Prompts
Prompt engineering and templates
balance-check
by SneakKestrel16
"Find balance outliers, broken progressions, degenerate strategies, economy imbalances in formulas and data. 'Check game balance'."
context-engineering-advisor
by HMS091
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
review-all-gdds
by SneakKestrel16
"Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload, pillar drift."
goal-prompt-builder
by lsi9923
작업을 바로 실행하지 않고 먼저 질문으로 구체화한 뒤, 에이전트가 스스로 판단할 수 있는 /goal 프롬프트(목표·완료조건·검증증거·제약·중단조건)를 만든다. "골 프롬프트 만들어줘", "/goal 써줘", "작업 지시문 만들어줘", "목표 프롬프트", "goal 작성" 요청에 쓴다.
tooling-git-guardrails-claude-code
by jasonraimondi
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
project-init
by ArjenSchwarz
Initialize Claude Code project settings with standard hooks and language-specific permissions. Use when setting up a new project for Claude Code or adding standard configuration to an existing project.
prompt-de-modulo
by Reedsy2407
Redacta el prompt de un módulo o etapa con la estructura fija (objetivo, pasos manuales, autorizaciones, criterios, límites de commits, paradas, bloque de merge) y lo autoverifica antes de entregarlo. Úsala cuando el humano pida el prompt de un módulo nuevo.
permission-analyzer
by ArjenSchwarz
Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding --dangerously-skip-permissions, or analyzing what permissions a project needs. Reads session logs to extract Bash commands and MCP tools actually used, then generates appropriate allow/deny rules.
gene-set-enrichment
by monarch-initiative
Perform gene set enrichment analysis using AI research providers. Analyzes lists of genes to identify biological themes, pathways, and functional associations.
skill-creator
by ArjenSchwarz
Guide for creating effective Claude Skills. This skill should be used when users want to create (or update) a skill that extends Claude's capabilities with specialised knowledge, workflows, or tool integrations.
skill-authoring-workflow
by HMS091
Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.
cierre-de-modulo
by Reedsy2407
Prepara el cierre de un módulo o etapa: cuenta los commits, corre el sello de pre-merge, pide el veredicto del revisor interno y redacta el informe único. Úsala al terminar la última rebanada, antes de pedir o ejecutar el merge.
publicar
by Reedsy2407
Publica un sitio estático (tipo A) en Workers con archivos estáticos - genera dist/, pasa las pruebas, despliega, hace la prueba de humo y deja la revisión humana en Chrome. Úsala solo cuando el humano pida publicar o actualizar el sitio.
judge
by jthorare
Tune, inspect, and undo cheap-agent-harness judge decisions in-session — config get/set, why, undo, health.
prompt-optimizer
by wasintoh
Advanced prompt optimization and composition system for all prompt types (system prompts, task-specific, creative, technical, agentic). Use when users need to refine, optimize, or transform prompts to achieve better AI outputs. Triggers include requests to improve prompts, make prompts more effective, analyze prompt quality, create prompts from scratch, optimize existing prompts for specific goals, or optimize for Claude 4.x models. Also use when users share prompts that could be improved or ask for prompt engineering guidance.
apple-foundation-models
by ios-agent
Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps
failure-taxonomy
by maragudk
Build a structured taxonomy of failure modes from open-coded trace annotations. Use this skill whenever the user has freeform annotations from reviewing LLM traces and wants to cluster them into a coherent, non-overlapping set of binary failure categories (axial coding). Also use when the user mentions "failure modes", "error taxonomy", "axial coding", "cluster annotations", "categorize errors", "failure analysis", or wants to go from raw observation notes to structured evaluation criteria. This skill covers the full pipeline: grouping open codes, defining failure modes, re-labeling traces, and quantifying error rates.
ado-create-feature
by charlesjones-dev
"Interactively create a new Feature work item in Azure DevOps using configured conventions."
ukrainianizer
by vitalii4reva
Видалення ознак AI-генерованого тексту з української мови. Використовуй для редагування або перевірки тексту, щоб він звучав природно по-українськи. Виявляє та виправляє: русизми, англіцизми, канцеляризми, плеоназми, AI-лексику, надмірне підкреслення значущості, промоційну мову, приховані Unicode watermarks, статистичні AI-патерни (низька perplexity, низька burstiness). Triggers: humanize Ukrainian text, зробити текст українським, прибрати AI, виправити суржик, редагувати українською, nature Ukrainian, remove AI patterns from Ukrainian, fix Russian calques, виправити русизми, канцелярит.
chapter3-guide
by orientpine
"Chapter 3 (사업 목표 및 추진 전략) 작성 가이드 - 템플릿 및 요구사항 통합"
correcting-mistakes
by Sawyer-Middeleer
Self-corrects skill and command instructions after resolving errors. Use when Claude errors during skill/command execution and finds a solution, or when user indicates a mistake was made. Finds the relevant instruction file and applies succinct fixes.
cangjie-lang
by ystyle
Cangjie programming language code generation and analysis expert. Use this when users need to write or analyze Cangjie code.
prompt-engineer
by dy9759
Comprehensive LLM prompt engineering and optimization workflow that orchestrates expert analysis, advanced techniques, and multi-domain optimization using the integrated toolset. Handles everything from basic prompt improvement to complex multi-agent prompt orchestration.
llms-generative-ai
by pluginagentmarketplace
LLMs, prompt engineering, RAG systems, LangChain, and AI application development