DevOps & Infra

inference-sh Bundle

Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an overview of inference.sh app development. Supports both Python and Node.js. Triggers: inference.sh app, belt app, inf.yml, inference.py, inference.js, deploy app, app development, build app, create app, GPU app, VRAM, app resources, app secrets, app integrations, multi-function app

inference-sh Bundle

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

gabrielmoreira Skill

Performance analysis patterns for runtime complexity, memory usage, cost optimization, and scalability assessment. Use for Big O analysis, profiling, caching strategies, and cloud cost modeling.

gabrielmoreira Skill

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API, switch from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. DO NOT USE FOR: building new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).

gabrielmoreira Skill

استعلام عن الوثائق الرسمية لشركة Microsoft للعثور على المفاهيم والدروس والأمثلة البرمجية عبر Azure و .NET و Agent Framework و Aspire و VS Code و GitHub والمزيد. يستخدم Microsoft Learn MCP كالإعداد الافتراضي، مع Context7 و Aspire MCP للمحتوى المتواجد خارج learn.microsoft.com.

inference-sh Skill

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

inference-sh Skill

Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools: inference.sh CLI, bash scripting, Python SDK, webhook integration. Use for: content automation, data processing, monitoring, scheduled generation. Triggers: ai automation, workflow automation, batch processing, ai pipeline, automated content, scheduled ai, ai cron, ai batch job, automated generation, ai workflow, content at scale, automation script, ai orchestration

bria-ai Bundle

End-to-end e-commerce product catalog generation — turn a folder of raw product photos into clean packshots, product cutouts, Amazon-style dimensions images, lifestyle scenes, and marketplace-ready listing variants for Amazon, Shopify, and Etsy. Powered by Bria.ai's product pipeline. Use when building a product catalog, batch-processing product photos, or creating packshots, cutouts, dimension images, lifestyle shots, or marketplace-compliant listing images at scale.

xuiltul Skill

AWS infrastructure collector. Fetches ECS status, CloudWatch logs, and metrics. Use when: checking ECS health, inspecting CloudWatch error logs, pulling infra metrics, or monitoring AWS resources.

xuiltul Skill

AWSインフラ情報収集ツール。ECS状態・CloudWatchログ・メトリクスを取得する。 Use when: ECS稼働確認、CloudWatchでエラーログ調査、メトリクス取得、AWSリソース監視が必要なとき。

xuiltul Skill

AWS 인프라 정보 수집 도구. ECS 상태·CloudWatch 로그·메트릭스를 가져온다. Use when: ECS 상태 확인, CloudWatch 오류 로그 조사, 메트릭스 조회, AWS 리소스 모니터링이 필요할 때.

idwong Skill

自动化工作流编排，支持 CI/CD 配置、脚本生成、定时任务和 Git Hooks 设置。

leeyudok Skill

Fact-check an agent's persistent memory against ground truth — verify each memory's load-bearing claims against code, database, issue tracker and filesystem, correct the stale ones, and report dead ones as archive candidates. Use when memory grows past ~30 files, right after a big stack/infra change (library swap, version upgrade, server migration, schema drop), when two memories seem to contradict each other, or on a "clean up / audit my memory" request.

craig-ai-tooling Bundle

Install and manage the Palette agent on a host that already has its own OS -- bring-your-own-OS edge devices, bare metal, VMs or cloud instances -- covering registration tokens, user-data, node validation, BYOOS-pack cluster profiles and uninstall. Use when Craig says: install the agent on this box, use agent mode, bring your own OS, register this existing host with Palette, add this VM as an edge host without building an ISO, create a registration token, why will the agent not register, uninstall the palette agent. Use spectrocloud-appliance-mode instead when the node is being shipped a Palette Edge ISO; note agent mode supports 1 or 3+ nodes and never 2.

craig-ai-tooling Bundle

Build the Palette Edge ISO and everything that goes into it -- CanvOS checkout and .arg file, earthly builds, provider images, user-data and site-user-data, content bundles, air-gap installs, 2-node HA. Use when Craig says: build an ISO, rebuild the ISO with X, which CanvOS tag or K8s version should we use, does appliance mode accept Site User Data, set the hostname and static IP in user-data, build the content bundle, do the airgap / offline / disconnected build, boot it on Proxmox and install, what will the provider image tag be, stylus or Kairos on the node, two-node with a witness, secure boot. Also for a node stuck in an install loop or a /oem user-data that did not take. Use spectrocloud-agent-mode instead when Palette manages an existing OS rather than shipping an ISO.

craig-ai-tooling Bundle

Figure out why a Palette cluster, edge host, or pack is not healthy -- cluster event stream and conditions via the API, log bundles, stylus and palette-agent logs over SSH, plus a list of which errors are real versus normal deploy noise. Use when Craig says: why is this cluster stuck, it is in Provisioning and not provisioning, take a look and see if you can figure out why, why are nodes going NotReady, why is it cordoned, everything is still failing yes, this pack will not install, the registry is syncing forever, gather the logs / grab a support bundle / pull a log bundle, deep dive on what is going on, do not fix it just diagnose it, watch the deploy and tell me what breaks. Also use while watching any deploy, since it says which errors to ignore and when impatience is the real problem.

