Claude Skills for a DevOps / SRE
ModLens — Plug-in Vision for Text-Only Models
Gives text-only coding models sight: paste an image, get structured JSON evidence — OCR, layout, and semantics — via a vision bridge.
OpenChamber Performance Engineering Skill
Eliminate structural waste before micro-optimizing: a measurement-driven methodology for interaction, render, polling, cache, and high-volume data paths.
Locale UI Patterns — OpenChamber UI Localization Rules
Enforces that every user-facing OpenChamber string gets a real translation in every language dictionary immediately — no English placeholders, ever.
aicontainer Sandboxed Devcontainer
Runs Claude Code, Codex, and OpenCode in bypass/auto-approve mode inside a devcontainer sandbox, so a prompt-injected dependency can't read your .env, SSH keys, or gh token.
skill-optimizer: Eval Workbench for Agent Skills
Run deterministic evals of agent skills inside isolated Docker workspaces, benchmark across OpenRouter models, and debug with full traces.
OpenChamber UI/API Decoupling Skill
Enforces correct layering between SDK calls, RuntimeAPIs, and browser asset access when modifying OpenChamber's shared UI data layer — preventing hardcoding and cross-runtime state leaks.
Archify Architecture Diagram Skill
Turn system and process descriptions into interactive, exportable technical diagrams.
Clack CLI Patterns
Defines consistent interactive prompt, --quiet, and -- output contracts for OpenChamber terminal commands, so policy validation always precedes presentation in every run mode.
AgentTrace
Audit your AI coding-agent sessions locally — cost, tokens, latency, failures, and health — without any data leaving your machine.
Vibe Replay
Turns AI coding sessions into shareable, interactive animated replays, so reviewers see the reasoning behind changes — not just the final diff.
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.
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.
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.
career-ops – Job Search Command Center
Turn any AI coding CLI into a full job search hub: evaluate offers, generate CVs, scan portals, and track applications.
OpenChamber Change Discipline
Enforces "smallest complete change, narrowest sufficient validation" discipline when modifying the OpenChamber codebase, preventing local fixes from ballooning into speculative rewrites.
serve-sim — iOS Simulator Remote Control from the Terminal
Boot, install, stream, and control a Capacitor iOS app in the Apple Simulator from your terminal — no Xcode needed.
Codeagent Multi-Backend Orchestration Skill
Run AI code tasks across Codex, Claude, Gemini, and OpenCode backends through one codeagent-wrapper command, with parallel multi-agent orchestration built in.
Open Code Review
An agent skill that runs OpenCodeReview (ocr) in the background, triages findings by severity, and applies validated fixes — avoiding the foreground-timeout trap.
Persistent File Planning
Keep coding agents on track through context loss, /clear, and crashes with durable planning files and completion checks.
OpenChamber Sync State Invariants
A rulebook that enforces state ownership and failure semantics when agents change session sync, event reducers, polling, and caches — preventing destructive data loss and state corruption.
ORCH — AI Agent Orchestrator
One CLI to orchestrate them all: run teams of AI agents in parallel on your codebase from isolated git worktrees, hands-free.
do — Feature Development Orchestrator
Turns feature work into a five-phase workflow where parallel sub-agents handle code understanding, design, implementation and review — the orchestrator never writes code itself.
OmO Multi-Agent Orchestrator
Trigger with /omo and dispatch code analysis, bug investigation, and fixes to the minimal right mix of agents — no fixed pipeline.