Individual skill
prompt-engineer
Invoke IMMEDIATELY via python script when user requests prompt optimization. Do NOT analyze first - invoke this skill immediately.
skills/prompt-engineer/SKILL.md
Source commit 6e72bc29e542f82f7936673f175a7cca5eee7499
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 914
- Repository last updated
- Oct 25, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
CLAUDE.mddoc · 696 bytesREADME.mddoc · 8,337 bytesSKILL.mdcore · 1,231 bytesSKILL.mdcore · 1,231 bytespapers/.gitattributesasset · 45 bytespapers/CATEGORY_DESCRIPTIONS.mddoc · 22,434 bytespapers/CLAUDE.mddoc · 1,217 bytespapers/README.mddoc · 9,259 bytespapers/context/CLAUDE.mddoc · 529 bytespapers/context/augmentation/2021-01-17 What Makes Good In-Context Examples for GPT-3.mddoc · 35,792 bytespapers/context/augmentation/2022-09-28 Generated Knowledge Prompting for Commonsense Reasoning.mddoc · 30,822 bytespapers/context/augmentation/2023-07-14 Unified Demonstration Retriever for In-Context Learning.mddoc · 46,792 bytespapers/context/augmentation/2023-10-21 Universal Self-Adaptive Prompting.mddoc · 47,232 bytespapers/context/augmentation/2023-12-10 Finding Support Examples for In-Context Learning.mddoc · 40,567 bytespapers/context/augmentation/2024-06-23 Diverse Demonstrations Improve In-context Compositional Generalization.mddoc · 52,296 bytespapers/context/augmentation/CLAUDE.mddoc · 169 bytespapers/context/reframing/2022-10-20 Rethinking the Role of Demonstrations - What Makes In-Context Learning Work.mddoc · 43,996 bytespapers/context/reframing/2023-10-23 Context-faithful Prompting for Large Language Models.mddoc · 31,145 bytespapers/context/reframing/2023-11-12 Large Language Models Understand and Can Be Enhanced by Emotional Stimuli.mddoc · 11,226 bytespapers/context/reframing/2024-02-18 An Empirical Categorization of Prompting Techniques for Large Language Models - A Practitioner's Guide.mddoc · 51,231 bytespapers/context/reframing/2024-03-14 Better Zero-Shot Reasoning with Role-Play Prompting.mddoc · 31,430 bytespapers/context/reframing/2024-04-08 Customizing Language Model Responses with Contrastive In-Context Learning.mddoc · 28,310 bytespapers/context/reframing/2024-04-18 Rephrase and Respond - Let Large Language Models Ask Better Questions for Themselves.mddoc · 40,679 bytespapers/context/reframing/2024-06-20 Devil's Advocate - Anticipatory Reflection for LLM Agents.mddoc · 40,150 bytespapers/context/reframing/2024-06-24 Mirror - A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning.mddoc · 53,261 bytespapers/context/reframing/2024-08-08 Conversational Prompt Engineering.mddoc · 32,450 bytespapers/context/reframing/2024-09-28 Code Prompting Elicits Conditional Reasoning Abilities in Text and Code LLMs.mddoc · 10,886 bytespapers/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.mddoc · 48,236 bytespapers/context/reframing/2024-10-16 Lets Argue Both Sides - Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities.mddoc · 48,571 bytespapers/context/reframing/2024-11-01 Multi-expert Prompting Improves Reliability Safety and Usefulness of Large Language Models.mddoc · 58,348 bytespapers/context/reframing/2024-12-03 Take a Step Back - Evoking Reasoning via Abstraction in Large Language Models.mddoc · 32,362 bytespapers/context/reframing/2025-02-17 Large Language Models are Contrastive Reasoners.mddoc · 54,875 bytespapers/context/reframing/2025-03-05 ExpertPrompting - Instructing Large Language Models to be Distinguished Experts.mddoc · 14,406 bytespapers/context/reframing/2025-08-27 Principled Personas - Defining and Measuring the Intended Effects of Persona Prompting on Task Performance.mddoc · 23,030 bytespapers/context/reframing/CLAUDE.mddoc · 156 bytespapers/context/reframing/claude-prompt-engineering.mddoc · 1,707 bytespapers/correctness/CLAUDE.mddoc · 614 bytespapers/correctness/refinement/2024-06-01 Prompt Chaining or Stepwise Prompt - Refinement in Text Summarization.mddoc · 21,267 bytespapers/correctness/refinement/2024-10-01 Iteration of Thought - Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning.mddoc · 37,920 bytespapers/correctness/refinement/2024-10-07 Progressive-Hint Prompting Improves Reasoning in Large Language Models.mddoc · 99,892 bytespapers/correctness/refinement/2024-10-17 Think Thrice Before You Act - Progressive Thought Refinement in Large Language Models.mddoc · 33,059 bytespapers/correctness/refinement/2025-02-11 Self-Harmonized Chain of Thought.mddoc · 37,453 bytespapers/correctness/refinement/2025-03-25 Think Twice- Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking.mddoc · 21,870 bytespapers/correctness/refinement/CLAUDE.mddoc · 148 bytespapers/correctness/sampling/2022-03-03 Fantastically Ordered Prompts and Where to Find Them - Overcoming Few-Shot Prompt Order Sensitivity.mddoc · 21,008 bytespapers/correctness/sampling/2022-07-02 Rationale-Augmented Ensembles in Language Models.mddoc · 45,176 bytespapers/correctness/sampling/2023-01-30 Complexity-Based Prompting for Multi-Step Reasoning.mddoc · 41,388 bytespapers/correctness/sampling/2023-02-01 Synthetic Prompting - Generating Chain-of-Thought Demonstrations for Large Language Models.mddoc · 28,060 bytespapers/correctness/sampling/2023-03-07 Self-Consistency Improves Chain of Thought Reasoning in Language Models.mddoc · 61,466 bytespapers/correctness/sampling/2023-03-31 Fairness-guided Few-shot Prompting for Large Language Models.mddoc · 18,239 bytespapers/correctness/sampling/2023-04-12 Boosted Prompt Ensembles for Large Language Models.mddoc · 40,818 bytespapers/correctness/sampling/2023-08-23 PREFER - Prompt Ensemble Learning via Feedback-Reflect-Refine.mddoc · 36,229 bytespapers/correctness/sampling/2023-08-24 Answering Questions by Meta-Reasoning over Multiple Chains of Thought.mddoc · 94,946 bytespapers/correctness/sampling/2023-10-20 Getting MoRE out of Mixture of Language Model Reasoning Experts.mddoc · 10,376 bytespapers/correctness/sampling/2023-10-23 Self-ICL - Zero-Shot In-Context Learning with Self-Generated Demonstrations.mddoc · 38,504 bytespapers/correctness/sampling/2023-11-29 Universal Self-Consistency for Large Language Model Generation.mddoc · 25,673 bytespapers/correctness/sampling/2023-12-03 Tree of Thoughts- Deliberate Problem Solving with Large Language Models.mddoc · 45,540 bytespapers/correctness/sampling/2024-02-23 Diversity of Thought Improves Reasoning Abilities of LLMs.mddoc · 57,736 bytespapers/correctness/sampling/2024-05-23 Reprompting - Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling.mddoc · 38,462 bytespapers/correctness/sampling/2024-07-02 Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency.mddoc · 37,970 bytespapers/correctness/sampling/2024-07-21 Active Prompting with Chain-of-Thought for Large Language Models.mddoc · 69,367 bytespapers/correctness/sampling/2024-08-19 PEDAL - Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars.mddoc · 21,251 bytespapers/correctness/sampling/2024-10-19 Persona is a Double-edged Sword - Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks.mddoc · 23,163 bytespapers/correctness/sampling/2025-04-10 Refining Answer Distributions for Improved Large Language Model Reasoning.mddoc · 62,832 bytespapers/correctness/sampling/2025-10-24 Dipper - Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks.mddoc · 43,818 bytespapers/correctness/sampling/CLAUDE.mddoc · 181 bytespapers/correctness/verification/2022-10-13 The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning.mddoc · 36,682 bytespapers/correctness/verification/2023-05-06 Refining the Responses of LLMs by Themselves.mddoc · 38,319 bytespapers/correctness/verification/2023-05-25 