DevOps & Infra

ekinoxis-evm Skill

Solidity development with Foundry (forge, cast, anvil) as used in our contract suites. Use when writing or running Solidity tests, deploying contracts with forge script, verifying on Basescan or Blockscout, forking a network for tests, debugging stack-too-deep or via_ir compile issues, managing lib/ dependencies with forge install, or inspecting chain state with cast. Covers foundry.toml config, our optimizer settings, and the deploy checklist.

ekinoxis-evm Skill

Serverless Redis with Upstash — REST-based client for edge and serverless, rate limiting with @upstash/ratelimit, caching, and session or nonce storage. Use when adding rate limiting to an API route, caching an expensive read, or storing short-lived state that Supabase would be overkill for.

ekinoxis-evm Skill

Deploying and operating Ekinoxis apps on Vercel — project linking, environment variables per environment, preview vs production deploys, build failures, runtime logs and errors, cron jobs, and domain setup. Use when a deploy fails, when an app works locally but not in production, when adding or rotating an env var, when setting up a scheduled job, or when configuring a custom domain.

agentik-os Skill

Analyze extracted Meta ad creatives and generate a professional competitive strategy report with inline videos/images grouped by funnel and landing page. Use when user says "/meta_ads_analyser", "analyze ads", "analyse les pubs", "rapport de stratégie pub", "ad strategy report", "review competitor creatives", "analyse créatives concurrentes", or "audit pub Meta". Run /meta_ads_extractor first to extract assets. For the full extraction + analysis pipeline in one command, see /ads_analyst.

agentik-os Bundle

Nettoyage intelligent du VPS/projets — analyse disque, fermeture des sessions de travail détachées (protège la connexion + l'infra), purge sûre (cache Docker/APT/journal, résidu /tmp, caches Bun/npm/go), purge des artefacts de build rebuildables (target/ Rust, node_modules, .next) avec garde-fou anti-session-active, et audit de cohérence de la documentation des projets.

agentik-os Skill

Extract and save ad creative assets (images + videos) from the Meta Ads Library via browser automation, with dimensions, aspect ratios, and CTA destination URLs. Use when user says "/meta_ads_extractor", "extract Meta ads", "download competitor ads", "swipe file", "save Facebook ad creatives", "scrape ad library", or in French "extrais les pubs Meta", "telecharge les pubs concurrentes", "recupere les creatives Facebook", "fais un swipe file". For analyzing extracted ads into a strategy report, see /meta_ads_analyser. For the full extraction + analysis pipeline in one command, see /ads_analyst.

agentik-os Bundle

Linear feedback resolution pipeline. Auto-detects intent (fix feedbacks by default), loads the 10-step protocol with DYNAMIC audit chain (audit-selector.py picks 4-12 relevant audits per ticket, scoped to the ticket only), dispatches sequential work sessions, Oracle quality gate. Use when user says "/linear", "linear", "fix linear", "resolve feedback", "regler les feedbacks".

agentik-os Skill

Deploy applications and websites to Vercel (preview by default, production only on explicit ask). Use when the user says "deploy my app", "deploy and give me the link", "push this live", "create a preview deployment", "ship it to Vercel", or in French "déploie sur Vercel", "mets en ligne", "mets en prod sur Vercel", "donne-moi le lien de déploiement". NOT for non-Vercel hosts (Netlify, Cloudflare, Convex) or for `/prod` pipeline runs that bundle build+test+push.

agentik-os Skill

Design Engineer Agent — single coherent design voice. Activate when the user types /gestalt, or asks to take any input (brief, monologue, URL, copy, raw idea) through the full design-engineering pipeline, or says "design this", "turn this into an experience", "design narrative", "UX direction from this brief", "conçois", "transforme en expérience", "direction design", "narratif design". Runs /mono → /lense → /sculp → /spruce STRICTLY in sequence, autonomously — each step consumes the prior step's output, so the pipeline is NOT parallelizable. Produces a stable brief, grounded references, a complete UX structure, and an embellished design narrative. The whole is greater than the parts. Not for forensic audits (use /uiuxaudit) or multi-angle research.

agentik-os Skill

Orchestrate complete competitive ad research in one command. Extracts ads from Meta Ad Library, generates a strategy report, deep-dives top creatives, and analyzes every unique landing page into one intelligence package. Use when user says "/ads_analyst", "competitor research", "analyze competitor ads", "competitive intelligence", "spy on competitor ads", "Meta Ad Library analysis", or in French "analyse des pubs concurrentes", "recherche concurrentielle", "espionner les pubs", "veille concurrentielle pub", "intelligence concurrentielle". Combines /meta_ads_extractor and /meta_ads_analyser into one pipeline. For individual steps, use those skills separately.

jhamidun Skill

Разработка под AWS: CDK, Lambda, serverless, S3. Триггеры: «лямбда», «выложи на s3», «инфраструктура в aws».

jhamidun Bundle

YouTube Shorts с AI-аватаром: SRT-нарезка → HeyGen Avatar V → SubMagic → обложка → YT. Триггеры: «нарежь шортсы», «шорт из вебинара». НЕ субтитры к чужому видео→submagic.

jhamidun Bundle

Гонит статью по стадиям: рисёрч → драфт → фактчек → голос → корректура → редактура → обложка → docx. Триггеры «напиши статью на Habr/VC/РБК/LinkedIn», «прогони статью по конвейеру». НЕ один пост в канал → tg-post; НЕ глава книги → book-post.

jhamidun Bundle

Операционка контент-фабрики: органика → лиды, 6-шаговый pipeline, «1 формат = 1 агент». Триггеры: «машинка контента». НЕ отдельный пост→content-engine.