datachain-ai Bundle

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/ (JSON + markdown). ALWAYS use this skill when the user creates a dataset, saves pipeline output, runs a data script, or references any storage bucket.

craig-ai-tooling Bundle

Write the long-form Markdown document behind a customer engagement -- the detailed writeup that an exec PDF, slide deck, or Google Doc is later cut from. Use when Craig says: write this up, build out a one pager, I need a doc for this customer, turn this into an actionable google doc, make the doc look nice with spectro branding, we need a migration plan (VMware or existing K8s to Palette), start a new doc to piece together why spectro and where our gaps are, write the postmortem / RCA / POC report / assessment / solution brief / architecture writeup. Also use for the detailed .md that feeds exec-doc-generator, where the markdown carries all the detail and the PDF is the 1-2 pager. Owns long-form writeups only -- for a 1-2 page executive PDF use exec-doc-generator, for a multi-page docs site use docs-site-generator, and for a slide deck (rendered PDF or a Google Slides link) use slide-deck-generator. See this skill's Deliverable Routing table for all four.

craig-ai-tooling Bundle

Build a multi-page documentation site (MkDocs Material or Docusaurus) -- structured Markdown, nav config, and Spectro Cloud theming. Craig calls these site docs or a docs-site. Use when he says: build this as a site doc like we did for other customers, turn it into a site doc page, write up and host a site-docs page walking through how to get this working, create the opp folder and a docs site for this customer, make a runbook site for their engineers, we need a v2 of these docs that is ops-focused and history-free, publish the docs when you are done. Also use for internal knowledge bases, deployment/runbook portals, and troubleshooting docs. Reach for this whenever the deliverable is more than one page and someone else has to navigate it; use doc-writer for a single long document. For prospect-facing POC guide sites use spectrocloud-poc-docs (it composes this skill); for architecture diagrams inside a site use architecture-diagrams. See the Deliverable Routing table in doc-writer.

craig-ai-tooling Bundle

READ THIS FIRST for any Spectro Cloud Palette API work -- getting the Palette API key out of 1Password, resolving the ProjectUid (always ask which project), pack and registry lookups, and the end-to-end order of operations for demo or meeting prep. Use whenever a task touches api.spectrocloud.com, a Palette tenant (prod, custeng-prod, a customer tenant, an EU tenant), or Craig says: use the spectrocloud skills that make sense, check palette, look at prod, I just added an API token for this tenant, get the key from op. Other spectrocloud-* skills assume this one has already been read; read it before them rather than guessing at auth, project scoping, or pagination.

craig-ai-tooling Bundle

Write the agent prompt when Palette / Spectro Cloud work is being fanned out to subagents, background loops, or another machine -- so each agent is told to READ the exact spectrocloud-* skills by name instead of improvising, and writes findings to a local ./learnings.md rather than back into the skills repo. Use when Craig says: use agents for this, fan this out, send an agent to do X, use ultracode or Fable on it, use the spectrocloud skills that make sense, push a prompt I can point Claude at, write me a prompt for this, do this on the other box. Also use when the main session is running low on context and Palette work should be delegated. Includes a mandatory critic pass over the drafted prompt before it is handed back.

craig-ai-tooling Bundle

Bin-pack a VMware estate from RVTools exports onto a target server spec and show how many servers each consolidation level needs -- cluster-for-cluster, moderate, aggressive -- with N+1 spares, licensing and tenant boundaries kept, memory right-sizing, servers avoided and a hardware-cost range, rendered as a two-page Spectro Cloud branded PDF. Use when someone asks things like can it do bin packing, how many servers or nodes do we need, how few hosts can we land this on, condense or consolidate the clusters, save the N+1 servers, cluster for cluster versus consolidated, size the target hardware from RVTools, turn the host savings into dollars, right-size the VMs for the migration. Pairs with a VMware migration readiness assessment; this skill owns the host-count and consolidation math, not OS readiness.

craig-ai-tooling Bundle

Create, inspect, tear down and re-create Palette clusters -- edge-native (agent mode, appliance mode, 2-node HA) plus imported and cloud clusters, via API or Terraform. Use when Craig says: create that cluster, deploy a 3 node palette cluster, spin up a cluster to demo, destroy and recreate the cluster, destroy all the Palette resources we created for this, delete the cluster and remove the import, import this EKS cluster, did you deploy the cluster yet, check on the cluster it seems like it is finishing up, add or replace a node. Ask for project, cluster name, profiles, and edge host UIDs before creating. Pair with spectrocloud-cluster-profiles for the profile layers and spectrocloud-troubleshooting when the cluster does not come up.

craig-ai-tooling Bundle

Build, test, and publish prospect-facing self-guided POC/POV guide sites for Spectro Cloud Palette. Full lifecycle - intake, scaffold an MkDocs Material site, author phased guides grounded in the spectrocloud-* technical skills, static QA (secret scan, link/anchor check, fence lint), optional live execution of annotated command blocks through a pluggable lab adapter, a critic loop, and gated publishing through a pluggable deploy provider (Cloudflare Pages with Access OTP gating is the default). Use when a prospect needs a step-by-step POC guide site, when asked to "packify" or productize POC docs, or to verify a guide's commands actually work before sending it to a customer.

