DevOps & Infra Agent Skills

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.

Deploy web apps with backend APIs, database, and file storage. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.

Bash Pipeline Analysis

Box API integration with managed OAuth. Manage files, folders, collaborations, and cloud storage. Use this skill when users want to upload, download, share, or organize files and folders in Box. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.

Game art principles. Visual style selection, asset pipeline, animation workflow.

Run end-to-end deploy pipelines across Stripe, Supabase, and Vercel using the Composio CLI. Promote Stripe products, push Supabase migrations, ship Vercel deployments, and verify with post-deploy checks — all from one script.

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.

Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

"Multi-cloud" is a loose word that hides four distinct architectures with

A VPC is a private IP space you own inside a region.

Use this skill for glTF/GLB assets, compression, optimization, transforms, texture sizing, browser delivery. Trigger when the task involves 3d web work related to Gltf Asset Pipeline, production implementation, audits, debugging, strategy, or validation.

Agent profile for handle CI/CD, environments, build pipelines, deployment topology, secrets, and operational readiness. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Route one Paperclip child stage of the PLE new-content routine, producing hash-verifiable evidence and a fail-closed handoff.

Layer 1c of the keyword research pipeline — SKIPPED on the current Semrush MCP (it exposes no AI-visibility / AI-toolkit reports, so there is no multi-engine citation-gap source). Retained as a logged no-op pass-through; never fabricate aio_gap rows. Revisit only if Semrush ships AI-toolkit reports on MCP.

Layer 1a of the keyword research pipeline. Generates seed keywords (broad niche terms) and modifiers (best, how-to, vs, calculator, etc.) from brand-config so the keyword multiplier has a real foundation to expand from. Replaces the "AI gives you generic keywords" problem with the structured 10-second hero prompt.

Deterministic workflow to download MATLAB Package Manager (mpm) and install MathWorks products from the OS command line with consistent, repeatable behavior. Use when installing MATLAB, Simulink, toolboxes, or support packages via command line, or setting up scripted installations for CI/CD, containers, or fleet provisioning.

Generate, verify, refine, and accelerate C/C++ or CUDA code from MATLAB with MATLAB Coder, Embedded Coder, GPU Coder, or MATLAB Test. Also covers writing codegen-ready MATLAB code: language constraints, coder.* directives, and optimization patterns. Triggers on: codegen, MEX, deploy MATLAB as C/C++, GPU Coder, coder.screener, coder.config, coder.gpuConfig, coder.typeof, coder.runTest, matlabtest.coder.TestCase, SIL, embedded config, no dynamic memory, EnableMexProfiling, coder.timeit, coder.perfCompare, %#codegen, writing codegen-ready MATLAB, code generation readiness, coder.varsize, coder.unroll, coder.noImplicitExpansionInFunction, coder.ceval, coder.inline, coder.extrinsic, coder.const, coder.classSignature, class codegen limitations, temporal types codegen, DMA-off, stack-only, host-target InstructionSetExtensions, SIMDAcceleration, OptimizeReductions, host SIMD tuning, host OpenMP, codegen performance.

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or imported models rebuilt as dlnetwork for lean hardware, (2) direct C/C++ code generation from PyTorch and LiteRT models. Both patterns support all targets (Cortex-M/A/R, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, loadLiteRTModel, importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromTensorFlow, importNetworkFromKeras, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.

Set up CI/CD pipelines for Flutter apps. Use when configuring automated testing, build, or deployment workflows with GitHub Actions or Fastlane.

Stop a running Docker container gracefully

Wire ETL, ingestion, cron, edge-function, and queue jobs correctly. Use for "build a pipeline", "sync X into Y", "nightly aggregation", "cron double-counts", "dedupe", "backfill", "the numbers are wrong after a retry". Bakes in idempotency, atomic writes, data contracts, dead-letter, and observability.

Apply-now consolidation of accreted CI gates, ratchets, and hooks into one aggregator required check. Use after audit-gate-logic, or when "clean up our CI checks", "we have three lint jobs", "make one quality gate". Audit-only → audit-gate-logic. Pipeline cost → audit-cicd.

Predicts the highest-impact next action for your project by running a 5-agent meta-DAG pipeline. Gathers project signals automatically (git, recent files, port-daddy, CLAUDE.md), then runs sensemaker → decomposer → skill-selector + premortem → synthesizer. When execution is approved, convert each predicted node into a skillful node prompt using skillful-node-prompt + skillful-subagent-creator, prefer live WinDAGs visualization backed by POST /api/execute and /ws/execution/:id, and fall back to ASCII only when live visualization is unavailable. Activate on: "what should I do", "what's next", "next move", "/next-move", "where should I focus", "what's the highest impact thing right now". NOT for: creating skills, debugging one specific bug, or promising topology-specific runtime behavior the current server cannot execute.

Use when running analytical SQL over Parquet/CSV/JSON without a warehouse, replacing pandas for data wrangling, joining S3 data in-place, building local data marts, or embedding OLAP into an app. Triggers: read_parquet/read_csv setup, partitioned dataset queries, hive partitioning, glob patterns for S3, COPY TO export, attach Postgres/MySQL, UDFs in Python/R, MotherDuck cloud sync, columnar performance vs row stores. NOT for OLTP workloads (concurrent writes), distributed analytics at petabyte scale (use Spark/Trino), or vector search (use pgvector/Lance).

ML Pipeline Specialist IA — Expert en pipelines ML (feature stores, data versioning, experiment tracking, model registry)

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I

Trigger: deployment pipeline, CI CD, Docker builds, DB migrations, expand contract database, Netlify. Scope: Application deployment, multi-stage builds, zero-downtime releases. Boundary: Excludes local editor settings.

Post-deploy canary monitoring. (gstack)

Land and deploy workflow. (gstack)