DevOps & Infra

aws-samples Skill

Diagnose and fix common ABCA issues: deployment failures, preflight errors, authentication problems, agent failures, and build issues. Use when the user says "troubleshoot", "debug", "not working", "error", "failed", "help me fix", "preflight_failed", "task failed", "deploy failed", "auth error", "401", "422", "503", or describes something not working as expected.

lucascruzfl Bundle

Operar uma instalação DeskcommCRM pelo MCP com descoberta dinâmica, validação antes de mutações e continuidade segura para ações humanas. Use quando alguém quiser consultar, configurar ou operar IA, CRM, atendimento, agenda, follow-up, automações, routing, knowledge, templates, produtos, webhooks, integrações, canais, equipe ou importações/exportações pelo MCP Deskcomm. Não use para deploy, infraestrutura, recuperação de secrets ou elevação de privilégios.

jimuelle07 Bundle

Routes a coding task to the best AI agent installed on this machine. Probes which agent CLIs are installed AND logged in - Claude Code, Codex, Cursor Agent, Gemini CLI, Aider, OpenCode, GitHub Copilot, Amp, Droid, Crush, Goose, Qwen Code, Ollama and local models - reads CPU/RAM/VRAM, then uses TypeSafe Jev, its required typed decision layer, to choose one, dispatch the task and judge whether the worker finished. Use it for: which model or agent should handle this; what agents or models do I have; is Claude or Codex better for this refactor; delegate, hand off, route, dispatch or orchestrate work across agents, sub-agents or a multi-agent build; can this run on a local model; an agent CLI that is installed but failing to call its model; and before any substantial build where picking the wrong tool is expensive, since an agent cannot see the sibling agents beside it. Not Helm the Kubernetes package manager: never for charts, `helm install`, releases or clusters.

undertone0809 Bundle

Conducts enterprise-grade research with multi-source synthesis, citation tracking, and verification. Produces citation-backed reports through a structured pipeline with source credibility scoring, and grounds abstract findings in concrete examples, cases, counterexamples, or mini-scenarios when helpful. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

bflabsai Bundle

Full Meta WhatsApp Cloud API (WABA) senior integration expert — direct Graph API v26.0 (no BSP, no MCP). Covers sending all message types (text, media, interactive buttons/lists, catalog, flows, templates, reactions, location, contacts), webhook setup with HMAC-SHA256 verification and anti-XSS challenge handling, System User Tokens, 24h service windows, per-message pricing model, Flow JSON 7.3, Coexistence, automated diagnostics with --fix, and resolving the 3 silent failure modes (WABA unsubscribed, missing webhook fields, token asset assignment, opaque error codes). Includes production Node.js/TypeScript and Python boilerplates. Triggers on any mention of WhatsApp Cloud API, WABA, Meta Graph API WhatsApp, WhatsApp webhooks, templates, messaging, or troubleshooting silent WhatsApp delivery failures.

caipe-io Skill

Analyze AWS costs by service, account, and time period. Identifies top spenders, cost anomalies, and optimization opportunities. Use when reviewing cloud spend, preparing cost reports, or investigating unexpected charges.

caipe-io Skill

Check Kubernetes cluster health including pod status, node conditions, resource utilization, and pending alerts across EKS clusters. Use when monitoring infrastructure health, investigating capacity issues, or performing cluster audits.

caipe-io Skill

Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.

caipe-io Bundle

Run and document CAIPE UI/BFF performance benchmarks with Locust against the Docker Compose UI, including audit-service, OpenFGA, MongoDB, Keycloak, RAG, and dynamic-agents health context. Use when asked to run UI performance, BFF latency, Locust load tests, benchmark user-count sweeps, or update UI benchmark result docs.

caipe-io Skill

List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.

caipe-io Skill

Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.

caipe-io Bundle

Analyze AWS costs by service, account, and time period. Identifies top spenders, cost anomalies, and optimization opportunities. Use when reviewing cloud spend, preparing cost reports, or investigating unexpected charges.

caipe-io Bundle

Check Kubernetes cluster health including pod status, node conditions, resource utilization, and pending alerts across EKS clusters. Use when monitoring infrastructure health, investigating capacity issues, or performing cluster audits.

caipe-io Bundle

Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.

