By 22Teikk
Production-grade engineering skills for AI coding agents by 22Teikk — covering the full software development lifecycle from spec to ship.
Write and verify Maestro E2E flows for critical user journeys (opt-in)
Set up Android foundation — Hilt, Gradle, Version Catalog, CI hooks
Run an Android performance audit via the android-performance-auditor persona
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
Set up or modify CI/CD pipelines and quality gates
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices for Android applications. Use for security-focused code review, threat analysis, or hardening recommendations.
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
Android performance auditor focused on App Startup, Frame Rendering (Jank), CPU/Memory profiling, and Jetpack Macrobenchmark analysis.
Handles data operations and concurrency in Java. Use when writing RxJava streams, CompletableFutures, Retrofit network requests in Java, or Room database queries in Java.
Handles data operations and concurrency in Kotlin. Use when writing Kotlin Coroutines, flows (StateFlow, SharedFlow), Retrofit network requests, Kotlin Serialization converters, or Room database operations.
Configures Android dependency injection and build environments. Use when setting up Hilt injection, editing Gradle Kotlin DSL (KTS) build scripts, adding libraries to the Version Catalog, or defining GitHub Actions/Firebase App Distribution workflows.
Writes and runs Maestro YAML flows for Android end-to-end user journeys. Use when a multi-screen app needs journey smoke tests, when SPEC.md declares E2E Maestro, or when invoked via /teikk-e2e. Do NOT use for unit tests, Compose component tests, or Macrobenchmarks.
Implements unit testing and performance benchmarking in Java. Use when writing Java JUnit tests, Mockito unit/integration tests, Espresso UI tests, or Macrobenchmark configurations.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Engineering workflows for AI coding agents — spec-first, test-driven, Android-focused.
Personal fork: 22Teikk/22Teikk-Agent-Skills-Hub
DEFINE ──▶ PLAN ──▶ BUILD ──▶ VERIFY ──▶ REVIEW ──▶ SHIP
npm install github:22Teikk/22Teikk-Agent-Skills-Hub#v1.4.0 --save-dev
npx teikk-agents-skills init cursor
Auto-install on npm install — add to your Android project's package.json:
{
"devDependencies": {
"teikk-agents-skills": "github:22Teikk/22Teikk-Agent-Skills-Hub#v1.4.0"
},
"teikk-agents-skills": { "target": "cursor" }
}
Other targets: claude | antigravity | gemini | opencode | all
Setup guides: docs/
/teikk-interview ← ask unclear? skip if you know what you want
/teikk-idea ← exploring options? skip if direction is clear
/teikk-spec ← lock WHAT + stack + arch + observability + E2E: none|Maestro
/teikk-planning ← break into tasks (Phase 0: Hilt + Timber first)
/teikk-build ← one task at a time
/teikk-build auto ← approve plan once, agent runs all tasks
/teikk-test ← TDD unit + Compose component (not E2E)
/teikk-e2e ← opt-in Maestro journeys (when SPEC says so)
/teikk-review ← before merge
/teikk-ship ← go/no-go + optional Maestro if .maestro/ exists
| Command | When |
|---|---|
/teikk-android-setup | New project — Hilt, Version Catalog, Gradle |
/teikk-observability | Timber, Crashlytics, analytics, perf traces |
/teikk-ci | GitHub Actions / quality gates |
/teikk-docs | ADRs, README updates |
/teikk-code-simplify | Code works but too complex |
/teikk-androidperf | Startup / jank audit |
E2E: none (default) or E2E: Maestro — flows: [...]/teikk-e2e — agent reads UI source → writes .maestro/flows/*.yaml → runs maestro test/teikk-ship — runs Maestro only if .maestro/flows/ exists and SPEC ≠ E2E: none/teikk-build or /teikk-test (too slow for TDD loop)Skill: skills/android-e2e-maestro/SKILL.md
| Phase | Command |
|---|---|
| Define | /teikk-interview, /teikk-idea, /teikk-spec |
| Plan | /teikk-planning |
| Build | /teikk-build, /teikk-android-setup, /teikk-observability |
| Verify | /teikk-test, /teikk-e2e |
| Review | /teikk-review, /teikk-code-simplify |
| Ship | /teikk-ship, /teikk-ci, /teikk-docs |
| Audit | /teikk-androidperf |
29 skills total — commands are entry points; agents also auto-match skills by intent (see AGENTS.md).
skills/ 29 workflow skills (SKILL.md each)
agents/ code-reviewer, test-engineer, security-auditor, android-performance-auditor
.cursor/ rules (4) + slash commands (15)
.claude/ slash commands + hooks
.agents/ Antigravity rules + workflows
references/ testing, security, performance, accessibility checklists
MIT
npx claudepluginhub 22teikk/22teikk-agent-skills-hub --plugin teikk-agents-skillsFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams