Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Inspect an agent workspace to inventory skills, prompts, plugins, tools, and configuration. Produce a prioritized gap and risk assessment based on observed evidence, with recommendations for the next workflow, while keeping files and settings unchanged.
Plan a software release by selecting changes, deriving its version, and defining rollout stages. Specify health checks, rollback thresholds, the exact recovery command, and its operator before handing execution to the host or CI.
Coordinate an active production incident by recording severity, assigning roles, and maintaining a timestamped timeline. Track temporary mitigations, verify recovery against an agreed health signal, and prepare customer notices with delivery status kept explicit.
Prepare a readiness record for an external service profile using identifiers, required capabilities, and metadata indicating whether credentials are present. Keep secret values unread and clarify permitted next steps without contacting the provider or validating credentials.
Sort incoming GitHub pull request, issue, review, and automated check events into review, triage, or repair handoffs. Recheck the repository's current state and prepare a next-action card that distinguishes suggested work from actions actually observed.
Assess release readiness before a production launch. Review evidence for testing, security, performance, monitoring, rollback, documentation, and support, then produce a readiness matrix, a release verdict, and a list of missing evidence.
Check the installed Hermes version and whether each MCP server allows simultaneous tool calls. Report current capabilities, explain possible conflicts, and prepare server-specific configuration changes that are applied only after explicit approval.
Plan an iOS or Android store release with signing checks, privacy declarations, beta testing, and staged rollout steps. Define halt thresholds and a replacement build before release, keeping planning separate from building, signing, uploading, or submission.
Plan self-hosted LLM serving by selecting an engine and quantization, which reduces model precision and memory needs. Prepare deployment runbooks and benchmarks that measure response latency and throughput against explicit service targets under defined loads.
Review saved infrastructure change plans to separate existing configuration drift from proposed changes, identify affected resources, and assess cost differences. Prepare staged application plans with health checks and rollback steps for each environment.
Prepare an operations board covering token use, cost, latency, run history, queues, and failures. Combine supplied metrics with Hermes records, distinguish measured values from estimates, and identify missing evidence and the next measurement needed.
Prepare a release checklist, deployment decision points, health indicators, rollback criteria, and a post-deployment status report. Keep planned actions separate from observed results so release owners can see what still needs verification.
Connect Hermes to a Buzz community, deliver local media attachments, or diagnose a self-hosted relay, the server that passes messages. Report verified setup and delivery stages separately, using observed receipts instead of assuming that configuration proves successful communication.
Diagnose local oh-my-hermes installation problems by checking command availability, managed skills, Hermes registration, and runtime state. Separate blocking issues from warnings and identify the next repair action without presenting a health check as a completed fix.
Deploy apps and websites to Vercel and get a URL to share. The workflow defaults to preview deployments, supports production when explicitly requested, and includes an alternative deployment script when CLI credentials are unavailable.
Inspect production errors in Sentry through read-only API queries. Summarize unresolved issues, occurrence counts, and recent events, then examine individual issue and event details to understand what has been happening.
Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.
Audit Node.js processes started by VCO, identify which are managed and still active, and report stale processes eligible for cleanup. Produce Markdown or JSON reports and simulate cleanup while keeping external and unknown processes outside the candidate set.
Deploy web projects to Netlify with its command-line tool. The skill checks authentication and project settings, links or creates a site, and publishes a preview or production version with deployment URLs and log links.
Investigate failed pull request checks in GitHub Actions using the GitHub CLI. The skill gathers logs, summarizes failures, proposes a repair plan, and applies changes after explicit approval, with a summary of changes and tests.
Publish files and static sites to IPFS, a distributed storage network, or create and deploy a web app with a frontend, backend APIs, and a database. The skill also guides email sending and updates through PinMe commands.
Turn browser automation into a cloud function on Browserbase, so it can run outside your machine. The skill guides project setup, function implementation, local testing, and deployment through the browse CLI.
Deploy or update the CDF Orchestration Airflow controller on Kubernetes. This skill guides prerequisite checks, image preparation, installation, connection setup, and post-install verification, producing a deployment report with readiness results and unresolved warnings.
Check whether a CDF Orchestration environment is ready for controller installation and workflow execution. Audit Linux tools, Kubernetes, GPUs, storage, and credentials, report missing evidence, and guide prerequisite setup before deployment.