Prompts
Prompt engineering and templates
model-researcher
by IgorWarzocha
Add new/custom AI models to opencode.json. Use proactively for bleeding-edge releases, non-standard providers, self-hosted models, or custom endpoints. Examples: - user: "Add the new Claude 4.5" → websearch for API specs, add provider entry with baseUrl, verify model ID format - user: "Use my local Ollama instance" → configure custom provider with http://localhost:11434, set model ID format - user: "Configure this OpenAI-compatible proxy" → add provider with custom baseUrl, set apikey env var, verify compatibility - user: "Model X just released, add it" → research provider documentation, find model ID and capabilities, add to config
neuro-symbolic-reasoning
by sundial-org
Neuro-symbolic AI combining LLMs with symbolic solvers. Use when exploring neuro-symbolic approaches (ideation, no code) or implementing solver integrations (code).
tinker-training-cost
by 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.
x-article-publisher
by joeseesun
Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
coder-rules-requirements
by OzeroHAX
Requirement quality rules for coding tasks with traceable MUST/SHOULD and verifiable acceptance criteria.
testing-api-manual
by OzeroHAX
Manually verify API behavior with reproducible requests and response checks; not contract version compatibility governance
coder-rules-clean-code
by OzeroHAX
Clean code execution rules for coding agents with verifiable quality gates.
skill-creator
by julianromli
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.
llm-application-dev
by julianromli
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
resend-design-skills
by julianromli
Use when needing Resend design resources. Routes to brand guidelines, visual identity, and other design sub-skills.
template-skill
by julianromli
Replace with description of the skill and when Claude should use it.
obsidian-helper
by ZhanlinCui
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩（00_Inbox/AI/、追加式、白名单字段） 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤，不要自作主张 【禁止行为】： - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记（除非用户明确指定）
doc-sync-tool
by ZhanlinCui
自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件，保持内容一致性。支持自动监听和手动触发。
skill-creator
by ZhanlinCui
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.
fullstack-template-generator
by pingcy
Generates a complete fullstack application template with Python FastAPI backend and React Vite frontend. Includes OpenAI ChatGPT integration, CORS configuration, comprehensive error handling, and a modern Tailwind CSS + shadcn/ui React UI. Use this skill when the user wants to bootstrap a new fullstack web application project with both API backend and web frontend components ready to go.
hiring-helper
by dazuck
Screen job candidates using AI-powered evaluation. Use when asked to "screen candidates", "review applicants", "evaluate candidates", or when reviewing resumes and applications.
docu-optimizer
by kojott
Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny's best practices
custom-local-skills-guidance
by EdanStarfire
Guide to the 6 custom injection points available for extending dev-setup workflows with project-specific behavior.
prompt-improver
by dazuck
Transform any rough prompt, task description, or job into an optimized AI instruction prompt. Use when users ask to "improve this prompt", "make this better for an AI", "optimize this for Claude/GPT", or provide raw instructions that need refinement into a well-structured prompt following best practices.
process-manager
by EdanStarfire
Safely start, monitor, and stop processes by PID. Use when managing background servers, finding running processes, or ensuring clean process termination.
worktree-manager
by EdanStarfire
Manage git worktrees for isolated issue work. Create, list, and remove worktrees safely.
handoff
by blacktop
Generate optimized handoff prompts for delegating tasks to LLM agents. Use when needing to hand off work to another agent (GPT-5.2/Codex, Claude Opus 4.5/Sonnet 4, or Gemini 3 Pro/Flash), whether for a sub-task/parallel task within the same project or a fresh start handoff to a new agent context. Triggers on requests like "create a handoff prompt", "delegate this task to another agent", "hand this off", or "prepare context for another agent".
personalize-skills
by dazuck
Customize Operator Skills for your environment. Use when first installing skills or when you want to update your personal values.
coach
by dazuck
Expert advisor and thinking partner for strategic situations. Rapidly develops domain expertise, identifies knowledge gaps, and provides radically candid coaching to accelerate learning and decision-making.