jhamidun Bundle

Финальная шлифовка нон-фикшн книги после того, как главы доведены до FINAL: 18 волн правки, каскад версий, cross-model review, тройная корректура, сборка EPUB+DOCX. Триггеры: «полируй книгу», «следующая версия книги», «книга готова, что дальше».

jhamidun Bundle

Разработка Telegram-ботов: python-telegram-bot, Telethon, деплой; антипаттерн бот-воронки из TG Ads. Триггеры: «напиши бота», «deploy бота».

jhamidun Bundle

Автономные агенты на Hermes (Python) и OpenClaw (TS): крон, плагины, Docker-деплой. Триггеры: «создай агента», «бот с нуля». НЕ MCP→mcp-builder; операции/дебаг бота→openclaw-ops.

jhamidun Skill

Конвейер художественного романа (dark/mafia/forbidden romance): библия персонажей, посценный синопсис, валидация глав против канона, чистка ИИ-стиля, иллюстрации. Триггеры: «напиши роман», «мафия-романс», «книга с иллюстрациями». НЕ нон-фикшн→book-post.

jhamidun Bundle

Гонит ролик по стадиям: бриф → сценарий → звук → раскадровка → промпты → генерация кадров → монтаж → контроль, и отдельно тренд → аватар → YouTube. Триггеры «сделай ролик», «ролик под ключ», «сделай видео и выложи». НЕ монтаж готового футажа → video-editor; НЕ одна AI-сцена → video-generation.

sameque00-source Bundle

This skill should be used when the user asks to build, debug, refactor, audit, test, secure, deploy, integrate, optimize, or architect software, websites, APIs, AI systems, databases, automations, or multi-agent workflows. Apply it whenever a task involves substantial software engineering or a production-quality code change.

majiayu000 Bundle

Integrate your Alexa Skill with a backend Lambda function with ease, on Sigma IDE

majiayu000 Bundle

Kubernetes SRE debugging and incident investigation for pod failures, crashes, and service issues. Use when: (1) Pods not starting, stuck, or failing (CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending), (2) Debugging Kubernetes errors or investigating "why is my pod...", (3) Service degradation or unavailability, (4) Reading pod logs or events, (5) Troubleshooting deployments, statefulsets, or daemonsets, (6) Root cause analysis for any Kubernetes incident. Triggers: "pod not starting", "pod stuck", "CrashLoopBackOff", "ImagePullBackOff", "OOMKilled", "Pending pod", "why is my pod", "kubernetes error", "k8s error", "service not available", "can't reach service", "pod logs", "debug kubernetes", "troubleshoot k8s", "what's wrong with my pod", "deployment not working", "helm install failed", "flux not reconciling"

majiayu000 Bundle

Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "run logs", "job list", "jenkins credentials", "jenkins node".

majiayu000 Bundle

TODO

majiayu000 Bundle

Deploy Azure infrastructure, BFF API, Static Web Apps, and configure App Service settings

majiayu000 Bundle

Audit shell scripts for correctness, portability, and common pitfalls. Triggers: shell script, bash, sh, script review, pipeline, exit code Use when: reviewing shell scripts, CI scripts, hook scripts, wrapper scripts DO NOT use when: creating new scripts - use attune:workflow-setup

majiayu000 Bundle

Guide for using the ct (CommonTools) binary to interact with pieces, recipes, and the Common Fabric. Use this skill when deploying recipes, managing pieces, linking data between pieces, or debugging recipe execution. Triggers include requests to "deploy this recipe", "call a handler", "link these pieces", "get data from piece", or "test this recipe locally".

majiayu000 Bundle

Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket Cloud".

majiayu000 Bundle

Delivery - CI/CD, testing, releases. Use when improving pipelines.

majiayu000 Bundle

Safe Docker management with dry-run defaults.

majiayu000 Bundle

Homelab infrastructure management with Terragrunt, OpenTofu, and Terraform patterns. Use when: (1) Planning or applying infrastructure changes to dev/integration/live clusters, (2) Adding/modifying machines in inventory.hcl, (3) Creating or updating units and stacks, (4) Working with feature flags, (5) Running validation (fmt, validate, test, plan), (6) Understanding the units→stacks→modules architecture, (7) Working with HCL configuration files, (8) Bare-metal Kubernetes provisioning or Talos configuration. Triggers: "terragrunt", "terraform", "opentofu", "tofu", "infrastructure code", "IaC", "inventory.hcl", "networking.hcl", "HCL files", "add machine", "add node", "cluster provisioning", "bare metal", "talos config", "task tg:", "infrastructure plan", "infrastructure apply", "stacks", "units", "modules architecture" Always use task commands (task tg:*) instead of running terragrunt directly.

majiayu000 Bundle

GitOps toolkit with Flux CD for Kubernetes continuous delivery. Use when implementing GitOps workflows, Helm releases, Kustomize deployments, or image automation. Triggers: fluxcd, flux, gitops, gitre

majiayu000 Bundle

Kafka operations expert for deployment, monitoring, and tooling. Kubernetes (Strimzi, Confluent), Terraform IaC, Prometheus/Grafana observability, and CLI tools (kcat, kafkactl). Use for Kafka deployment, monitoring setup, or operational tasks.

majiayu000 Bundle

Performance and load testing for API endpoints, payment pipeline, and concurrent user scenarios

majiayu000 Bundle

Kubernetes node autoscaling with Karpenter for efficient cluster scaling. Use when implementing node provisioning, consolidation, spot instance handling, or optimizing compute costs. Triggers: karpent

majiayu000 Bundle

Kubernetes native configuration management with Kustomize. Use when managing environment-specific configs, patching resources, or organizing Kubernetes manifests. Triggers: kustomize, kustomization, o