cbenjamin23 Bundle

Analyze existing MOOS .alog files for post-run, log-backed questions such as mission reconstruction, variable history, helm-state context, or timestamped incident evidence.

cbenjamin23 Bundle

Build or modify user-owned IvP helm behaviors outside the core MOOS-IvP source tree: BHV_* C++ classes, IvPBehavior lifecycle methods, shared behavior libraries, IVP_BEHAVIOR_DIRS wiring, and behavior-specific configuration parameters.

cbenjamin23 Bundle

Build or repair the ordinary mission layer for one standalone MOOS-IvP mission: launchers, meta files, helm layout, communities, ports, nsplug targets, viewer setup, and README updates. For self-evaluating missions, use moos-ivp-eval-mission-builder as the primary skill.

ericpardee Skill

Use when User wants a cross-model review gate before shipping code or on a pull request - "before I push/merge/deploy", "have codex review this branch/these commits/the plan", "gate PR 123", "cross-model review", "second set of eyes on this branch", or /codex-gate. Runs Codex CLI at max reasoning against a diff scope, forces a fix-or-rebut disposition on every Critical/High/Medium finding, loops until clean (max 2 rounds), and writes a ledger. On someone else's PR it posts verified findings as a review instead of changing code.

brenordv Bundle

Senior PostgreSQL architect and DBA for PostgreSQL 16+. Use for schema and data-type design, indexing (B-tree, GIN, GiST, BRIN, HNSW/pgvector), query optimization with EXPLAIN ANALYZE, partitioning, replication, extensions, RLS/roles/security, connection pooling, VACUUM/autovacuum and configuration tuning, zero-downtime migrations, ORM integration, and cloud PostgreSQL (RDS/Aurora, Neon, Supabase).

brenordv Bundle

Polyglot Azure Cosmos DB development. NoSQL API, data modeling, production patterns. Supports Python, Java, TypeScript, and Rust SDKs. Use when building or reviewing Azure Cosmos DB (NoSQL API) solutions: data modeling, partition keys, RU/cost optimization, queries, consistency, or SDK code.

brenordv Bundle

Azure Event Hubs polyglot development. High-throughput event streaming with C#, Java, Python, TypeScript, and Rust SDKs. Use when building or reviewing Azure Event Hubs solutions: producers, consumers, checkpointing, partitions, consumer groups, throughput tuning, or SDK code.

brenordv Bundle

Senior NoSQL database architect for cross-paradigm NoSQL selection and modeling. Use to choose a NoSQL technology and design query-first data models for document stores (MongoDB, Firestore), key-value (Redis, DynamoDB), wide-column (Cassandra, ScyllaDB), graph (Neo4j, Neptune), and vector databases (Pinecone, Weaviate, Qdrant, pgvector); for partitioning/sharding, replication and consistency, indexing, migrations, and production operations (monitoring, backup, security); and to weigh NoSQL vs SQL trade-offs. For Azure Cosmos DB specifics, use the azure-cosmos skill.

brenordv Bundle

Senior Azure SQL Server architect and DBA for Azure SQL Database, Managed Instance, and SQL Server on Azure VM. Use for T-SQL query/stored-proc optimization, execution plans, indexing, schema design, security (TDE, Always Encrypted, RLS, dynamic data masking, Azure AD auth), high availability, geo-replication, failover groups, migrations (DMS, DACPAC, DMA, EF Core), DTU/vCore sizing, elastic pools, DMV/Query Store monitoring, partitioning, columnstore, temporal tables, JSON, and IaC (Bicep, ARM, Terraform). Not for MongoDB, Cosmos DB, DynamoDB, or non-SQL databases.

rhenter Skill

Use for tasks specifically involving AWS services, IAM, AWS architecture, deployment, operations, reliability, or cost.

rhenter Skill

Use for Kubernetes-specific manifests, deployments, pods, services, ingress, autoscaling, probes, troubleshooting, or cluster architecture.

emily-zall Bundle

Review Helm charts and Kubernetes manifests for syntax/schema correctness, conformance to the team's own service standard, and human readability/maintainability: naming, template complexity, values.yaml organization, label/annotation consistency, resource/probe clarity, and documentation. Use this whenever the user asks to review, lint, clean up, or improve a Helm chart, values.yaml, _helpers.tpl, or raw Kubernetes manifests, or asks things like "is this chart readable", "does this follow our conventions", "review my helm templates", or "is this valid", even if they don't say "review". Compares against the org's declared reference charts or standard doc when configured, otherwise against sibling charts in the repo, otherwise a generic Helm baseline, and can help a team choose or define a service template when none exists. Does NOT cover security posture, RBAC, secrets management, or deprecated API versions (use a security or GitOps audit skill), and does NOT do generic diff simplification. Prefer this skill o