Claude Skills by KevinZai

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Prompt engineering technique: present possibly-wrong claims to trigger correction instead of 'remember to X' reminders. Use when: writing CLAUDE.md rules, agent instructions, system prompts, or when agents keep forgetting instructions.

Real-time cost tracking across all agent sessions with budget alerts

Claude Desktop Cowork integration guide for CC Commander users. Cowork is Claude Desktop's autonomous execution mode with 11 official Anthropic plugins. This skill teaches how to configure CC Commander skills for Cowork mode, plugin compatibility, scheduled task patterns, custom plugin development, handoff protocols, and security considerations.

Guide for building custom Cowork plugins that leverage CC Commander skills. Covers plugin anatomy (manifest, handler, permissions), 5 example plugins, packaging CC Commander skills as plugins, local testing, and publishing to the plugin directory.

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate).

Structured subagent delegation with 7 agent types, report format enforcement, and model selection. Use when delegating work to subagents, spawning parallel agents, or orchestrating multi-agent tasks. Triggers: 'delegate', 'subagent', 'orchestrate agents', 'spawn worker', 'multi-agent', 'dispatch agent'.

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsiste...

Server-browser-test-iterate development cycle using Claude Desktop's preview feature or Playwright MCP. Start dev server, open browser, test interactions, capture results, fix issues, iterate. Supports Next.js, Vite, Express, and other frameworks with auto-detection.

Curated SVG tech stack icons for React/Next.js. TypeScript-first, SVGO-optimized, with light/dark/wordmark variants. Use when adding technology logos, stack badges, or brand icons to UI.

Multi-agent opposing review for important decisions. Spawns FOR agent + AGAINST agent + Referee for synthesized analysis. Use when: architecture decisions, vendor evaluations, approach tradeoffs, 'should we X?', 'I'm not sure about', reversibility concerns, major refactors.

Dispatch is Claude's background task execution system. Bible-optimized patterns for background task execution, overnight builds, batch processing, scheduled reviews, Dispatch + Task Commander integration, error handling, retry logic, cost tracking, and completion notifications.

Pre-built Dispatch task templates for common background workflows. 8 ready-to-use templates: overnight-build, batch-review, dependency-update, security-scan, performance-benchmark, content-generation, data-migration, monitoring-setup. Each includes description, duration, cost estimate, permissions, and config.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped.

Build email capture and newsletter signup components for Next.js + shadcn/ui projects. Signup forms, lead magnets, popup/slide-in triggers, Resend/Mailchimp/ConvertKit integration, double opt-in, and drip sequence templates. Use when: user wants email signup, newsletter forms, lead magnets, popups, or email marketing integration.

You are an email systems engineer who has maintained 99.9% deliverability across millions of emails. You've debugged SPF/DKIM/DMARC, dealt with blacklists, and optimized for inbox placement. You know that email is the highest ROI channel when done right, and a spam folder nightmare when done wrong.

**Tier:** POWERFUL **Category:** Engineering **Tags:** AI agents, architecture, system design, orchestration, multi-agent systems

**Tier:** POWERFUL **Category:** Engineering **Domain:** Multi-Agent Systems / AI Orchestration ---

**Tier:** POWERFUL **Category:** Engineering / Architecture **Maintainer:** Claude Skills Team

**Tier:** POWERFUL **Category:** Engineering **Domain:** Testing / API Quality ---

**Tier:** POWERFUL **Category:** Engineering **Domain:** Release Management / Documentation

**Tier:** POWERFUL **Category:** Engineering **Domain:** DevOps / Automation

**Tier:** POWERFUL **Category:** Engineering **Domain:** Documentation / Developer Experience ---

**Tier:** POWERFUL **Category:** Engineering **Domain:** Data Architecture / Backend ---

> **Skill Type:** POWERFUL > **Category:** Engineering > **Domain:** Dependency Management & Security

**Tier:** POWERFUL **Category:** Engineering **Domain:** Security / DevOps / Configuration Management ---

**Tier:** POWERFUL **Category:** Engineering **Domain:** Parallel Development & Branch Isolation

This skill should be used when the user asks to "design interview processes", "create hiring pipelines", "calibrate interview loops", "generate interview questions", "design competency matrices", "analyze interviewer bias", "create scoring rubrics", "build question banks", or "optimize hiring systems". Use for designing role-specific interview loops, competency assessments, and hiring calibration systems.

**Tier:** POWERFUL **Category:** Engineering **Domain:** AI / API Integration

**Tier:** POWERFUL **Category:** Engineering - Migration Strategy **Purpose:** Zero-downtime migration planning, compatibility validation, and rollback strategy generation

**Tier:** POWERFUL **Category:** Engineering **Domain:** Monorepo Architecture / Build Systems ---

**Category:** Engineering **Tier:** POWERFUL **Description:** Design comprehensive observability strategies for production systems including SLI/SLO frameworks, alerting optimization, and dashboard generation.

**Tier:** POWERFUL **Category:** Engineering **Domain:** Performance Engineering ---

**Tier:** POWERFUL **Category:** Engineering **Domain:** Code Review / Quality Assurance ---

The RAG (Retrieval-Augmented Generation) Architect skill provides comprehensive tools and knowledge for designing, implementing, and optimizing production-grade RAG pipelines. This skill covers the entire RAG ecosystem from document chunking strategies to evaluation frameworks, enabling you to build scalable, efficient, and accurate retrieval systems.

**Tier:** POWERFUL **Category:** Engineering **Domain:** Software Release Management & DevOps

**Tier:** POWERFUL **Category:** Engineering **Domain:** DevOps / Site Reliability Engineering ---

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks,...

--- **Name**: skill-tester **Tier**: POWERFUL **Category**: Engineering Quality Assurance **Dependencies**: None (Python Standard Library Only) **Author**: Claude Skills Engineering Team **Version**: 1.0.0 **Last Updated**: 2026-02-16 ---

--- **Name**: sample-text-processor **Tier**: BASIC **Category**: Text Processing **Dependencies**: None (Python Standard Library Only) **Author**: Claude Skills Engineering Team **Version**: 1.0.0 **Last Updated**: 2026-02-16 ---

**Tier**: POWERFUL 🔥 **Category**: Engineering Process Automation **Expertise**: Code Quality, Technical Debt Management, Software Engineering

Define success criteria before writing specs. Progression: evals → spec → plan → implement → verify. Use when: starting features, writing specs, planning work, 'how should I build this?', feature kickoff.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API