writing-prompts
Use when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performance
npx skills add majiayu000/claude-skill-registry --skill writing-prompts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Defines a structured approach to crafting prompts for large language models to improve response quality, accuracy, and task performance. Emphasizes an iterative RED-GREEN-REFACTOR workflow, the use of system/role prompts, structured output formats, and reasoning guidance. Includes explicit constraints and testing practices, plus a library of techniques (system prompts, few-shot examples, chain-of-thought, XML/structured tags, output formatting, and safety guards).
How it works
The skill instructs the agent to:
- Follow an iterative process: Define Success Criteria, Test Baseline (RED), Draft Initial Prompt, Apply Techniques (GREEN), Test & Iterate, Refactor, and optimize for efficiency.
- Use System Prompts to establish persistent context and output rules; structure the user prompt with task description, context/constraints, input specification, and output format.
- Provide examples (2-5) demonstrating desired input-output patterns and edge cases; include both simple and complex scenarios.
- Incorporate reasoning techniques (Chain of Thought or XML-driven reasoning steps) to guide the model's thinking before producing final output.
- Apply constraints and safety guards to restrict output to the required schema and prevent disruptive actions.
- Optimize prompts for token efficiency and model-specific features (Anthropic/XML, GPT/JSON, Gemini capabilities).
When to use it
Use when designing prompts intended to maximize LLM performance across a range of tasks, especially for complex reasoning, role-adoption, and production-grade prompts. Also applicable for refining prompts that underperform or exhibit high variability.
What it can touch
- Mentions utilizing system prompts and structured outputs (JSON/XML).
- Encourages use of examples and multi-step reasoning instructions.
Caveats
- Emphasizes measurable success criteria and test methodology; outcomes depend on model behavior.
- Provides explicit constraints to avoid extraneous content and unrecognized formats.
- Content prescribes processes and templates, not guarantees of model performance.
# Writing Prompts ## Overview Prompt engineering is the systematic process of crafting effective prompts for large language models (LLMs) to achieve better, more reliable, and more targeted responses. This skill provides proven techniques for maximizing LLM capabilities through structured prompt design, iterative refinement, and model-specific optimization. **Core principle:** Great prompts are specific, contextual, and tested. They guide the model's reasoning process while leaving appropriate degrees of freedom for the task at hand. ## When to Use Use this skill when: - Creating initial prompts for new tasks with LLMs - Improving existing prompts that produce inconsistent or suboptimal results - Working with complex tasks requiring step-by-step reasoning - Needing LLMs to adopt specific roles or behaviors - Developing prompts for production applications - Debugging prompt-related issues in LLM interactions - Optimizing token usage while maintaining output quality - Adapting prompts across different LLM providers (Anthropic, GPT, Gemini, etc.) ## Core Pattern Follow this iterative RED-GREEN-REFACTOR process for prompt development: 1. **Define Success Criteria** (Write the Test): Cl
- Overview
- When to Use
- Core Pattern
- Fundamental Principles
- 1. Be Specific and Direct
- 2. Provide Sufficient Context
- 3. Match Freedom to Task Fragility
- 4. Show, Don't Just Tell
- 5. Guide the Reasoning Process
- Quick Reference
- Implementation
- Step 1: Establish Success Criteria (Write Your Test)
- Step 2: Test Baseline Behavior (RED)
- Step 3: Use System Prompts for Persistent Context
What does the writing-prompts skill do?
Use when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performance
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill writing-prompts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.