Prompts
Prompt engineering and templates
super-ralph-wiggum
by tdimino
Super Ralph Wiggum - autonomous iteration loops with templates, PRD support, progress tracking, and browser testing. This skill should be used when running Claude Code in autonomous loops for test coverage improvement, PRD-based feature development, documentation generation, dataset creation, lint fixing, code cleanup, or framework migrations. Combines the plugin's in-session loop mechanism with specialized templates and best practices from Geoffrey Huntley, Ryan Carson, and AI Hero.
claude-agent-sdk
by tdimino
Build AI agents using the Claude Agent SDK. Covers query functions,
minoan-swarm
by tdimino
Orchestrate Claude Code Agent Teams with Minoan-Semitic naming. This skill should be used when planning or launching multi-agent teams to tackle project phases, features, or complex tasks in parallel. It auto-discovers project context (CLAUDE.md, roadmaps, plans, issues) and generates named team configurations with structured task lists and file ownership.
codex-cto
by tdimino
Inverted orchestration—Codex CLI acts as CTO (planning and reviewing), Claude Code executes with native tools. Use when a task benefits from external architectural oversight before and after implementation.
mcp-server-manager
by tdimino
Configure and manage MCP (Model Context Protocol) servers in Claude Code CLI. Use this skill when adding, removing, listing, or troubleshooting MCP servers, or when questions arise about MCP configuration, transport types, scopes, or authentication. Essential for connecting Claude Code to external tools, databases, and APIs.
claude-md-manager
by tdimino
Create, audit, and maintain CLAUDE.md documentation files that configure Claude Code for projects. Use this skill when (1) initializing a new project with Claude Code configuration, (2) reviewing or improving existing CLAUDE.md files, (3) organizing project instructions using progressive disclosure patterns, (4) converting repeated instructions into permanent documentation, or (5) setting up agent_docs/ structures for larger codebases. Handles the WHAT/WHY/HOW framework, conciseness optimization, and file import patterns.
ralph-wiggum
by jkitchin
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
claude-light
by jkitchin
Expert assistant for conducting remote experiments with Claude-Light - a web-accessible RGB LED and spectral sensor instrument for statistics, regression, optimization, and design of experiments
image-generation
by jkitchin
AI-powered image generation and editing using Google Gemini, Google Imagen, and OpenAI models. Generate images from text descriptions, edit existing images, create logos/stickers, apply style transfers, and produce product mockups. Use this skill when the user requests: - Image generation from text descriptions - Image editing or modifications - Logos, stickers, or graphic design assets - Product mockups or visualizations - Style transfers or artistic effects - Iterative image refinement Available models: - Google Gemini: gemini-2.5-flash-image (Nano Banana), gemini-3-pro-image-preview (Nano Banana Pro) - Google Imagen: imagen-4.0-generate-001, imagen-4.0-ultra-generate-001, imagen-4.0-fast-generate-001 - OpenAI: gpt-image-1.5 (recommended), gpt-image-1, dall-e-3, dall-e-2 Inspired by: https://github.com/EveryInc/every-marketplace/tree/main/plugins/compounding-engineering/skills/gemini-imagegen
image-forge
by tdimino
Precision image editing using ImageMagick 7, sips, rembg, and Pillow with intelligent routing to AI semantic editing (Gemini/nano-banana-pro) for content-aware operations. This skill should be used when performing any image manipulation task including cropping, resizing, compositing, annotating, format conversion, color adjustment, batch processing, montage creation, or when combining deterministic edits with AI-powered semantic edits.
linear-a-decipherment
by tdimino
"Computational analysis of Linear A inscriptions using Cyrus H. Gordon's Semitic hypothesis. This skill should be used when working with Linear A transliterations, Minoan language decipherment, inscription analysis, sign frequency or co-occurrence statistics, consonantal skeleton extraction, Proto-Semitic root comparison, Gordon lexicon lookups, libation formula patterns, or preparing training data for ML decipherment models. Triggers: Linear A, Linear B projection, Minoan script, GORILA corpus, HT/ZA/PK tablets, Semitic cognates, transliteration analysis, sign values, syllabary, undeciphered scripts, computational epigraphy, Phaistos, Hagia Triada, lashon ha-kretan."
smolvlm
by tdimino
Local vision-language model for image analysis using SmolVLM-2B
slack-respond
by tdimino
"Process unhandled Slack messages as Claudicle with persistent memory. Loads user models and soul state, posts terminal-styled thinking messages, generates cognitive-step responses, updates memory based on mentalQuery decisions. Requires Session Bridge listener running."
rlama
by tdimino
Local RAG system management with RLAMA. Create semantic knowledge bases from local documents (PDF, MD, code, etc.), query them using natural language, and manage document lifecycles. This skill should be used when building local knowledge bases, searching personal documents, or performing document Q&A. Runs 100% locally with Ollama - no cloud, no data leaving your machine.
slack
by tdimino
"Slack workspace integration: 7 on-demand scripts (post, read, search, react, upload, channels, users) + Session Bridge (connect any Claude Code session to Slack via background listener + inbox.jsonl). Daemon, soul engine, and memory system live in Claudicle (github.com/tdimino/claudicle)."
promptify
by intellectronica
Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.
word-export
by u9401066
Word 匯出技能 - 將草稿匯出為符合期刊格式的 Word 文件。 LOAD THIS SKILL WHEN: 匯出 Word、export、template、word count、轉成 docx
idea-validation
by u9401066
研究假說驗證與可行性評估框架。 LOAD THIS SKILL WHEN: hypothesis、假說、PICO、feasibility、可行性、testable、可驗證、研究計畫評估、check feasibility CAPABILITIES: 純指令技能，不需要專屬 MCP tool。利用 LLM 推理能力 + 現有 tools (list_saved_references, search_local_references) 完成分析。
fogg-behavior-model
by flpbalada
Design behavior change using the B=MAP framework. Use when designing
claude
by danielraffel
Ask Claude directly via bridge mode by default (claude -p), with optional deterministic prompt-package generation when explicitly requested.
academic-debate
by u9401066
學術辯論與觀點比較框架。 LOAD THIS SKILL WHEN: debate、辯論、pro/con、正反方、devil's advocate、挑戰假設、counter-argument、反駁、compare viewpoints、比較觀點、challenge、質疑 CAPABILITIES: 純指令技能，不需要專屬 MCP tool。利用 LLM 推理能力 + 現有 tools (read_draft, search_local_references) 完成分析。
trent-config
by trentshaines
Overview of Trent's development environment and dotfiles setup. Use this skill first to understand the overall setup, then reference specific skills for details. CRITICAL - Trent uses fish shell, NOT zsh.
openclaw-self-healing
by Ramsbaby
4-tier autonomous self-healing system for OpenClaw Gateway with persistent learning, reasoning logs, and multi-channel alerts. Features Claude Code as Level 3 emergency doctor for AI-powered diagnosis and repair.
trent-claude-skills
by trentshaines
Help with creating and managing Claude Code skills. Use when the user asks about creating skills, skill structure, or customizing Claude Code behavior.