user asks to speed up or optimize performance, reports that something is slow, shares logs, traces, timings, or profiles showing high latency or low throughput, or when the current coding task clearly depends on fixing a runtime bottleneck. Diagnose before changing code: identify the hot path, classify the bottleneck (algorithmic, CPU, I/O, database, network, memory, serialization, contention, logging, or redundant work), propose ranked optimizations, apply the highest-confidence improvements, and remeasure. Use profiling, query plans, logs, benchmarks, and suitable tools such as vectorization, batching, caching, indexing, concurrency, DuckDB, or Polars when justified by evidence. Do not use for generic bug fixing, correctness-only debugging, build or install speed, infra provisioning, or vague optimize requests with no performance signal.

kawaruko Bundle

Deploy or align a user's local shell environment, especially zsh, oh-my-zsh, tmux, and dotfiles. Use when the user wants terminal setup, dev-container shell parity, or reproducible workstation environment configuration across platforms.

kawaruko Skill

Deploy or align a user's local shell environment, especially zsh, oh-my-zsh, tmux, and dotfiles. Use when the user wants terminal setup, dev-container shell parity, or reproducible workstation environment configuration across platforms.

cypack Bundle

Dokploy self-hosted PaaS platform yonetimi (MCP API + Playwright troubleshooting). Deploy icin DokployServer MCP API kullanir. UI sorunlarinda Playwright ile browser katmanini test eder. PLATFORM: Dokploy (30.2k GitHub stars) - Docker + Traefik mimarisi URL: http://localhost:3000 KULLANIM DURUMLARI: - Uygulama deploy et, redeploy, rollback - Compose service olustur ve deploy et (GOLDEN PATH: REST API ile composeFile set et) - Docker container yonetimi (restart, logs, status) - Backup zamanlama ve manuel tetikleme - Domain / SSL yonetimi - Proje ve environment yonetimi - Registry (Docker Hub, GHCR, private) yonetimi - Deployment gecmisi ve izleme - UI sorun giderme (Playwright ile browser katmani test) TRIGGERS: dokploy, deploy, redeploy, rollback, compose deploy, backup, domain, ssl, traefik, container restart, deployment, waha, whatsapp api, connection failed, not connected KRITIK KURALLAR: 1. compose-update MCP ile composeFile GUNCELLENMIYOR → REST API kullan 2. application-saveEnvironment env var Docker Sw

khaledmahfouz5 Bundle

Apply UNIX philosophy principles to any coding or system-design conversation. Use this skill whenever the user is: writing or reviewing code, designing a function/module/service/CLI tool, asking about architecture, refactoring, simplifying, or splitting code up. Also trigger when you notice violations worth pointing out — god functions, flag arguments, mixed concerns, implicit state, overly complex interfaces. Works for any language (Python, Go, Bash, JS, Rust, etc.) and any scope (a 5-line function or a 5-service system). Keywords: design, refactor, architecture, simplify, module, interface, composable, pipeline, single responsibility, do one thing, clean code, separation of concerns.

uhdyindy Bundle

Cloud and container security testing - AWS, Azure, GCP, Docker, and Kubernetes misconfigurations and exploitation.

uhdyindy Skill

Detects cloud providers (AWS, Azure, GCP) and PaaS platforms

kirillklem Bundle

Orchestrate a multi-stage research-to-architecture-to-implementation workflow for a non-trivial software change. Trigger when the user wants to start, continue, or structure a complex change involving research, architecture, module boundaries, adoption planning, or execution planning, including phrases like "давай соберем workflow", "сделай pipeline для этого изменения", "свяжи research и plan", "начнем change dossier", or similar. Create and maintain a change dossier under docs/changes/<slug>/, determine the correct current stage, explicitly route the work to the appropriate specialized skill, and keep INDEX.md synchronized across stages. Do not replace the specialized skills with one large analysis. Orchestrate them and maintain documentation continuity.

saolalab Skill

CI/CD pipeline design and management. Use when building, troubleshooting, or optimizing build and deployment pipelines.

saolalab Skill

Guide for designing, building, and maintaining reliable data pipelines

sawallesalfo Skill

Capture a full-page screenshot of any public URL using Playwright's headless Chromium browser. Use this skill whenever the user provides a URL and asks to take a screenshot, capture a page, grab a visual snapshot, or see what a website looks like. Also trigger when the user says things like "screenshot this", "capture this page", "show me what this site looks like", or "get a screenshot of [URL]". Works on GitHub, Docker Hub, dev.to, npm, PyPI, and any public website. No API key required — uses a local headless browser via Playwright.

saolalab Skill

Sales pipeline management and forecasting. Use when tracking opportunities, forecasting revenue, or managing deals.

doitintl Bundle

Use this skill ALWAYS when the user asks about cloud costs, spending, reports, services, invoices, or any DoiT Cloud Analytics data. Triggers on requests like "create a report", "show my costs", "top services", "spending by project", "list reports", "monthly cost breakdown", "cost by region", "how much am I spending", or any cloud cost analysis. This skill MUST be used before calling any DoiT MCP tools directly.

0xarx Bundle

Build applications with the Claude Managed Agents API — Anthropic's managed infrastructure for running Claude as an autonomous agent in a cloud container. Trigger this skill whenever the user wants to build with managed agents, asks about agent sessions, wants to stream agent events, uses client.beta.agents / client.beta.sessions / client.beta.environments, asks about the managed-agents-2026-04-01 beta, wants Claude to autonomously run tools in a sandbox, or asks about outcomes, multiagent orchestration, or persistent agent memory. Also trigger when the user asks how to run Claude for long-running tasks, async work, or when they want Claude to execute bash commands, write files, or browse the web autonomously.

jaypalsolanki Skill

Hardens CI/CD pipelines with quality gates, security checks, deployment safety, and rollback readiness. Use when creating or improving build and release pipelines.

jaypalsolanki Skill

Reviews Azure and AWS architectures for reliability, operability, and cost efficiency. Use during architecture decisions, optimization work, or production readiness reviews.

harudium Skill

Use when resuming the in-flight 2026-03-25 AWS rollout and you need the exact current deployment snapshot without loading the full migration history.

harudium Skill

Use when continuing the 2026-03-26 model-api vLLM sidecar rollout where compute-2b is the only known-good outbound placement, compute-2a still fails Hugging Face outbound, EFS already contains model artifacts, and the next step is a direct virtual-subnet canary from devdi without helper wrappers.

arrect Bundle

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

arrect Bundle

Advanced academic paper writing engine for Gemini 3.1 Pro. Features: 12-agent conceptual pipeline, Google Search citation validation, Obsidian-optimized Markdown (LaTeX + [[links]]), and hierarchical multi-file project structure. Triggers: write paper, academic paper, guide my paper, parse reviews, 寫論文, 學術論文, 引導我寫論文, 審查意見.

arrect Bundle

Orchestrator for the full academic research pipeline with automated project state tracking. Manages the transition between RESEARCH, WRITE, REVIEW, and PUBLISH states. Features: shell-based file management, automatic YAML frontmatter synchronization (status: active/archived), and wiki-link [[ ]] reference management.

stoffl6781 Skill

Go-Live Checkliste und Deployment. Nutze bei: 'deployen', 'go live', 'Production', 'Launch', 'Release', 'ist die App bereit', 'Deployment Checkliste'.

travisleeeeee Bundle

Responsibilities