anthropic-prompt-engineer
Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.
What this skill does
# Anthropic Prompt Engineer Master the art and science of prompt engineering with Anthropic's proven techniques. Generate new prompts from scratch or improve existing ones using best practices for Claude AI models (Claude 4.x, Sonnet, Opus, Haiku). ## What This Skill Does Helps you create and optimize prompts for Claude AI using Anthropic's official techniques: - **Generate new prompts** - Build effective prompts from requirements - **Improve existing prompts** - Optimize prompts for better results - **Apply best practices** - Use proven techniques from Anthropic - **Avoid common mistakes** - Prevent hallucinations and unclear outputs - **Optimize for Claude 4.x** - Leverage latest model capabilities - **Structure complex prompts** - Build multi-step, production-ready prompts ## Why Prompt Engineering Matters **Without proper prompting:** - Inconsistent or incorrect outputs - Hallucinations and made-up information - Unclear or verbose responses - Wasted tokens and API calls - Poor performance on complex tasks - Difficulty reproducing results **With engineered prompts:** - Precise, reliable outputs - Factual, grounded responses - Clear, formatted results - Efficient token usage - Excellent complex task performance - Reproducible, production-ready results ## Quick Start ### Generate a New Prompt ``` Using the anthropic-prompt-engineer skill, create a prompt that: - Extracts structured data from customer emails - Returns JSON format - Handles missing information gracefully - Includes 2 examples ``` ### Improve an Existing Prompt ``` Using the anthropic-prompt-engineer skill, improve this prompt: "Analyze this code and tell me if there are bugs" Make it more effective using Anthropic's best practices. ``` ## Core Techniques Summary ### 1. Be Clear and Direct Provide explicit, unambiguous instructions. Claude 4.x excels with precise direction. ### 2. Use XML Tags for Structure Organize prompts with semantic tags like `<instructions>`, `<example>`, `<context>`. ### 3. Chain of Thought (CoT) Ask Claude to think step-by-step for complex reasoning. ### 4. Prefilling Start Claude's response to guide format and style. ### 5. Few-Shot Examples Provide 2-5 diverse examples showing the pattern you want. ### 6. Role Assignment Give Claude a specific role or persona for appropriate context. ## Reference Materials All techniques, examples, and templates are available in the `references/` directory: - **core_techniques.md** - Essential techniques with examples - **advanced_techniques.md** - Advanced methods and optimization - **common_mistakes.md** - Pitfalls to avoid - **claude_4_best_practices.md** - Claude 4.x specific guidance - **prompt_templates.md** - Ready-to-use templates ## Usage Examples ### Example 1: Generate a Data Extraction Prompt Create a prompt that extracts names, emails, and phone numbers from business cards. ### Example 2: Improve a Vague Prompt Transform "Write about machine learning" into a structured, effective prompt. ### Example 3: Debug a Failing Prompt Fix inconsistent outputs by adding structure, examples, and format specification. ## Best Practices Checklist - [ ] Instructions are clear and specific - [ ] Output format is explicitly defined - [ ] Examples align with desired behavior - [ ] XML tags separate different sections - [ ] Context is minimal but sufficient - [ ] Edge cases are addressed - [ ] Tested on diverse inputs - [ ] Token usage is optimized ## Key Principles 1. **Empirical Approach** - Test, measure, iterate 2. **Context as Resource** - Every token counts 3. **Clarity Over Cleverness** - Explicit instructions work best 4. **Examples Teach Best** - Show, don't just tell 5. **Structure Helps** - Organization reduces confusion 6. **Iteration Improves** - Refine based on results ## Summary Master prompt engineering to create: - Reliable and consistent outputs - Production-ready prompts - Token-efficient solutions - Easy to maintain systems Apply Anthropic's proven techniques for best results. --- **Remember:** Good prompts are engineered, not guessed.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.