提示词

tinker-training-cost

sundial-org

Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

claude-code-plugins

melodic-software

"Draft an autoMode classifier block for Claude Code by interviewing you about what should and should not be auto-approved, then printing a paste-ready JSON block to stdout. Entries follow the shape the classifier actually reads well — a label, bulleted COVERED / NOT COVERED, one line of rationale — and every section keeps \"$defaults\" so customizing does not discard the built-in rules. Use when: 'help me write auto mode rules', 'draft an autoMode block', 'set up auto mode', 'add an auto-mode rule for X', 'my auto mode rules are too vague', 'rewrite this classifier entry', or after an audit shows rules being dropped or ignored. Prints only — never writes any settings file."

codex

Lucklyric

This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.

my-skill Skill

2025Emma

Claude Skills Meta-Skill

2025Emma

arxiv-to-md

solatis

Convert arXiv papers to LLM-consumable markdown. Invoke when user provides an arXiv ID or URL, or when syncing academic papers from a PDF folder to a markdown destination.

prompt-engineer

solatis

Invoke IMMEDIATELY via python script when user requests prompt optimization. Do NOT analyze first - invoke this skill immediately.

AI Core Skill

markus41

Qdrant Documentation

Energy Management Skill

markus41

Coral TPU Object detection USB

Design Styles Skill

markus41

"Access 263+ design styles with AI-optimized prompt keywords for frontend development"

doc-sync

solatis

Synchronizes docs across a repository. Use when user asks to sync docs.

gemini-imagegen

MooseGoose0701

Generate and edit images using Google Gemini's native image generation models (Nano Banana / Nano Banana Pro). Supports text-to-image, image editing with reference images, multi-image composition, and character consistency. Use when the user asks to generate images via Gemini, create AI illustrations, edit photos with Gemini, or needs high-quality image generation with the Google API. Requires GEMINI_API_KEY. Triggers: "generate image with gemini", "nano banana", "gemini image", "create illustration", "AI generate picture", "text to image".

trace-qa

MooseGoose0701

Analyze and answer questions about agent execution traces. Use this skill when the user asks about a trace, wants to debug a failed agent run, understand what an agent did, analyze token usage or efficiency, or asks "what happened in trace X". Triggers: trace analysis, trace debugging, trace QA, execution review, agent run review.

peers-advisory-group

isjiamu

私董会专家助手，引导用户完成完整的私董会流程。通过四位顶级幕僚（巴菲特、比尔·盖茨、马斯克、乔布斯）的多轮提问和反馈，帮助用户深入剖析问题本质并获得可执行的解决方案。触发场景：(1) 用户说"开始私董会"、"私董会"、"peers advisory"，(2) 用户需要多角度分析复杂决策问题，(3) 用户希望获得不同商业领袖视角的建议，(4) 用户面临职业、创业、投资等重大决策需要深度咨询。支持自定义幕僚阵容。

q-infographics

TyrealQ

Converts documents into business stories and infographics using Gemini 3.0 Pro (Python SDK). Use when the user wants to convert a document, report, or text into a visual business story or infographic.

saas-seeder

peterbamuhigire

"Bootstrap a new SaaS from the SaaS Seeder Template: setup database, configure environment, create super admin user, and verify three-tier panel structure. Use when initializing a new multi-tenant SaaS project from this template."

skill-creator

peterbamuhigire

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

customer-workspace

aktsmm

Customer workspace initialization skill. Provides inbox (information accumulation), meeting minutes management, and auto-classification rules. Use for "setup customer workspace" or "add inbox feature" requests.

agentic-workflow-guide

aktsmm

"Create, review, and update Prompt and agents and workflows. Covers 5 workflow patterns, agent delegation, Handoffs, Context Engineering. Use for any .agent.md file work or multi-agent system design. Triggers on 'agent workflow', 'create agent', 'ワークフロー設計'."

doc-architect

peterbamuhigire

"Generate Triple-Layer AGENTS.md documentation by scanning a project for its tech stack, data directory, and planning directory. Use when the user asks to standardize project documentation, generate agent files, or create AGENTS.md guides."

project-requirements

peterbamuhigire

"Guided interview to create comprehensive project requirements documentation (requirements.md, business-rules.md, user-types.md, workflows.md) for a new SaaS project. Use before bootstrapping the SaaS Seeder Template."

skill-creation-guide

gleanwork

Auto-triggers when users discuss creating skills or ask about SKILL.md format. Triggers on phrases like "create a skill", "write a skill", "make a skill", "new skill", "SKILL.md format", "skill structure", "how do skills work", "skill best practices", or when the user wants to add custom behavior to Claude Code.

q-topic-finetuning

TyrealQ

"Fine-tune and consolidate topic modeling outputs (BERTopic, LDA, etc.) into a theory-driven classification framework for academic manuscripts. Use when processing topic modeling results that need topic consolidation, theoretical classification, domain-specific preservation, multi-category handling, data verification, or Excel updates with final labels."

ai-error-prevention

peterbamuhigire

Error prevention strategies for AI-assisted development. Use when working with Claude to minimize hallucinations, incomplete solutions, and wasted tokens. Enforces "trust but verify" workflow.