By lisovet
Continuously probe your project for bugs, silent failures, and visual inconsistencies with six specialist QA agents.
Verifies data consistency across sources, validates computed values, checks for corruption, and monitors growth trends. Use when numbers don't add up.
Finds divergence between config files, environment variables, code defaults, and actual runtime behavior. Use when investigating config-related issues.
Verifies domain rules, business logic, and guardrails from CLAUDE.md are enforced in code and at runtime. Use when you need to check if project rules are actually followed.
Generates remediation PRDs from QA findings with root cause analysis, fix approach, and acceptance criteria
Finds error handling gaps, swallowed exceptions, empty catch blocks, and fallback behavior that masks real problems. Use when investigating reliability and error handling.
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.
Drop-in skills and plugins for Claude Code that turn it into a specialist.
Autonomous QA • iOS design • AI image generation • DTC copywriting • Landing page architecture
Skills are markdown instruction files that give Claude Code deep domain expertise. Install one and Claude gains an opinionated, battle-tested workflow for that domain — not just knowledge, but judgment.
Each skill is a SKILL.md file (with optional reference docs) that you drop into ~/.claude/skills/. Claude Code loads them automatically.
| Plugin | What It Does | |
|---|---|---|
| qa-monkey | A suspicious, curious QA engineer that continuously probes your project for bugs nobody else caught. 6 specialist agents (Invariant Checker, Silent Failure Hunter, Drift Detector, Data Integrity Auditor, Test Gap Finder, Visual Auditor) investigate with confidence-scored, evidence-backed findings. Ralph-loop iteration, Puppeteer screenshots, multi-hypothesis testing. Born from catching real production bugs — the hard way. |
Plugins vs Skills: Plugins have commands (
/qa-monkey), hooks, and agents. Skills are passive instruction files. Both live in this repo.
| Skill | What It Does | |
|---|---|---|
| ios-frontend-design | An opinionated creative director for iOS apps. Produces distinctive SwiftUI interfaces that honor HIG while rejecting the generic "AI-generated app" look. Includes anti-slop patterns, color palette methodology, adaptive layout system, and worked examples. |
| Skill | What It Does | |
|---|---|---|
| ad-creator | Generates ad images using Google's Nano Banana (Gemini) API. Comes with a Python generation script, 40 proven DTC ad templates (social proof, comparison, UGC, editorial, and more), and an interactive prompt-crafting workflow. |
| Skill | What It Does | |
|---|---|---|
| conversion-architect | 20 mental models for auditing and architecting DTC landing pages. Covers MECLABS diagnostics, belief chains, emotional sequencing, objection mapping, and more. The strategic foundation layer for all copywriting skills. | |
| copywriting-strategist | Generates campaign angles using the Angle Generation Machine methodology. Includes Schwartz's 7 techniques, 25 headline formulas, emotional triggers library, and a systematic process for turning brand knowledge into high-converting hooks. |
┌─────────────────────────┐
│ conversion-architect │ Audit existing pages or
│ (20 Mental Models) │ architect new ones
└──────────┬──────────────┘
│
▼
┌─────────────────────────┐
│ copywriting-strategist │ Generate strategic angles
│ (Angle Generation) │ and headline variations
└──────────┬──────────────┘
│
▼
[ Your copy ]
Start with conversion-architect to diagnose what's wrong or plan what to build. Then use copywriting-strategist to generate the angles and headlines.
git clone https://github.com/lisovet/claude-skills.git /tmp/claude-skills
cp -r /tmp/claude-skills/skills/qa-monkey ~/.claude/plugins/qa-monkey
Then restart Claude Code and run /qa-monkey to start investigating.
git clone https://github.com/lisovet/claude-skills.git /tmp/claude-skills
cp -r /tmp/claude-skills/skills/* ~/.claude/skills/
npx claudepluginhub lisovet/claude-skills --plugin qa-monkeyComprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.