Prompts
Prompt engineering and templates
SKILL.md
by miabascacal
Xolgadas no esta confirmado como nombre final solido. Mantener validacion de marca como workstream paralelo, sin desplazar seguridad.
cmd
by jyasuu
Cheat sheet for Windows Command Prompt commands.
langfuse-observation-view
by neuradex
View Langfuse observation (Generation/Span) details. Use when checking specific LLM call input/output, debugging issues, or analyzing costs.
chuangshimao-skills
by guangwen1648
AI image generation skill using GPT-Image-2 model. Simply provide a text prompt and size to generate images. Supports 15 aspect ratios.
prompt-optimizer
by Yukiniro
Transforms vague or simple user prompts into high-quality, structured, and high-performance AI instructions using systematic optimization techniques like XML tagging, few-shot examples, and Chain-of-Thought. Use this skill when you need to improve the reliability, accuracy, or formatting of an AI's output.
telegram-checker
by vood
Check Telegram for unanswered messages, find pending conversations, list unread chats. Use when user asks to check Telegram, find unanswered messages, see pending responses, or review Telegram inbox.
self-enhance
by keenranger
Framework for improving Claude configuration (skills, agents, commands). Use when analyzing work patterns, proposing new skills, identifying knowledge gaps, reviewing Claude setup, or when user asks to improve how Claude helps them.
cx-scope
by m19803261706
CX 工作流 — 项目蓝图探讨。当用户提到"蓝图"、"整体规划"、"项目范围"、 "scope"、"项目探讨"、"功能方案"时触发。多轮对话探讨项目或功能方案， 将结果保存到本地 .claude/cx/features/{dev_id}-{feature}/scope.md， 可选同步到 GitHub Issue（基于 config.github_sync 模式）。
ok-mcp-toggle
by okash1n
ok-mcp-toggle が管理する MCP を global/project scope で有効化/無効化する。管理対象は claude/gemini で、codex は対象外。
lib-docs-generator
by 884js
Generates skills from library documentation automatically. Use when creating a skill from external documentation, fetching docs to local storage, or crawling documentation with curl. Can also be invoked directly with "ライブラリドキュメント", "/lib-docs-generator".
agentic-patterns
by cuba6112
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.
veo-video
by asebesta
Generate videos using Google's Veo 3.1 API via the @google/genai SDK (JavaScript/TypeScript). Use when the user wants to: generate video from a text prompt, animate an image into video, interpolate between two frames, extend an existing video, use reference images for style/asset guidance, or build any application involving AI video generation with Veo. Triggers on mentions of: Veo, video generation, text-to-video, image-to-video, AI video.
scrum
by gyumaruya
Scrum framework for AI agent self-management. Brings Scrum practices into any project to drive development and continuous improvement. Ceremonies chain automatically. Tool-agnostic: works with any issue tracker, VCS, or just local markdown files. Triggers: "scrum", "sprint", "retrospective", "backlog", "レトロ", "計画", "振り返り"
wechat-tech-writer
by yanglei1826877278
自动搜索、抓取、改写技术内容，生成适合微信公众号的中文科普文章。涵盖AI大模型、GitHub开源工具、技术话题。当用户说"写一篇关于XXX的文章"、"帮我研究XXX"、"生成公众号文章"时使用。
smart-routing
by jamelna-apps
When deciding which Claude model (Opus/Sonnet/Haiku) to use, or when "route", "which model", "complex task", "multi-file", "architectural", or "deep debugging" is mentioned. Guides quality-first model selection.
continuous-claudemd-updates
by vijaykpatel
Maintains CLAUDE.md in sync with codebase changes after commits. Use when (1) A commit has been made and CLAUDE.md needs updating, (2) User explicitly requests CLAUDE.md update or audit, (3) Major refactoring or architectural changes occur, (4) New conventions or patterns are established, (5) Files referenced in CLAUDE.md are deleted/moved. Keeps documentation concise by moving verbose content to docs/ folder with links, removes outdated information, and ensures CLAUDE.md reflects current codebase state.
plan-prd
by navidemad
Create product requirement documents when user wants to plan features, write specs, or document new functionality. Supports minimal core features, focused expansions, and task-based changes. Automatically loads context from related PRDs to maintain consistency.
missy
by boilermaker-innovator
Missy is Jon's iTabs AI coach and skill router. Activate when Jon wants to talk through his business, figure out what to work on, OR when he describes something he wants to build or do. Missy interviews Jon with a few quick questions, identifies the right skill, then builds ONE combined link — tap it and Claude opens with the skill loaded and the brief already written. No copy-paste needed.
daily-learning-push
by yuzhaoyang4java
每日技术学习内容生成与推送 Skill，面向后端工程师（Java/Go 等）。每天两次主动推送丰富内容：上午9点和下午14点各推送算法题（2道）+ 架构 + AI大模型 + 前沿资讯（3篇）。内容包含完整代码示例、原理图解、业务场景联想，适合中高级工程师进阶。触发场景：(1) 心跳检查时判断当前时段是否已推送；(2) 用户说"今日学习"、"给我推送内容"、"每日推送"、"学习内容"等；(3) 用户反馈内容不够详细时重新生成。
section-11
by sjh-ttm
Evidence-based endurance coaching protocol (v11.39). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.
claude-dash-admin
by jamelna-apps
When user mentions "system health", "cleanup", "optimize claude-dash", "memory system", "indexes", "watcher", or wants to maintain the claude-dash infrastructure. Provides self-maintenance guidance.
mistral-hidden-params-ft
by Haruk1y
Run end-to-end fine-tuning for request_text-to-hidden-params JSON prediction with Ministral-3-3B in this repository. Use when rebuilding train/validation/test splits from train-only data, converting data to prompt-completion format, launching TRL SFT on Hugging Face Jobs, validating strict JSON output behavior, merging LoRA adapters into full models, and reporting job/model status with links.
inquirer-patterns
by vanman2024
Interactive prompt patterns for CLI tools with text, list, checkbox, password, autocomplete, and conditional questions. Use when building CLIs with user input, creating interactive prompts, implementing questionnaires, or when user mentions inquirer, prompts, interactive input, CLI questions, user prompts.
paper-to-note
by hixz12d
"将实验型与深度学习论文 PDF 转为 evidence-backed 的 Obsidian Markdown 笔记。支持论文类型路由、Figure 论证路径分析，以及实验/模型训练信息的结构化整理。"