convez.ai
MCP ServerProdutividadeIntermediário
ramzi-bouzaiene

Claude Tips, Tricks & Hidden Features

ramzi-bouzaiene/claude-tips-and-tricks

Dicas e truques técnicos para dominar Claude ao máximo

Ver no GitHub
InicialPluginScore · de 0 a 100

Coleção colaborativa comunitária com dicas avançadas, truques pouco documentados, templates de prompts e snippets de código para potencializar o uso de Claude. Inclui técnicas de prompting, padrões agentic, boas práticas de API e macetes do Claude.ai.

Instalação

$npx convez-ai ramzi-bouzaiene/claude-tips-and-tricks

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
6
Forks
2
Acompanhando
0
Saúde
57%
Último commit
há 8 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Otimizar prompts complexos e chain-of-thought
  • Implementar workflows agentic e tool use eficientes
  • Reutilizar templates de sistema e tarefas estruturadas
  • Explorar recursos ocultos e comportamentos não documentados

Veredito

Repositório prático e bem-organizado que documenta técnicas reais de prompting e uso avançado de Claude. Útil para devs e prompt engineers que querem ir além dos basics, embora dependente de manutenção comunitária para manter conteúdo atualizado e relevante.

README

A tradução para o português deste README ainda está na fila.

🧠 Claude Tips, Tricks & Hidden Features

Claude PRs Welcome License Stars Last Commit

A community-curated collection of tips, tricks, hidden features, prompt templates, and code snippets for getting the most out of Claude AI.

Tips & Tricks · Prompts · Scripts · Contribute


📖 Table of Contents


💡 Why This Repo?

Claude is one of the most capable AI assistants available — but most people only scratch the surface of what it can do. This repo collects battle-tested tips, undocumented behaviors, clever prompting patterns, and reusable scripts from the community.

Whether you're a developer calling the API, a power user using Claude.ai, or a prompt engineer crafting complex workflows — there's something here for you.


🎯 Tips & Tricks

Prompting Fundamentals

1. Use XML Tags to Structure Complex Prompts

Claude is trained to understand XML-style tags natively. Use them to separate context, instructions, examples, and data clearly.

<context>
You are an expert data analyst at a SaaS company.
</context>

<task>
Analyze the following churn data and identify the top 3 risk segments.
</task>

<data>
{{paste your data here}}
</data>

<format>
Return a markdown table with: Segment | Risk Score | Recommended Action
</format>

Why it works: Claude was trained with XML-structured prompts and processes tagged sections with higher fidelity than plain paragraphs.


2. Tell Claude What NOT to Do (Negative Constraints)

Positive instructions alone often leave too much room. Add explicit negative constraints.

Summarize this article.
- Do NOT use bullet points
- Do NOT include your own opinions
- Do NOT exceed 3 sentences

3. Ask for Step-by-Step Reasoning Before the Answer

Trigger chain-of-thought by asking Claude to reason first.

Before answering, think through this step by step. 
Show your reasoning, then give your final answer.

Question: [your question]

4. Use "Let's think about this carefully" for Hard Problems

This phrase consistently elicits more thorough, careful responses on complex topics compared to just asking the question directly.


5. Specify Your Audience Explicitly

Explain quantum entanglement to:
- A 10-year-old
- A physics undergrad  
- A quantum computing researcher

Claude will adjust vocabulary, depth, and examples for each.


Hidden Features

6. Claude Can Hold Persona Across a Full Conversation

Set a system prompt (or opening message) once and Claude will maintain consistent behavior throughout:

You are Alex, a brutally honest senior software engineer with 20 years of experience. 
You give direct feedback without sugarcoating. You value simplicity over cleverness. 
You speak in short, punchy sentences.

7. "Continue Exactly Where You Left Off"

When Claude's response gets cut off, use this exact phrase:

Continue exactly where you left off, starting from: "[last few words]"

This prevents Claude from summarizing or restarting.


8. Force JSON Output with Schema

Claude will reliably output structured JSON when you provide the schema:

Respond ONLY with valid JSON. No explanation, no markdown, no preamble.

Schema:
{
  "title": "string",
  "summary": "string (max 100 words)",
  "sentiment": "positive | neutral | negative",
  "tags": ["string"]
}

Analyze the following text: {{text}}

9. Use "The Magic Words" for Code

Adding these phrases dramatically improves code quality:

  • "Production-ready code only"
  • "Include error handling"
  • "Add inline comments explaining non-obvious logic"
  • "Follow [language] best practices and idioms"

10. Instruct Claude to Ask Clarifying Questions First

Before you begin, ask me the 3-5 most important clarifying questions 
that would affect your approach. Wait for my answers before proceeding.

Context & Memory Tricks

11. Create a "User Profile" in Your System Prompt

## About the user
- Name: [name]
- Role: Senior backend engineer
- Stack: Python, FastAPI, PostgreSQL, Redis
- Prefers: Concise answers, code examples over prose, no hand-holding
- Never: Use bullet points for explanations

12. Summarize and Carry Forward Long Conversations

When context is getting long, ask Claude to compress it:

Summarize everything we've discussed so far into a compact briefing 
I can paste at the start of a new conversation to continue seamlessly.

