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-darthlinuxer-agentic-skills --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
Guides the agent to design prompts for large language models to improve quality, accuracy, consistency, and task performance. Emphasizes an iterative RED-GREEN-REFACTOR process and structured output practices.
How it works
Describes a step-by-step prompt engineering workflow: establish success criteria, test baseline, use system prompts for persistent context, structure the user prompt, add examples (few-shot), incorporate reasoning techniques (chain of thought or structured XML), add constraints and safety guards, test and iterate, then refactor for efficiency. It includes concrete example formats (JSON/XML sketches), and model-specific optimization tips. It also provides a quick-reference of techniques (System Prompts, Role Prompting, Chain of Thought, Few-Shot Prompting, etc.) and a set of common mistakes to avoid.
When to use it
Applicable when creating initial prompts, improving prompts with inconsistent results, handling complex tasks requiring step-by-step reasoning, assigning specific roles or behaviors, developing prompts for production use, debugging prompt issues, optimizing token usage, and adapting prompts across different LLM providers.
What it can touch
Mentions interaction with multiple prompt components and outputs, including JSON and XML formats, examples, and structured outputs. It references system prompts, role prompts, few-shot examples, and structured reasoning constructs. (Note: The skill itself prescribes creating and using these elements; no external tools or file references are invoked directly in this description.)
Caveats
Highlights need for explicit constraints to prevent extraneous text, graceful handling of unrecognizable inputs (default to LOW severity and manual review), and the risk of over-constraining simple tasks. Emphasizes iterative testing and model-specific adjustments to avoid generic prompts that underperform across models.
# 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 (Claude, GPT, Gemini, etc.) ## Core Pattern Follow this iterative RED-GREEN-REFACTOR process for prompt development: 1. **Define Success Criteria** (Write the Test): Clear
- 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-darthlinuxer-agentic-skills --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.