Cloud & DevOps Agent Skills for ChatGPT

Triage a Replit published-app incident, separate platform from application failures, contain safely, and preserve redacted evidence.

Set up a Replit project with .replit + replit.nix configuration, Secrets,

Load test and scale Replit deployments with Autoscale tuning, Reserved

Apply production-ready patterns for Replit Database, Object Storage,

Create or adopt a repository managed by Vivswan/repo-platform - create the repo, write .repo-platform.yml, grant the fleet token, run the…

Scans a GitHub repository to understand its tech stack, hosting, monitoring, integrations, and current production readiness.

Audit how far a downstream repo has drifted from the upstream repomatic reference.

Onboard new repositories into a managed ecosystem with seed.yaml contracts, CI/CD setup, documentation standards, and governance…

Resource Sharing Skill

Retell AI deploy integration \u2014 AI voice agent and phone call automation.\n\

Git revert workflow and Revertomatic PR template for reverting merged PRs

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Cloud cost optimization expertise covering instance right-sizing, reserved and savings plans, spot/preemptible instances, resource…

Scalability analysis expertise including horizontal vs vertical scaling, sharding strategies, read/write splitting, eventual consistency…

Use this skill to debug the EweserDB Docker Compose local development stack.

Run a committed Java revision as a bounded disposable remote build for compilation, tests, analyzers, profiling, benchmarks, or toolchain…

Run an SDLC delegated workflow via Archon.

Write an operational runbook for a service, incident type, or deployment procedure.

Deploy application to target platform. Use when user explicitly says 'deploy', 'push to production', 'ship it'. Handles Vercel, Netlify…

CI environment rules for GitHub Actions workflows.

Tend-specific guidance for this repo. Project build commands, test strategy, error conventions, etc. are in CLAUDE.md — don't duplicate…