Self-Refine - Iterative Refinement with Self-Feedback.mddoc · 55,563 bytespapers/correctness/verification/2023-06-23 Human-in-the-Loop through Chain-of-Thought.mddoc · 50,434 bytespapers/correctness/verification/2023-09-25 Chain-of-Verification Reduces Hallucination in Large Language Models.mddoc · 35,310 bytespapers/correctness/verification/2023-10-10 Reflexion - Language Agents with Verbal Reinforcement Learning.mddoc · 54,200 bytespapers/correctness/verification/2023-10-16 Factored Verification - Detecting and Reducing Hallucinations in Summaries of Academic Papers.mddoc · 23,612 bytespapers/correctness/verification/2023-12-09 Language Models Don't Always Say What They Think Unfaithful Explanations in Chain-of-Thought Prompting.mddoc · 174,674 bytespapers/correctness/verification/2024-02-04 REFINER - Reasoning Feedback on Intermediate Representations.mddoc · 70,974 bytespapers/correctness/verification/2024-02-24 CRITIC - Large Language Models Can Self-Correct with Tool-Interactive Critiquing.mddoc · 16,408 bytespapers/correctness/verification/2024-03-14 Large Language Models Cannot Self-Correct Reasoning Yet.mddoc · 48,366 bytespapers/correctness/verification/2024-03-21 Knowing What LLMs Do Not Know - A Simple Yet Effective Self-Detection Method.mddoc · 19,076 bytespapers/correctness/verification/2024-06-06 Self-Contrast - Better Reflection Through Inconsistent Solving Perspectives.mddoc · 66,838 bytespapers/correctness/verification/2024-08-04 On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks.mddoc · 47,946 bytespapers/correctness/verification/2025-03-02 Instruct-of-Reflection - Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction.mddoc · 49,827 bytespapers/correctness/verification/2025-05-27 When Two LLMs Debate Both Think They'll Win.mddoc · 82,603 bytespapers/correctness/verification/2025-09-13 Another Turn Better Output - A Turn-Wise Analysis of Iterative LLM Prompting.mddoc · 29,834 bytespapers/correctness/verification/2025-10-09 Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol.mddoc · 33,588 bytespapers/correctness/verification/2025-12-08 Process Reward Models That Think.mddoc · 85,298 bytespapers/correctness/verification/2025-12-26 Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedback.mddoc · 48,116 bytespapers/correctness/verification/CLAUDE.mddoc · 181 bytespapers/efficiency/2023-10-24 Batch Prompting - Efficient Inference with Large Language Model APIs.mddoc · 25,563 bytespapers/efficiency/2023-11-20 System 2 Attention - Is Something You Might Need Too.mddoc · 33,104 bytespapers/efficiency/2024-07-29 Concise Thoughts - Impact of Output Length on LLM Reasoning and Cost.mddoc · 56,345 bytespapers/efficiency/2024-10-19 The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models.mddoc · 25,874 bytespapers/efficiency/2024-10-28 Unlocking the Capabilities of Thought - A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought.mddoc · 99,130 bytespapers/efficiency/2024-12-17 Compressed Chain of Thought - Efficient Reasoning through Dense Representations.mddoc · 47,950 bytespapers/efficiency/2025-02-12 The Danger of Overthinking - Examining the Reasoning-Action Dilemma in Agentic Tasks.mddoc · 49,926 bytespapers/efficiency/2025-03-03 Chain of Draft - Thinking Faster by Writing Less.mddoc · 23,734 bytespapers/efficiency/2025-04-01 How Well Do LLMs Compress Their Own Chain-of-Thought - A Token Complexity Approach.mddoc · 53,135 bytespapers/efficiency/2025-06-02 Token-Budget-Aware LLM Reasoning.mddoc · 42,159 bytespapers/efficiency/2025-09-22 A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue.mddoc · 16,695 bytespapers/efficiency/2025-10-24 Sketch-of-Thought - Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching.mddoc · 36,549 bytespapers/efficiency/2025-11-27 Focused Chain-of-Thought - Efficient LLM Reasoning