Skills

from affaan-m/everything-claude-code

from affaan-m/everything-claude-code

Test-driven development workflow for Laravel using PHPUnit or Pest — factories, Unit/Feature/Integration layering, `RefreshDatabase` vs `DatabaseTransactions` strategies, `actingAs`/`postJson`/`assertDatabaseHas` patterns, and an 80%+ coverage target, following a RED-GREEN-REFACTOR cycle.

Bun as an all-in-one JavaScript runtime, package manager, bundler, and test runner — when to choose Bun vs Node, npm/yarn migration notes (`bun install`, `bun run`, `bun x`), `bun test`, `Bun.serve`, `Bun.file`, and Vercel deployment with `bun install --frozen-lockfile`.

A skill from the Everything Claude Code performance system that provides data scraping agent patterns and workflows, part of a comprehensive AI agent harness framework featuring 48 specialized subagents and 183+ skills for production-ready development.

An interactive grilling session that stress-tests your plan against the existing domain model, sharpens fuzzy terminology, cross-references code for contradictions, and updates CONTEXT.md and ADR documentation inline as decisions crystallize.

Production-grade engineering skills encoding senior-level workflows, quality gates, and best practices for every phase of the software development lifecycle.

A curated collection of awesome LLM applications with skills for building AI-powered apps, covering RAG, agents, and various use cases.

Provides Kotlin development expertise and patterns, from a collection of 65 skills and 9 workflows built for full-stack developers.

Generates secure, gas-optimized transaction payloads for complex blockchain interactions with advanced encoding and validation techniques.

`/health` skill from tw93's Waza bundle (Claude Code only) — audits a Claude Code setup by checking CLAUDE.md, rules, skills, hooks, MCP, and agent behavior, then flags issues by severity. Built on the six-layer framework described in the author's blog post.

Give any coding agent live crypto data via the Surf CLI — prices, technical indicators, order books, funding rates, wallet balances, DeFi TVL, Polymarket/Kalshi odds, and SQL-queryable on-chain tables across 40+ blockchains and 200+ sources. The skill teaches the agent to auto-discover endpoints (`surf list-operations`, `surf <cmd> --help`) and return structured JSON, with 30 free credits daily and no API key required to start.

Persona skill distilled by 女娲 — encodes Tong Jincheng (童锦程, the "deep-emotion ancestor")'s cognitive frameworks (吸引力 > 讨好, 给台阶, 人性不可考验, 炫耀即暴露不安全感, 成功前后是两个世界) and 9 decision heuristics into a runnable Claude Code skill, grounded in ~200,000 characters of first-hand video transcripts (livestream compilations + dating vlogs) for relationship, dating, and personal-growth analysis.

A skill from the Everything Claude Code performance system providing Kotlin Ktor framework patterns and best practices for building server-side applications, part of a comprehensive collection covering 12+ language ecosystems with production-ready standards.

from affaan-m/everything-claude-code

Writes Shopify Customer Account API GraphQL queries and mutations for customer-facing data — orders, payment methods, addresses. Every response first searches the latest Shopify documentation and then validates the generated code before returning it.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky that preserves the author's voice (optionally sourced from the `brand-voice` skill) and adapts a single source idea per platform constraint — while banning duplicate copy, fake founder-reflection posts, and filler CTAs like "What do you think?".

A self-improving agent skill for OpenClaw that automatically captures experiences through 7 trigger conditions (errors, corrections, knowledge gaps, better practices, etc.), with structured LEARNINGS/ERRORS/FEATURE_REQUESTS tracking, experience promotion mechanisms, and safety guardrails including anti-drift and value-priority scoring.

Xiaohongshu (小红书) note analysis tool built as an AI Studio app, analyzing content performance and providing recommendations for social media posts.

from minimax-ai/skills

from binance/binance-skills-hub

from affaan-m/everything-claude-code

from affaan-m/everything-claude-code

from affaan-m/everything-claude-code

Unofficial Convex development skills for AI coding agents, providing tools and workflows for building reactive backends with TypeScript on the Convex platform.

Unified media generation via the fal.ai MCP — image (Nano Banana 2 and Pro), video (Seedance 1.0 Pro, Kling Video v3 Pro, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound) — exposing `search`, `find`, `generate`, `result`, `status`, `cancel`, `estimate_cost`, `models`, and `upload` tools.

Three-layer verification pipeline for AI output — classifies every response, extracts verifiable claims, finds supporting or contradicting sources via web search, runs an adversarial hallucination check, and emits inline or full reports tagging each claim as VERIFIED / PLAUSIBLE / DISPUTED / FABRICATION RISK with source links. Supports a persistent active mode and on-demand one-shot mode.

A skill from the Everything Claude Code performance system covering Perl security patterns including taint mode and safe I/O practices, part of a comprehensive multi-language AI agent harness framework with rules and skills for 12+ language ecosystems.

A skill from the Everything Claude Code performance system providing Perl TDD workflows with Test2::V0, prove, and Devel::Cover, part of a comprehensive multi-language AI agent harness framework with production-ready testing patterns for 12+ ecosystems.

Covers the full React Native upgrade workflow including template diffs via Upgrade Helper, dependency updates, Expo SDK steps, and common pitfalls. Provides problem-to-skill mapping and reference files for core upgrades, dependency compatibility, React 19 alignment, and monorepo targeting.