Claude Skills by Zandereins

A skill with contradictory instructions to test clarity scoring. Use when testing contradiction detection in the clarity dimension. Do NOT use for actual linting.

Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure.

1. [Tech Stack & Architecture](#1-tech-stack--architecture) 2. [โครงสร้างโปรเจกต์ (Project Structure)](#2-โครงสร้างโปรเจกต์-project-structure) 3. [Roles & Permissions](#3-roles--permissions) 4. [Authentication — SSO Flow](#4-authentication--sso-flow) 5. [Router Configuration](#5-router-configuration) 6. [Portal Page — หน้าเมนูระบบกลาพร้ง](#6-portal-page--หน้าเมนูระบบกลาง) 7. [Application Step Form (v-stepper)](#7-application-step-form-v-stepper) 8. [Dashboard](#8-dashboard) 9. [Application State

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model...

Voice conversations with Claude about your projects. Call a phone number to brainstorm, or have Claude call you with updates.

Manage Raindrop.io bookmarks, collections, tags, and highlights via API. Use when user mentions raindrop, bookmarks, saving links, organizing URLs, bookmark collections, or web highlights.

This skill helps with deployment stuff. It probably works for most deployment scenarios and you might want to use it when you need to deploy things.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Provides Anthropic's official brand color and typography tokens (hex values, font families, sizes, accent order) as reference data to apply when styling an artifact. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. This skill supplies the values; apply them using your target tool's styling API (e.g. python-pptx, CSS, Markdown).

Linux system administration cheatsheet of memory/IO diagnostics, available-RAM capping via the bootloader, job backgrounding, and emergency reboot. Use when the user asks how to inspect memory or disk IO usage on Linux, limit usable RAM for testing, detach a running process to the background and survive a logout, or force a host to restart via SysRq. Covers Red Hat / Fedora (GRUB Legacy and GRUB2). NOT for algorithm or data-structure questions.

Deterministic linter and scorer for instruction files — SKILL.md, AGENTS.md, CLAUDE.md. No model in the loop: the same bytes score the same everywhere. Use for linting, scoring, auditing or CI-gating an instruction file, and for checking whether the commands a file promises actually resolve in the repo. Trigger phrases: "lint my skill", "score my skill", "audit skill", "review my skill", "harden skill", "make this skill better", "optimize my skill", "improve [metric] from X to Y", "benchmark ...

Deterministic skill linter and scoring engine for Claude Code — the Ruff for SKILL.md files. 7-dimension structural scoring (structure, triggers, quality, edges, efficiency, composability, clarity) with anti-gaming detection, ~32% rule-based patches, and cross-session episodic memory. An autoresearch loop that measures first, then fixes — not the other way around. Use for linting, scoring, and autonomously improving any Claude Code skill: trigger accuracy, output quality, edge coverage, token...

This is a skill about doing things. It helps with stuff. You might want to consider using it when you need help. You should possibly try it out. It could maybe be useful for some tasks. Remember to always test your code. Don't forget to save your files. TODO: add more content here FIXME: this section needs work

Multi-perspective code review council: advisors analyze, reviewers cross-examine, chairman synthesizes verdict. USE for: architecture decisions, security audits, tradeoff analysis, "what am I missing" questions, pre-merge deep reviews, iterative re-reviews after fixes. DO NOT USE for: simple code generation, syntax fixes, single-file refactors, or factual lookups. TRIGGERS: 'hydra', 'hydra this', 'hydra review', 'run hydra', 'hydra deep', 'Hydra starten', 'hydra iterate', 'hydra re-review', '...