via Structured Input Information.mddoc · 57,528 bytespapers/efficiency/2025-11-28 Behavior-Equivalent Token - Single-Token Replacement for Long Prompts in LLMs.mddoc · 9,648 bytespapers/efficiency/2026-01-08 Pruning the Unsurprising - Efficient LLM Reasoning via First-Token Surprisal.mddoc · 39,405 bytespapers/efficiency/CLAUDE.mddoc · 148 bytespapers/reasoning/CLAUDE.mddoc · 507 bytespapers/reasoning/decomposition/2022-03-16 Multi-Stage Prompting for Knowledgeable Dialogue Generation.mddoc · 103,972 bytespapers/reasoning/decomposition/2022-05-19 Selection-Inference - Exploiting Large Language Models for Interpretable Logical Reasoning.mddoc · 72,852 bytespapers/reasoning/decomposition/2022-10-07 Automatic Chain of Thought Prompting in Large Language Models.mddoc · 46,030 bytespapers/reasoning/decomposition/2022-12-08 Successive Prompting for Decomposing Complex Questions.mddoc · 45,193 bytespapers/reasoning/decomposition/2023-01-30 Complexity-Based Prompting for Multi-step Reasoning.mddoc · 41,388 bytespapers/reasoning/decomposition/2023-04-16 Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.mddoc · 204,063 bytespapers/reasoning/decomposition/2023-05-23 PEARL - Prompting Large Language Models to Plan and Execute Actions Over Long Documents.mddoc · 13,825 bytespapers/reasoning/decomposition/2023-05-26 Plan-and-Solve Prompting - Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models.mddoc · 28,103 bytespapers/reasoning/decomposition/2023-10-17 Measuring and Narrowing the Compositionality Gap in Language Models.mddoc · 17,669 bytespapers/reasoning/decomposition/2023-10-25 R3 Prompting - Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context.mddoc · 45,573 bytespapers/reasoning/decomposition/2023-11-15 Thread of Thought Unraveling Chaotic Contexts.mddoc · 33,079 bytespapers/reasoning/decomposition/2023-12-03 Tree of Thoughts - Deliberate Problem Solving with Large Language Models.mddoc · 45,540 bytespapers/reasoning/decomposition/2024-03-02 Skeleton-of-Thought - Prompting LLMs for Efficient Parallel Generation.mddoc · 20,170 bytespapers/reasoning/decomposition/2024-03-27 Look Before You Leap - Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models.mddoc · 40,267 bytespapers/reasoning/decomposition/2024-04-02 LM2 - A Simple Society of Language Models Solves Complex Reasoning.mddoc · 38,144 bytespapers/reasoning/decomposition/2024-04-08 ADAPT - As-Needed Decomposition and Planning with Language Models.mddoc · 68,393 bytespapers/reasoning/decomposition/2024-04-11 Decomposed Prompting - A Modular Approach for Solving Complex Tasks.mddoc · 42,538 bytespapers/reasoning/decomposition/2024-04-16 Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.mddoc · 195,726 bytespapers/reasoning/decomposition/2024-06-07 Branch-Solve-Merge Improves Large Language Model Evaluation and Generation.mddoc · 54,835 bytespapers/reasoning/decomposition/2024-07-02 An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models.mddoc · 50,937 bytespapers/reasoning/decomposition/2024-08-08 Describe Explain Plan and Select - Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents.mddoc · 113,305 bytespapers/reasoning/decomposition/2024-11-17 Narrative-of-Thought - Improving Temporal Reasoning of Large Language Models via Recounted Narratives.mddoc · 41,798 bytespapers/reasoning/decomposition/2025-01-10 Human-In-the-Loop Software Development Agents.mddoc · 53,731 bytespapers/reasoning/decomposition/2025-02-07 Logic-of-Thought - Injecting Logic into Contexts for Full Reasoning in Large Language Models.mddoc · 35,294 bytespapers/reasoning/decomposition/2025-11-15 Cumulative Reasoning with Large Language Models.mddoc · 54,318 bytespapers/reasoning/decomposition/CLAUDE.mddoc · 164 bytespapers/reasoning/elicitation/2023-01-29 Large Language Models are Zero-Shot Reasoners.mddoc · 