Saturate
UserSkills, plugins, and config for AI coding agents (Claude Code, OpenCode, and more)
Categories
Indexed Skills (28)
azure-init
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.
using-chrome-devtools
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.
code-metrics
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.
codebase-audit
Performs comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.
evaluating-dependencies
Evaluates packages before installation across npm, pnpm, yarn, bun, cargo, pip, uv, go, and nuget. Checks footprint, maintenance status, alternatives, license, and security. Use when adding dependencies, choosing between libraries, optimizing bundle size, or running npm install, pnpm add, yarn add, bun add, cargo add, pip install, uv add, go get, or dotnet add package.
hunting-bugs
Audits codebases for common bug patterns and anti-patterns including timezone issues, null safety, type coercion, async handling, and performance problems. Searches for known problematic patterns and provides actionable fixes. Use when asked to find bugs, audit for issues, check for common problems, or hunt for bugs in codebase.
make-pr
Creates pull requests on GitHub or Azure DevOps by analyzing commits and generating descriptions. Detects platform from git remote and uses gh CLI or az CLI. Use when asked to create PR, open PR, make pull request, submit PR, create pull request, new PR, raise PR, push PR, open pull request, submit changes, PR workflow, or when user mentions PR creation. Generates casual, context-aware PR descriptions that explain WHY not WHAT.
managing-ports
Detects framework, finds available ports, and starts dev servers with correct port flags. Resolves port conflicts when multiple projects compete for the same default port (common with git worktrees). Scans running processes, identifies frameworks from config files, and uses the right CLI flag per framework. Use when starting dev server, port conflict, port in use, address already in use, EADDRINUSE, npm run dev, pnpm dev, yarn dev, listen EADDRINUSE, port 3000 taken, or managing multiple local servers.
safe-delete
Safely handles recursive file/directory deletion by classifying targets, backing up what can't be recovered, and verifying nothing is lost before committing the delete. Use when running rm -rf, rm -r, deleting directories, removing files recursively, cleaning up paths, delete folder, remove directory, or clean up.
validate-skill
Validates Claude Code skills against official best practices from Anthropic documentation. Fetches latest documentation dynamically to ensure current standards. Checks frontmatter, structure, line count, descriptions, references, workflows, and provides actionable recommendations. Use when asked to validate skill, check skill quality, review skill, or audit skill compliance.
stats
Query Claude Code usage stats from observability logs. Shows costs, session summaries, tool usage, token consumption, and more. Use when asked about costs, usage, stats, spending, session history, most-used tools, or token usage. Invoked with /stats or when asking questions like "how much have I spent today?"
api-design
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.
code-review
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.
code-simplification
Simplifies code safely using Chesterton's Fence principle - understanding why code exists before changing it. Makes one change at a time with verification after each. Use when simplifying code, reducing complexity, refactoring, cleaning up, making code simpler, untangling, or when code feels unnecessarily complex.
commit
Commits staged changes using Conventional Commits with auto-detected scope, work item linking, and secret scanning. Use when committing, making a commit, git commit, save changes, commit changes, commit my work, or when triggered by incremental-implementation.
debugging
Systematic debugging workflow that follows evidence instead of guessing. Checks APM and monitoring first, gathers context through available tools, localizes to layer, and tracks what has been tried to prevent loops. Use when debugging, fixing a bug, something is broken, error investigation, troubleshooting, diagnosing issues, finding root cause, or when stuck on a problem.
documentation-adrs
Records architecture decisions to memory provider when significant technical choices are made. Lightweight format capturing what was decided, why, alternatives considered, and tradeoffs. Use when recording a decision, documenting architecture, ADR, architecture decision record, why did we choose, technical decision, or when a significant choice is made about dependencies, patterns, or infrastructure.
frontend-ui-engineering
Guides frontend UI development with component hierarchy, separation of concerns, accessibility as requirement, and performance awareness. Framework-agnostic, detects stack from project. Triggers chrome-devtools for verification. Use when building UI, frontend development, creating components, UI engineering, component architecture, building pages, or when working on frontend code.
idea-refine
Sharpens vague ideas into actionable briefs by generating 3-5 options with tradeoffs, checking technical feasibility, and defining scope with a "Not Doing" list. Use when brainstorming, refining an idea, scoping a feature, exploring options, defining requirements, what should we build, unclear requirements, or when starting something new without a clear spec.
incremental-implementation
Builds features in vertical slices where each slice is implemented, tested, verified, and committed before moving to the next. Triggers code-review before creating PRs and make-pr when complete. Use when implementing a feature, building incrementally, vertical slices, step by step implementation, building a feature, or when starting to code a planned feature.
launch-checklist
Validates full deployment readiness beyond code, checking infrastructure, Docker configuration, Kubernetes manifests, environment config, monitoring, security headers, and pipeline status. Use when launching, deploying to production, release readiness, go-live, deployment check, pre-launch, shipping to prod, or when preparing for production deployment.
no-ai-slop
Guides prose writing to avoid AI-generated slop patterns. Applies structural variety, voice authenticity, and a multi-step self-review with worked examples.
performance-profiling
Guides active performance investigation with measure-identify-fix-measure cycle for both frontend and backend. Triggers chrome-devtools for frontend profiling. Use when profiling performance, investigating slow code, optimizing speed, performance issues, slow page, slow API, latency problems, or when something feels sluggish.
pre-planning
Gathers context from multiple sources before entering plan mode, including git remote work items, codebase structure, reference projects, and memories. Detects platform from git remote. Use when starting planning, before plan mode, gather context, prep for planning, kickoff, starting a new feature, beginning work on a task, or before implementing something non-trivial.
push
Runs project quality gates before pushing. Auto-detects lint, format, typecheck, test, and build commands from project config. Fixes auto-fixable issues and amends the last commit. Use when pushing, git push, pushing changes, push to remote, or before creating a PR.
security-deep-dive
Performs red team security analysis with threat modeling, attack surface mapping, auth flow analysis, and dependency chain audits. Goes beyond checklists to think like an attacker. Use when doing security audit, penetration testing, threat modeling, security review, attack surface analysis, red team assessment, or when codebase-audit flags serious security concerns.
skill-router
Meta-skill that maps tasks to the right skill. Consult at the start of any non-trivial task to pick the right workflow skill, and before specific actions (installing deps, committing, opening PRs, reviewing) to pick the right action skill. Loaded automatically at session start by the skill-router plugin.
tdd
Guides test-driven development with RED-GREEN-REFACTOR cycle, prove-it pattern for bugs, and consumer-driven interface testing. Prefers real implementations over mocks. Use when writing tests first, TDD, test driven development, red green refactor, prove a bug, writing tests, test first, or when asked to add tests before implementation.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.