Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Diagnose failed GitHub Actions runs using available job and step evidence. Identify the likely cause, propose a focused fix, and, when implementation is requested, update local code and run relevant checks while noting what needs remote verification.
Assesses a release using Sentry errors, recurring problems, affected users, and crash evidence. Compares equivalent periods with the previous stable release, identifies gaps in the evidence, and recommends rollout actions only when the findings support them.
Compare Sentry issues across selected time windows and releases to find new or recurring problems and changes in frequency or affected users. Prioritize findings using user impact and the strength of available evidence.
Investigate failing GitHub Actions checks on a pull request using the GitHub CLI. The skill gathers logs, summarizes failures, and proposes a fix plan, then implements changes only after explicit approval and reports changes and tests.
Inspect production errors recorded in Sentry through read-only API access. Summarize unresolved issues, recent crashes, occurrence counts, and event details to understand what happened and when each problem was last seen.
Monitor automated build and test runs in Nx Cloud, review suggested fixes, and apply or improve them when runs fail. Set monitoring limits and approval preferences, then follow subsequent runs to check the outcome.
Deploy applications and infrastructure to Cloudflare by choosing services that fit the project. Covers Workers, Pages, storage, and related platform options, with authentication checks and references for configuring and publishing the selected setup.
Plan AWS architectures, compare services, and review security using documentation verified through AWS MCP tools, which connect agents to external information. Get implementation examples and trade-offs tailored to the team's existing tools, experience, and constraints.
Deploy applications to Render by inspecting the code and preparing service settings. Generate a render.yaml configuration or create services through MCP, an agent tool connection, then check deployment status, logs, and basic service health.
Deploy an application or website to Vercel and receive its deployment link. Create a preview by default, request production explicitly, or use the included fallback script when the command line tool has no saved credentials.
Deploy web projects to Netlify with its command-line tool. The skill checks login status, links or creates a site, detects build settings, and publishes a preview or production version with deployment URLs and log links.
Use Quicknode to connect applications to blockchains, retrieve wallet and asset data, and monitor activity. Covers event notifications, live data streams, historical backfills, and SQL queries, with guidance for choosing suitable services and access methods.
Manage AltLLM Portal API keys for external agents and applications through the local CLI. Covers creation, model access limits, disabling, and revocation, while documenting production failures that currently restrict working operations to listing and creating keys.
Coordinate Cloud Claw workflows from launching an agent deployment to managing its virtual machine. It routes work to focused skills for setup, starting and stopping machines, viewing logs, renewing usage, and accessing dashboards through local altllm commands.
Launch a new OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw using the local CLI. Configure the agent type, deployment name, model, and Telegram settings according to the supported launch options and requirements.
Follow a release workflow for game changes, from screenshots and changelog entries through testing, commits, and live deployment. Verify the published version, measure transfer sizes, and report evidence while applying approval rules for large uploads.
Prepare and deploy Three.js or other web games from a tested commit, a specific saved code version. Check the live game's controls, assets, and display, then record release evidence and a rollback target.
Package a finished local web project for GitHub with a tailored README and a preview from the running project. Audit files before pushing, publish compatible projects through GitHub Pages, and verify the repository and live demo.
Estimate whether a model execution fits the available hardware and identify likely performance limits. Separate memory capacity, computation, data movement, and sequential waiting to produce a table of assumptions, ideal minimum times, unknowns, and measurement priorities.
Compare running models or tasks on a device, nearby edge infrastructure, or in the cloud. Break down interaction delays, data transfers, energy use, costs, and failure recovery to assess deployment choices for multimodal and real-time agents.
Compare batching, request scheduling, and memory management for a single model serving instance. Assess concurrent request capacity, response times, generation speed, and GPU time per result that meets the required quality and deadline.
Compare ways to distribute AI inference across multiple instances, including replicas and separate input-processing and generation stages. Estimate capacity, throughput, delays, state-transfer costs, and recovery overhead to support routing and scaling decisions.
Estimate cross-server traffic, network bottlenecks, and synchronization waits for AI training or inference. Map communication onto physical network paths and assess how topology or communication changes affect the time needed to complete the job.
Plan when an agent’s tool environments are created, kept available, released, and restored. Estimate peak concurrency, resource use during work and waiting, total task duration, and cost across model calls, tool execution, validation, and retries.