13. Use Projects on Claude.ai for Persistent Context

Claude.ai Projects let you set a persistent system prompt and upload reference documents that persist across all chats in that project. Great for: codebases, style guides, research corpora.


Output Formatting

14. Request Specific Document Formats

Format your response as:
- A Notion-ready document with H1/H2/H3 headers
- A Slack message (no markdown, casual tone, < 300 chars)
- A formal memo with To/From/Date/Subject/Body
- An RFC document with Motivation, Proposal, Alternatives, and Drawbacks sections

15. Control Response Length Precisely

  • "Answer in exactly 3 sentences."
  • "Keep your response under 150 words."
  • "Give me an exhaustive, comprehensive answer. Do not truncate."

16. Request Tables When Comparing Multiple Options

Compare these 5 database options across: Performance, Cost, Ease of Use, 
Scalability, and Community Support. Use a markdown table.

Agentic & Tool Use

17. Break Down Agentic Tasks with a Planning Step

I want you to [complex task]. 

First, create a detailed plan with numbered steps. 
Show me the plan and ask for my approval before executing anything.

18. Use Sub-Agent Patterns for Parallel Work

When using Claude via API in agentic settings, orchestrate multiple specialized Claude instances:

# See /scripts/python/parallel_subagents.py for full implementation
orchestrator = ClaudeOrchestrator()
results = await orchestrator.run_parallel([
    {"role": "researcher", "task": "Find competitor pricing"},
    {"role": "analyst",    "task": "Analyze our cost structure"},
    {"role": "writer",     "task": "Draft executive summary template"}
])

Claude.ai UI Tips

19. Keyboard Shortcuts

ActionShortcut
New chatCtrl/Cmd + Shift + O
Focus inputEsc then type
Submit messageEnter
New line in messageShift + Enter

20. Use the Artifacts Panel for Iterative Work

When Claude generates code, documents, or visualizations as Artifacts, you can:

  • Ask Claude to modify specific parts without rewriting the whole thing
  • Download the artifact directly
  • Share a link to the artifact (Claude.ai Pro)

21. Upload Files for Context

Claude.ai supports uploading PDFs, images, CSVs, code files, and more. You can:

  • Upload an entire codebase (as a ZIP or individual files)
  • Reference uploaded docs with "As described in the uploaded document..."
  • Upload screenshots for UI debugging

📚 Prompt Library

System Prompts

Pre-built system prompts for common use cases. See /prompts/system-prompts/

FileDescription
senior-engineer.mdCode review & technical mentorship persona
research-analyst.mdDeep research and synthesis
socratic-tutor.mdLearn anything via Socratic dialogue
editor.mdWriting coach and copy editor
product-manager.mdPRD writing, user story generation
devils-advocate.mdRed team your ideas and decisions

Task Prompts

Single-shot prompts for specific tasks. See /prompts/task-prompts/

FileDescription
summarize-paper.mdAcademic paper → structured summary
code-review.mdThorough code review with scoring
write-tests.mdGenerate comprehensive test suites
explain-codebase.mdOnboard to a new codebase fast
rewrite-email.mdPolish emails for any tone/audience
sql-from-english.mdNatural language → SQL queries

Chain Prompts

Multi-step prompt sequences for complex workflows. See /prompts/chain-prompts/

FileDescription
research-pipeline.md5-step deep research workflow
blog-post-writer.mdOutline → draft → edit → SEO
system-design.mdRequirements → architecture → tradeoffs

💻 Code Snippets & Scripts

Python

FileDescription
basic_chat.pyMinimal API chat loop
streaming_response.pyStream tokens as they generate
structured_output.pyForce JSON with Pydantic validation
parallel_subagents.pyRun multiple Claude calls in parallel
conversation_manager.pyMulti-turn conversation with context trimming
batch_processor.pyProcess files/rows with Claude in bulk

JavaScript / TypeScript

FileDescription
basic_chat.jsNode.js chat example
stream_to_ui.jsStream response to browser UI
tool_use.jsFunction/tool calling example

Bash

FileDescription
claude_ask.shOne-liner CLI wrapper
summarize_file.shPipe any file to Claude for summary

📡 Resources

Official


🤝 Contributing

Contributions are what make this repo valuable. Please read CONTRIBUTING.md before submitting.

Quick contribution guide:

  1. Fork this repo
  2. Create a branch: git checkout -b tip/your-tip-name
  3. Add your content following the templates
  4. Open a Pull Request

Every tip, prompt, and script should include:

  • A clear title and description
  • Why it works (the reasoning)
  • A concrete example

📄 License

MIT License — see LICENSE for details.


If this helped you, please ⭐ the repo and share it with others!

Ver o original no GitHub

Bom para