Designs APIs with contract-first, consumer-driven approach including validation at boundaries, consistent error responses, and security focus. Generates types from OpenAPI/Swagger. Use when designing an API, creating endpoints, API architecture, REST design, building an API, defining contracts, new service, or when starting API work.
Initialize local dev environment from Azure DevOps by cloning all project repositories. Use when user asks to "initialize Azure project", "clone Azure repos", "setup Azure project locally", or wants to download all repositories from an Azure DevOps project.
Automates headless Chrome via MCP for web scraping, screenshots, testing, and browser interactions. Handles multi-instance server selection to avoid lock conflicts between parallel agents. Triggers when browsing a website, taking a screenshot, scraping a page, testing a web app, automating browser interactions, or when chrome-devtools MCP tools are needed.
Runs code metric tools (scc for LOC, lizard for cyclomatic complexity, jscpd for duplicate detection) to produce triage signals for audits, cleanup, and refactoring prioritization. Use when asked for code health metrics, complexity hotspots, duplicate code, LOC breakdown, technical debt signals, what to clean up first, pre-audit analysis, or to feed metric context into other skills like codebase-audit or simplify. Not a fix-it tool — it surfaces flags, not mandates.
Performs self-review during development by checking changed code for bugs, security issues, performance problems, and test gaps. Runs inline before committing or creating PRs. Use when reviewing own code, self-review, check my changes, review before commit, review my code, code review, quality check, or when triggered by incremental-implementation before a PR.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skills, plugins, and configuration for AI coding agents. Works with Claude Code, OpenCode, and more.
skills/ Shared agent skills (tool-agnostic markdown)
skills/_shared/ References shared across multiple skills
plugins/ Plugins (observability, skill-router)
claude/ Claude Code config (CLAUDE.md, settings, statusline)
opencode/ OpenCode config (commands, agents)
install.sh Symlinks config for one or both tools
git clone https://github.com/Saturate/agents.git
cd agents
./install.sh # Both Claude Code and OpenCode
./install.sh claude # Claude Code only
./install.sh opencode # OpenCode only
./install.sh --force # Backup existing files, no prompts
Skills are also available as a Claude Code plugin:
/plugin marketplace add Saturate/agents
The observability plugin (hook logging with optional Loki/Grafana push) can be installed separately:
/plugin install observability@Saturate-agents
/plugin install skill-router@Saturate-agents
Guide how you approach different types of work. They trigger action skills at the right moments.
| Skill | Description |
|---|---|
| idea-refine | Sharpen vague ideas into actionable briefs with options and tradeoffs |
| pre-planning | Gather context from git remote, codebase, memories before planning |
| incremental-implementation | Build in vertical slices, verify each, commit as you go |
| tdd | Test-driven development with RED-GREEN-REFACTOR and prove-it pattern |
| debugging | Systematic debugging - follow evidence, track attempts, fix root cause |
| code-simplification | Simplify code safely with Chesterton's Fence principle |
| frontend-ui-engineering | Component hierarchy, accessibility, performance, state handling |
| api-design | Contract-first API design with security focus and sane defaults |
| performance-profiling | Measure-identify-fix-measure cycle for frontend and backend |
| security-deep-dive | Red team analysis, threat modeling, attack surface mapping |
| launch-checklist | Full deployment readiness: infra, Docker, K8s, DNS, monitoring |
| documentation-adrs | Record architecture decisions to memory provider |
| commit | Conventional commits with scope detection, work item linking, secret scanning |
| code-review | Self-review during development before PRs |
Do specific things well. Often triggered by workflow skills.
| Skill | Description |
|---|---|
| azure-init | Initialize local dev environment from Azure DevOps |
| chrome-devtools | Browser automation via Chrome DevTools MCP |
| codebase-audit | Security, architecture, and quality audit |
| evaluating-dependencies | Evaluate packages before installing |
| hunting-bugs | Find common bug patterns and anti-patterns |
| make-pr | Create pull requests (GitHub and Azure DevOps) |
| managing-ports | Detect and resolve dev server port conflicts |
| node-package-management | npm, pnpm, yarn, and bun package management |
| nuget-package-management | .NET NuGet package management with CPM |
| pr-review | Comprehensive PR code review |
| validate-skill | Validate skill files against best practices |
npx claudepluginhub saturate/agents --plugin skill-routerComprehensive Claude Code observability — tracks sessions, costs, tool usage, prompts, subagents, and more via daily-rotated JSONL with optional Loki push
Unified capability management center for Skills, Agents, and Commands.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Skill and agent authoring tools: generate, audit, and improve Claude Code skills, commands, and agents
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.