prompt-engineer

Files (174)

• CLAUDE.md
• README.md
• SKILL.md
• .gitattributes · papers/
• CATEGORY_DESCRIPTIONS.md · papers/
• CLAUDE.md · papers/
• README.md · papers/
• CLAUDE.md · papers/context/
• 2021-01-17 What Makes Good In-Context Examples for GPT-3.md · papers/context/augmentation/
• 2022-09-28 Generated Knowledge Prompting for Commonsense Reasoning.md · papers/context/augmentation/
• 2023-07-14 Unified Demonstration Retriever for In-Context Learning.md · papers/context/augmentation/
• 2023-10-21 Universal Self-Adaptive Prompting.md · papers/context/augmentation/
• 2023-12-10 Finding Support Examples for In-Context Learning.md · papers/context/augmentation/
• 2024-06-23 Diverse Demonstrations Improve In-context Compositional Generalization.md · papers/context/augmentation/
• CLAUDE.md · papers/context/augmentation/
• 2022-10-20 Rethinking the Role of Demonstrations - What Makes In-Context Learning Work.md · papers/context/reframing/
• 2023-10-23 Context-faithful Prompting for Large Language Models.md · papers/context/reframing/
• 2023-11-12 Large Language Models Understand and Can Be Enhanced by Emotional Stimuli.md · papers/context/reframing/
• 2024-02-18 An Empirical Categorization of Prompting Techniques for Large Language Models - A Practitioner's Guide.md · papers/context/reframing/
• 2024-03-14 Better Zero-Shot Reasoning with Role-Play Prompting.md · papers/context/reframing/
• 2024-04-08 Customizing Language Model Responses with Contrastive In-Context Learning.md · papers/context/reframing/
• 2024-04-18 Rephrase and Respond - Let Large Language Models Ask Better Questions for Themselves.md · papers/context/reframing/
• 2024-06-20 Devil's Advocate - Anticipatory Reflection for LLM Agents.md · papers/context/reframing/
• 2024-06-24 Mirror - A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning.md · papers/context/reframing/
• 2024-08-08 Conversational Prompt Engineering.md · papers/context/reframing/
• 2024-09-28 Code Prompting Elicits Conditional Reasoning Abilities in Text and Code LLMs.md · papers/context/reframing/
• 2024-10-09 When A Helpful Assistant Is Not Really Helpful - Personas in System Prompts Do Not Improve Performances of Large Language Models.md · papers/context/reframing/
• 2024-10-16 Lets Argue Both Sides - Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities.md · papers/context/reframing/
• 2024-11-01 Multi-expert Prompting Improves Reliability Safety and Usefulness of Large Language Models.md · papers/context/reframing/
• 2024-12-03 Take a Step Back - Evoking Reasoning via Abstraction in Large Language Models.md · papers/context/reframing/
• 2025-02-17 Large Language Models are Contrastive Reasoners.md · papers/context/reframing/
• 2025-03-05 ExpertPrompting - Instructing Large Language Models to be Distinguished Experts.md · papers/context/reframing/
• 2025-08-27 Principled Personas - Defining and Measuring the Intended Effects of Persona Prompting on Task Performance.md · papers/context/reframing/
• CLAUDE.md · papers/context/reframing/
• claude-prompt-engineering.md · papers/context/reframing/
• CLAUDE.md · papers/correctness/
• 2024-06-01 Prompt Chaining or Stepwise Prompt - Refinement in Text Summarization.md · papers/correctness/refinement/
• 2024-10-01 Iteration of Thought - Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning.md · papers/correctness/refinement/
• 2024-10-07 Progressive-Hint Prompting Improves Reasoning in Large Language Models.md · papers/correctness/refinement/
• 2024-10-17 Think Thrice Before You Act - Progressive Thought Refinement in Large Language Models.md · papers/correctness/refinement/
• 2025-02-11 Self-Harmonized Chain of Thought.md · papers/correctness/refinement/
• 2025-03-25 Think Twice- Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking.md · papers/correctness/refinement/
• CLAUDE.md · papers/correctness/refinement/
• 2022-03-03 Fantastically Ordered Prompts and Where to Find Them - Overcoming Few-Shot Prompt Order Sensitivity.md · papers/correctness/sampling/
• 2022-07-02 Rationale-Augmented Ensembles in Language Models.md · papers/correctness/sampling/
• 2023-01-30 Complexity-Based Prompting for Multi-Step Reasoning.md · papers/correctness/sampling/
• 2023-02-01 Synthetic Prompting - Generating Chain-of-Thought Demonstrations for Large Language Models.md · papers/correctness/sampling/
• 2023-03-07 Self-Consistency Improves Chain of Thought Reasoning in Language Models.md · papers/correctness/sampling/
• 2023-03-31 Fairness-guided Few-shot Prompting for Large Language Models.md · papers/correctness/sampling/
• 2023-04-12 Boosted Prompt Ensembles for Large Language Models.md · papers/correctness/sampling/
• 2023-08-23 PREFER - Prompt Ensemble Learning via Feedback-Reflect-Refine.md · papers/correctness/sampling/
• 2023-08-24 Answering Questions by Meta-Reasoning over Multiple Chains of Thought.md · papers/correctness/sampling/
• 2023-10-20 Getting MoRE out of Mixture of Language Model Reasoning Experts.md · papers/correctness/sampling/
• 2023-10-23 Self-ICL - Zero-Shot In-Context Learning with Self-Generated Demonstrations.md · papers/correctness/sampling/
• 2023-11-29 Universal Self-Consistency for Large Language Model Generation.md · papers/correctness/sampling/
• 2023-12-03 Tree of Thoughts- Deliberate Problem Solving with Large Language Models.md · papers/correctness/sampling/
• 2024-02-23 Diversity of Thought Improves Reasoning Abilities of LLMs.md · papers/correctness/sampling/
• 2024-05-23 Reprompting - Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling.md · papers/correctness/sampling/
• 2024-07-02 Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency.md · papers/correctness/sampling/
• 2024-07-21 Active Prompting with Chain-of-Thought for Large Language Models.md · papers/correctness/sampling/
• …and 114 more

SKILL.md (first lines)

# Prompt Engineer

Run the script before analyzing and follow its output; it runs the optimization
workflow.

## Invocation

Start with step 1 (triage) to determine scope:

<invoke working-dir=".claude/skills/scripts" cmd="uv run python -m skills.prompt_engineer.optimize --step 1" />

Then continue with determined scope:

<invoke working-dir=".claude/skills/scripts" cmd="uv run python -m skills.prompt_engineer.optimize --step 2 --scope <scope>" />

| Argument  | Required | Description                                      |
| --------- | -------- | ------------------------------------------------ |
| `--step`  | Yes      | Current step (1 = triage, 2 onward = workflow)   |
| `--scope` | For 2+   | Required from step 2 on. Determined by step 1.   |

### Scopes

- **single-prompt**: One prompt file, general optimization
- **ecosystem**: Multiple related prompts that interact
- **greenfield**: No existing prompt, designing from requirements
- **problem**: Existing prompt(s) with specific issue to fix

From gcharang/claude-config, MIT.

More from gcharang/claude-config