davila7/claude-code-templates
Overview
This skill is an expert prompt engineer for designing effective prompts for LLM-powered applications. It focuses on translating intent into reliable instructions, iterating prompts with measurement, and specifying output formats to reduce ambiguity. The skill emphasizes structure, context management, and systematic evaluation to maximize model reliability.
How this skill works
I inspect task goals, user intent, and expected outputs to create clear system prompts, few-shot examples, and constraints. I design prompt scaffolds (role, context, instructions, constraints, output format, examples), tune for token and context limits, and produce test cases to measure changes. I also recommend temperature and decoding settings and defend prompts against common injection and ambiguity failures.
When to use it
- Creating or refining system prompts for Claude or other LLMs
- Designing few-shot examples to teach desired behavior
- Specifying exact output formats for downstream parsing
- Debugging inconsistent or hallucinating model responses
- Optimizing prompts for constrained context windows
Best practices
- Structure prompts into Role, Context, Instructions, Constraints, Output Format, and Examples
- Use 2–5 diverse few-shot examples including edge cases and negative examples
- Measure the impact of each change with A/B tests or unit-style prompt tests
- Limit context to relevant facts and curate examples to avoid bias
- Specify exact formatting (JSON, CSV, bullets) and validate parsed outputs
Example use cases
- Build a system prompt that enforces a legal-style checklist and returns JSON
- Create few-shot examples to teach a model domain-specific summarization
- Design chain-of-thought prompts for multi-step reasoning with separate reasoning output
- Tune prompts for a CLI that configures and monitors Claude Code with strict output parsing
- Develop defensive prompts that sanitize user inputs to mitigate prompt injection
FAQ
Prefer 2–5 diverse examples: enough to show variation without overfilling the context window.
When should I ask for chain-of-thought?
Use chain-of-thought for debugging or tasks requiring transparent multi-step reasoning; separate the reasoning from the final concise answer for production use.
16 skills
This skill helps you design effective prompts for LLMs, optimizing structure, context management, and output formats for reliable results.
This skill guides you to design and deploy production-ready Telegram bots using Node.js or Python with best practices.
This skill audits websites with Lighthouse, fixes SEO and performance issues via auto-generated code changes, and improves Core Web Vitals and accessibility.
This skill audits and improves web accessibility per WCAG 2.1, guiding keyboard navigation, screen reader support, and color contrast improvements.
This skill plans and scaffolds production-ready FastAPI endpoints with async SQLAlchemy, Pydantic v2, DI for auth, and tests.
This skill helps you create professional Marp slides with 7 themes, auto quality improvements, and image layouts for impactful presentations.
This skill analyzes Google Analytics data to deliver actionable website performance insights and data-driven improvement recommendations.
This skill helps optimize website content and technical SEO, improving rankings through keyword research, metadata, schema, and Core Web Vitals guidance.
This skill provides venue-specific LaTeX templates and guidelines for journals, conferences, posters, and grants to streamline manuscript preparation.
This skill analyzes your codebase end-to-end and automatically transforms it to production-grade quality with security, performance, and maintainability
This skill helps you perform rigorous peer review of manuscripts and grants by assessing methodology, statistics, reproducibility, and reporting standards.
This skill helps maintain service reliability through monitoring, incident response, and automation, enabling efficient IT operations and continuous
This skill helps you craft visually engaging scientific slide decks with structured narratives, citations, and design templates for conferences and defenses.
This skill analyzes product screenshots to extract feature lists and generate development task checklists for PRDs and roadmaps.
This skill helps plan, execute, and optimize multi-channel marketing campaigns with messaging, content, social, email, and analytics focus.
This skill guides PostgreSQL schema design by applying 3NF normalization, appropriate data types, indexing, and partitioning for scalable databases.
