Claude Skills for a DevOps / SRE — Page 19
Hugging Face Evaluation Manager Skill
Structure benchmark scores into Hugging Face model cards: extract them from READMEs, import from Artificial Analysis, or run your own evals with vLLM/lighteval.
Agents Observe
Real-time observability for Claude Code sessions and multi-agent runs — see subagents, tool calls, and token costs live.
ShellWard Security Deployment Guide
An interactively executed deployment checklist for OpenClaw/ShellWard covering network control, container isolation, credential hygiene, audit logging, and patching.
Rails Upgrade Analyzer
Analyzes your Rails app's upgrade path: detects the current version, fetches the latest release and official guides, and upgrades files via selective merging that preserves local customizations.
ESP32 Master Embedded Engineering Skill
Expert guidance for ESP32 chip selection, GPIO validation, and firmware generation, actively preventing bricking and protocol conflicts.
Move Code Quality Checker
Reviews Move packages against the official Move Book Code Quality Checklist and returns actionable, prioritized feedback.
PDF Skill
Teaches an agent to read, split, merge, and create PDF files with Python libraries, covering the most common PDF operations in document automation.
Cost Mode
A Claude Code behavioral mode that cuts costs 30-60% through concise responses, smart model routing, and session discipline — without sacrificing technical accuracy.
cmux Ghostty Submodule Workflow Skill
Standardizes Ghostty submodule commits, GhosttyKit.xcframework rebuilds, and parent pointer updates for cmux contributors, preventing dangling submodule pointers that break CI and checkouts.
unbox-ai — AI Agent Trace Analysis CLI
Analyze AI agent trace files from the CLI without reading megabytes of raw JSON, and find out why an agent run was slow or expensive.
babysit — PR Babysitting Skill
Drive an open pull request through conflicts, review bots, and CI until it is fully green with every thread handled, then hand it off labeled Ready for Human Review.
Create Verification Skill (for e2e)
Generates a project-local verify-<app> skill so any coding agent can launch your app, drive it like a user, keep evidence, and bug bash it.
Continuous Code Review
Dispatch focused reviews after tasks, major features, and before merges to catch problems early.
Writing Plans
Turn multi-step software requirements into executable, testable implementation plans.
Karpathy Coding Guidelines
Reduce coding-agent mistakes with explicit assumptions, simpler implementations, surgical edits, and verifiable goals.
Terraform & OpenTofu Infrastructure Skill
Helps AI coding agents test, structure, and deliver production-oriented Terraform and OpenTofu infrastructure code.
CC Safety Net Command Guard
Blocks destructive Git and filesystem commands before AI coding agents execute them.
Codex Bundled Skill Installer
Install curated or repository-hosted Codex skills without manually assembling their files and paths.
KYC Intake Parser
Turn onboarding packets into structured KYC data ready for screening.
VS Code Chat Performance Lab
Benchmark chat rendering and detect memory growth across VS Code builds.
Component Fixtures for Screenshot Testing
Create stable, theme-aware VS Code component fixtures for isolated screenshot testing.
VS Code Smoke Test Assistant
Run, filter, and debug VS Code end-to-end smoke tests.
VS Code Crash Dump Symbolicator
Turn native VS Code crash dumps into readable backtraces with method names.
Local VS Code Web Workbench
Validate VS Code workbench and Agents window changes in a local vscode.dev instance.