Prompts
Prompt engineering and templates
model-hierarchy
by zscole
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: "model routing", "cost optimization", "which model", "too expensive", "spawn agent".
agent-sdk
by majesticlabs-dev
Guide for Claude Agent SDK - build custom AI agents powered by Claude. Covers installation, authentication providers, tool permissions, file-based configuration, TypeScript/Python code examples, and project scaffolding templates.
agents-md
by ranbot-ai
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed
second-opinion
by lv416e
"Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion."
ai-evaluation-evals
by oldwinter
Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.
humanizer-zh
by oldwinter
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
fundraising-strategy
by oldwinter
Plan early-stage fundraising strategy, investor pipeline, and process execution.
skilling-it
by v1-io
Use when creating, writing, editing, or improving Claude Code skills. Covers SKILL.md structure, frontmatter, description optimization, progressive disclosure, bundled resources, and validation. Triggers on "create a skill", "write a skill", "improve skill", "skill description", "SKILL.md".
skill-creator
by lv416e
"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. 効果的なスキルを作成するためのガイド。専門知識、ワークフロー、ツール統合によってClaudeの能力を拡張する新しいスキルを作成（または既存スキルを更新）したい場合に使用"
voice-mode
by llblab
"Unified voice I/O super-skill: speak via say, listen via listen, and run duplex voice dialogue."
building-with-llms
by oldwinter
"Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents."
sync-skills-manager
by oldwinter
Manage synchronization workflows between repository skills and local system skill directories.
agent-evaluation
by ranbot-ai
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on re...
template-skill
by lv416e
"Replace with description of the skill and when Claude should use it. スキルの説明とClaudeがそれを使用すべきタイミングに置き換えてください"
oracle-codex
by PaulRBerg
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think", "second opinion on code", "consult the oracle", "ask the oracle", or mentions using an AI oracle for planning or code review. NOT for implementation tasks.
audit-context-building
by lv416e
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
refine-prompt
by PaulRBerg
This skill should be used when the user asks to "refine a prompt", "optimize a prompt", "improve my prompt", "rewrite prompt for LLM", "craft a better prompt", or mentions prompt engineering, prompt optimization, or appending to PROMPT.md.
claude-in-chrome-troubleshooting
by lv416e
Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
advanced-evaluation
by ranbot-ai
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise compari
humanizer-zh
by oldwinter
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
skill-creator
by futuregerald
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.
prompt-engineering
by v1-io
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
ai-evaluation-evals
by oldwinter
Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.
smalltalk-mcp
by CorporateSmalltalkConsultingLtd
Interact with live Smalltalk images (Squeak, Cuis) via MCP. Evaluate code, browse classes, view method source, define and modify classes and methods, query hierarchies and categories in a running Smalltalk environment.