Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Run and manage an agent in Anthropic's cloud for long or asynchronous tasks. Create a session with packages and tools, send work, inspect status and activity, continue with saved files and conversation, then terminate the session.
Review HTTP Content-Type headers, which identify file formats, across web pages and static assets. Find mismatches that can block stylesheets or scripts, and identify server configuration changes needed to serve resources correctly.
Investigate slow page loads and check whether resources use HTTP/2 or HTTP/3. Measure the actual bottleneck, then recommend server or CDN changes where appropriate, explaining how shared connections and compressed headers affect loading.
Set up or review production error monitoring to capture unhandled errors, failed requests, and performance signals. Check event context, release labels, and alert routing so teams receive useful information when problems occur.
Audit browser caching to reduce repeated downloads when people revisit a site. Check cache headers for static files and HTML pages, then suggest suitable storage durations and validation settings based on measured loading problems.
Audit slow page loads by measuring how static files, such as images and scripts, are delivered. Check CDN usage, a network of distributed servers, and identify caching or delivery settings that need improvement.
Check whether HTML, JavaScript, and CSS are delivered with Gzip or Brotli compression. Use measured loading problems and response headers to guide server or CDN changes that reduce the amount of data downloaded.
Manage OpenSpec releases by auditing merged changes and release records, checking release pull requests, and verifying publication. Support stable and beta releases, resume from the current GitHub state, and finish with polished release notes.
Review a release proposal by reading its deployment diff and quoting changed replica settings, which describe running instance counts. The review surfaces the specific configuration changes for inspection.
Review Orchard deployment manifests, the files describing deployment settings, and keep source paths in the result. The workflow stops when evidence is missing, tying review findings to the available source material.
Review deployment evidence and recovery conditions when assessing a release. The skill directs the agent to consult the accompanying restore reference and include a timestamp in its decision, providing a narrowly defined release review procedure.
Publish an approved Orchard release while retaining source paths in the result. The skill requires work to stop when supporting evidence is missing, making evidence availability a condition for proceeding.
Prepare and publish standalone @cline/ui releases to npm, the package registry. Covers version updates, quality checks, production and preview channels, release verification, and the initial setup that lets GitHub Actions publish the package.
Prepare and publish releases of the Cline VS Code extension. Follow separate paths for stable, nightly, and emergency legacy releases, covering version selection, release notes, approval steps, packaged builds, and checks after publication.
Prepare Cline desktop releases for stable, beta, or nightly testing. Coordinate release notes, matching version files, tags, and a GitHub Actions workflow that builds signed installers and manages automatic update feeds for release channels.
Prepare Cline CLI releases for npm, the package registry, by reviewing SDK changes, drafting release notes, updating versions and changelogs, and creating release tags. Guides checks and publication through GitHub Actions or an authenticated local machine.
Publishes oh-my-opencode through GitHub Actions, then checks package versions and release artifacts. Covers related packages, user-facing release summaries, and Discord announcements, reporting failures without starting code repairs during the release process.
Set up an ElevenLabs API key for MCP tools that connect agents to ElevenLabs. Checks existing credentials, guides key creation when needed, validates access, and saves a working key in a .env file.
Set up Muse’s built-in Tailscale connector, join a private Tailscale or Headscale network, and check connection status. Use a TCP tunnel proxy to reach private machines and consult documentation about routing capabilities and supported limits.
Diagnose problems in Muse Code itself using the installed executable, settings, crash reports, and session evidence. The skill narrows down the likely failing component, summarizes evidence with sensitive information removed, and recommends a safe next action.
Inspect Vercel websites and apps, check deployment status, and read build and runtime logs to investigate production errors or failed releases. The skill also supports project management and deployment through Vercel’s official MCP server.
Audit a Claude Code setup for installation problems, broken settings, unused extensions, and duplicated instructions. It reviews local usage evidence, recommends cleanup, and applies approved fixes, with separate confirmation for permission changes.
Update the published Remotion plugin for Codex and ChatGPT to a released version. Prepare and validate an upload ZIP, preserve existing listing details, and follow the dashboard workflow through review and publication verification.
Monitor a specific Vercel deployment in Codex and report when it becomes ready or fails. The skill identifies the exact deployment, checks its recorded state, and includes dashboard and preview links in the notification.