caipe-io Bundle

List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.

andrewdryga Skill

Pre-deploy checklist and release sanity for the GCP portal control plane - migrations, secrets, image build, HCP Terraform plan, and health. Use before deploying or when changing the Dockerfile, release config, runtime config, or infra delivery path. Does not apply infrastructure.

ngrok Bundle

Reference for ngrok's traffic model - what an endpoint is and what happens to traffic at the edge. Covers endpoint types (agent, cloud, internal), bindings and protocols (HTTP, TLS, TCP), and Traffic Policy - the YAML rule language of phases, CEL expressions, and actions, with a generated catalog of all 26 actions. Other ngrok skills point here to decide what to build, then to ngrok-surfaces to apply it. Not a standalone task - load when another skill references it.

ngrok Bundle

How to apply an ngrok endpoint and Traffic Policy on whichever surface the user is actually working in - the agent CLI and ngrok.yml, the ngrok SDKs (Go, JavaScript, Python, Rust), the REST API at api.ngrok.com, the Terraform provider, and the Kubernetes Operator. Routes from signals in the user's project to the right surface, then to that surface's reference file. Other ngrok skills point here once they know what to build. Not a standalone task - load when another skill references it.

ngrok Bundle

Expose an in-development MCP (Model Context Protocol) server for remote testing against AI model providers like Claude and OpenAI, with per-provider authentication and traffic inspection. Puts a cloud endpoint in front of your local MCP server, authenticates each provider with its own bearer token via Vaults, and forwards to your server kept off the public internet. Use when the user is building or testing an MCP server and needs a remote AI client to reach it. Use when the user says "test my MCP server", "expose my MCP server to Claude", "connect my MCP server to OpenAI", or "front door for my MCP server".

ngrok Bundle

Give every sandbox, container, device, or tenant its own isolated ngrok endpoint, provisioned programmatically at runtime from a controlplane. Covers the per-workload resource set - service user, reserved address or domain, ACL-scoped authtoken, cloud endpoint forwarding to a private internal endpoint - plus the agent config that runs inside the workload, and teardown. Use when the user is building a platform that spins up isolated environments.

robertoatila Skill

Localization Pipeline

robertoatila Skill

Submits and monitors automated protein assays via Adaptyv Bio Foundry API.

robertoatila Skill

Trains massive LLMs using Megatron tensor, pipeline, and sequence parallelism strategies.

macotasu Bundle

自律ループのフロントドア（HOTL = Human on the Loop）。リポジトリ内の仕様 ./goals/<slug>.md を起点に、拾い上げ→実装→司法検証→PR を無人で回す。 /conductor:dev（単発・human-in-loop）と並立する自律ループの入口。手動起動: /loop-engine:loop-engine <slug> または /loop-engine:loop-engine <issue番号>（GitHub issue 経由。label + Spec: コメントから spec を解決）。 進行は本 skill 同梱の reference/autonomy-gates.md のゲート G1〜G6 を正として行う。手動 /loop-engine:loop-engine <slug> に加え、autonomous-entry（Claude Code の cloud routine で定期発火し、loop-ready label が付いた issue を走査する・手順は reference/routine.md）がある。自律は spec の autonomy: L1|L2（省略=L1=報告のみ）で spec ごとに制御。L2 でも G6(自動マージ) 手前=PR作成で停止する（自動マージ runtime は Phase 3.1 で未出荷）。

robertoatila Skill

Multi-cloud compute orchestration and automatic cost optimization for distributed ML workloads.

clay-run Bundle

Clay Audiences — the workspace's own people, companies, and deals (contacts, leads, accounts, customers). Use for any request about their records when no surface is named, including counts, fill rates, lookups ("how many people have a phone?"), saved segments, and field definitions. Also deal and pipeline questions like largest opportunities, biggest pipeline items, recent wins, closed-won, deal stage, and ACV.

legalquants Bundle

Use when the user uploads or pastes a Software-as-a-Service Master Services Agreement (MSA), Master Subscription Agreement, SaaS Agreement, or Cloud Services Agreement and asks for review, redline, risk assessment, or recommendation on whether to sign. Conducts a structured review of MSA framework terms (liability, indemnification, IP, data protection, warranties, term and termination, payment, and others), calibrated to the user's perspective (vendor or customer), with severity-rated findings, redline language for material gaps, and clause-level citations. Optionally surfaces conflicts between the MSA and a provided Order Form or SOW.

