Claude Skills by KevinZai

Fleet Commander — launch, monitor, and manage parallel CC agent teams

Post-implementation hallucination detection. Four questions to verify work is complete, correct, and evidence-based. 94% detection rate for AI errors. Inspired by SuperClaude Framework.

You are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads, attract organic traffic, and build brand awareness.

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits".

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Practical implementation guide for GDPR-compliant data processing, consent management, and privacy controls.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Build a knowledge graph from your codebase for 71.5x token reduction per query

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety".

Run when Claude feels off, ignores rules, or hooks/MCP need auditing.

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

Interactive project initialization — questionnaire-driven setup that determines build type, selects skills, and generates a tailored CLAUDE.md

Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.

Pattern for progressively refining context retrieval to solve the subagent context problem

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production".

Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan.

Switch between optimized workflow modes — design, saas, marketing, research, writing, night, yolo, unhinged, caveman, normal

Brainstorm 3-5 monetization strategies with audience fit, risks, and validation experiments. Use when exploring revenue models, evaluating pricing strategies, or deciding how to monetize a product.

Advanced multi-agent orchestration — swarm patterns, agent specialization, shared state, consensus, and supervision trees

Cross-repo changes using Claude Code's --add-dir flag. Orchestrate changes across 2+ repos simultaneously for shared dependency updates, API contract changes, and monorepo migration. Includes branch management, conflict resolution, and commit strategy across repositories.

MyWiFi Networks / Guest Networks platform patterns. Multi-tenant WiFi management, location provisioning, splash page builder, campaign manager, and guest data analytics.

Setup guide for n8n-MCP server — connect Claude Code to 400+ n8n integrations

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is ex...

Scaffold a new OpenClaw agent from scratch. Interviews for requirements, then generates complete workspace files (SOUL.md, AGENTS.md, TOOLS.md, IDENTITY.md, USER.md) plus the OpenClaw gateway config JSON snippet. Ensures consistency across the 35+ agent fleet.

Bridge CC Commander skills and hooks to OpenClaw agent orchestration platform

OpenClaw ↔ CCC Bridge — lets OpenClaw agents dispatch CCC tasks, browse skills, and manage sessions via the agent-friendly CLI API. Use when OpenClaw agents need to use CC Commander as a project manager.

Full OpenClaw system health audit. Checks all agents, gateway status, costs, memory, cron jobs, errors, and service health. Use for daily check-ins, debugging, or when something feels off. Produces a structured health report.

Complete OpenClaw management suite for Claude Code. Combines self-healing, doctor dispatch, free fleet routing, and the external neurosurgeon pattern into one shareable skill. Works with any OpenClaw installation. Includes health monitoring, auto-repair, cost optimization, and cron-driven autonomous operation.

Native integration with OpenClaw platform — auto-detection, skill sync, bidirectional hooks, agent profiles, memory sync

Production patterns from a 38-agent orchestration system — COMP protocol, atomic messaging, cost-aware routing, escalation boundaries

After fixing a bug, don't stop — write tests, check for similar issues, update instructions. Every bug is a learning opportunity. Use when: bug fix complete, post-fix review, 'what else could break?', preventing regressions.

Run autonomous batch jobs overnight or during long unattended periods. Patterns for usage limit retries, batch checkpointing, multi-session resume, and human gate points. Use when: 'run this overnight', 'batch process', 'autonomous run', 'unattended execution', 'scheduled batch'.

Integration with Paperclip task management API for tracking CC Commander workflows

Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.

Create new Paperclip plugins with the current alpha SDK/runtime. Use when scaffolding a plugin package, adding a new example plugin, or updating plugin authoring docs. Covers the supported worker/UI surface, route conventions, scaffold flow, and verification steps.

Interact with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research, etc.) — only for Paperclip coordination.

File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running w...

Standards and process for creating, cleaning, and maintaining vendor/partner SVG logos across GuestNetworks projects

Master PCI DSS (Payment Card Industry Data Security Standard) compliance for secure payment processing and handling of cardholder data.

This skill should be used when the user asks to \"plan a penetration test\", \"create a security assessment checklist\", \"prepare for penetration testing\", \"define pentest scope\", \"foll...

Full-stack performance monitoring — Core Web Vitals, APM, RUM, synthetic monitoring, and performance budgets