legalquants Bundle

Use when extracting the negotiated positions from a single prior contract as input to the Easy Playbook auto-generation pipeline. Reads a contract's text, identifies the clauses that take a substantive position on a contract issue (definition of confidential information, limitation of liability, indemnification, payment terms, etc.), and emits a structured list of {issue, clause_text, source_offsets} for downstream clustering. Output is intermediate; the in-house attorney evaluates the final assembled playbook, not this stage.

iancchambers Bundle

Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions (like city, date), check metrics and dimensions compatibility, or verify API enablement. Don't use for Google Analytics Admin API operations (e.g., creating properties, managing users) or for front-end tracking installation.

iancchambers Bundle

Manages Google Analytics account and property settings, enables the Analytics Admin API via the Cloud CLI, lists accounts and properties, and manages data streams, custom dimensions, conversion events, and integrations. Use when you need to programmatically configure Google Analytics accounts, provision properties, manage data retention, configure Measurement Protocol secrets, or manage Firebase and Google Ads links.

robertoatila Skill

Multi-cloud compute orchestration and automatic cost optimization for distributed ML workloads.

ai-automation-tools Bundle

Design, create and track a Claude Code cloud routine — a scheduled agent run on Anthropic's infrastructure that opens a pull request — and connect it to Cronsole's CLAUDE_CODE source. Use whenever the user wants a recurring cloud agent, a scheduled Claude routine, a weekly drift check, or a docs/catalog refresh that runs by itself; whenever they want to list, pause, edit, retire or debug an existing routine; whenever a routine "ran" but opened nothing, or Cronsole shows no Claude routines, cannot pause one, or reports them all UNKNOWN. Also use to decide whether a scheduled agent job belongs in the cloud or on a local machine before building it.

ai-automation-tools Bundle

Add, change or debug an Edge Spectrum API endpoint across its two entry points — the local Express server (site/server.ts) and the Vercel serverless functions (site/api/*) — which must both be thin adapters over shared logic in site/src/server/. Covers Zod validation at the trust boundary, the strategySchema / strategyBounds split that keeps Zod out of the client bundle, and the demo-mode + passcode gate that makes the Gemini advisor fail closed. Use for "add an API route", "the endpoint works locally but 404s/500s on Vercel", "validate this request body", "the advisor returns 503 / 403 / 401", "ADVISOR_PASSCODE", "EDGE_SPECTRUM_MODE", "demo mode", "check:deployment failed", and any work under site/api/, site/server.ts or site/src/server/.

orderful Bundle

Migrate a NetSuite SuiteAnalytics Dataset from one NS account to another via SDF — the typical sandbox-to-prod move for an Orderful "Packaging Data Source" (carton dataset, pallet dataset, or any Analytics Dataset the SuiteApp consumes via N/dataset at runtime). Walks through SDF project bootstrap, interactive auth setup via an expect-driven flow that only needs the user for the browser OAuth, object:import from source, the workbook-required SDF validation gotcha, customer-ID filter swap, the "file upload error" misleading-failure trap, and the post-deploy REST step to register the dataset on customrecord_orderful_pkg_data_src. Use when the user says "migrate dataset from sandbox to prod", "move the carton dataset to prod", "deploy the SuiteAnalytics dataset via SDF", "/migrate-dataset", or after authoring a dataset in sandbox per the alternative-packing-source flow and needing to promote it.

davidgfolch Skill

How to view backend logs using docker-compose.

orderful Bundle

Apply a controlled JSONata change across every customer-enabled-transaction-type record of a given doc type in a customer's NetSuite. Walks through audit (with per-record backups), plan (textual diff preview), dry-run, deploy (one record at a time with read-back verification), and rollback. Use when the user says "I need to add field X to every 850 customer", "roll out an externalid mapping to all customers", "update all our 856 JSONata to do Y", "audit our existing JSONata", or any other "apply the same JSONata change to many enabled transactions" scenario. Does NOT change the SuiteApp source. Does NOT touch records the user did not approve. Refuses to deploy without an explicit dry-run + plan approval.