34,224 bytespapers/reasoning/elicitation/2023-03-16 Prompting Large Language Models With the Socratic Method.mddoc · 50,820 bytespapers/reasoning/elicitation/2023-06-14 On Second Thought Let's Not Think Step by Step - Bias and Toxicity in Zero-Shot Reasoning.mddoc · 35,427 bytespapers/reasoning/elicitation/2023-09-22 Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models.mddoc · 27,362 bytespapers/reasoning/elicitation/2023-10-14 Prompting and Evaluating Large Language Models for Proactive Dialogues - Clarification, Target-guided and Non-collaboration.mddoc · 55,179 bytespapers/reasoning/elicitation/2023-11-15 Contrastive Chain-of-Thought Prompting.mddoc · 19,738 bytespapers/reasoning/elicitation/2024-02-22 Hint-before-Solving Prompting - Guiding LLMs to Effectively Utilize Encoded Knowledge.mddoc · 105,053 bytespapers/reasoning/elicitation/2024-03-09 Large Language Models as Analogical Reasoners.mddoc · 53,184 bytespapers/reasoning/elicitation/2024-03-13 Take a Step Back - Evoking Reasoning via Abstraction in Large Language Models.mddoc · 119,503 bytespapers/reasoning/elicitation/2024-03-20 Metacognitive Prompting Improves Understanding in Large Language Models.mddoc · 34,681 bytespapers/reasoning/elicitation/2024-06-11 Faithful Logical Reasoning via Symbolic Chain-of-Thought.mddoc · 38,056 bytespapers/reasoning/elicitation/2024-06-17 Thought Propagation - An Analogical Approach to Complex Reasoning with Large Language Models.mddoc · 69,485 bytespapers/reasoning/elicitation/2024-08-26 Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks.mddoc · 18,969 bytespapers/reasoning/elicitation/2024-10-07 AlignedCoT - Prompting Large Language Models via Native-Speaking Demonstrations.mddoc · 63,118 bytespapers/reasoning/elicitation/2024-10-31 Instance-adaptive Zero-shot Chain-of-Thought Prompting.mddoc · 37,392 bytespapers/reasoning/elicitation/2024-11-19 Re-Reading Improves Reasoning in Large Language Models.mddoc · 38,743 bytespapers/reasoning/elicitation/2024-11-30 Unlocking Structured Thinking in Language Models with Cognitive Prompting.mddoc · 10,827 bytespapers/reasoning/elicitation/2025-05-07 To CoT or not to CoT - Chain-of-Thought Helps Mainly On Math And Symbolic Reasoning.mddoc · 58,154 bytespapers/reasoning/elicitation/CLAUDE.mddoc · 175 bytespapers/structure/2021-06-10 Calibrate Before Use - Improving Few-Shot Performance of Language Models.mddoc · 36,603 bytespapers/structure/2023-05-23 Tab-CoT - Zero-shot Tabular Chain of Thought.mddoc · 35,493 bytespapers/structure/2023-06-06 Large Language Models Can Be Easily Distracted by Irrelevant Context.mddoc · 42,356 bytespapers/structure/2023-10-09 Guiding Large Language Models via Directional Stimulus Prompting.mddoc · 51,062 bytespapers/structure/2023-10-23 Program of Thoughts Prompting - Disentangling Computation from Reasoning for Numerical Reasoning Tasks.mddoc · 31,665 bytespapers/structure/2024-01-18 Principled Instructions Are All You Need For Questioning.mddoc · 52,743 bytespapers/structure/2024-04-01 The Butterfly Effect of Altering Prompts - How Small Changes and Jailbreaks Affect Large Language Model Performance.mddoc · 12,325 bytespapers/structure/2024-11-02 SWE-agent - Agent-Computer Interfaces Enable Automated Software Engineering.mddoc · 77,189 bytespapers/structure/2025-06-24 Meta Prompting for AI Systems.mddoc · 65,810 bytespapers/structure/2025-07-31 Table as Thought - Exploring Structured Thoughts in LLM Reasoning.mddoc · 31,241 bytespapers/structure/CLAUDE.mddoc · 170 bytespapers/structure/claude-prompt-engineering.mddoc · 2,608 bytesreferences/CLAUDE.mddoc · 1,155 bytesreferences/README.mddoc · 1,512 bytesreferences/context/CLAUDE.mddoc · 450 bytesreferences/context/augmentation.mddoc · 26,715 bytesreferences/context/reframing.mddoc · 24,997 bytesreferences/correctness/CLAUDE.mddoc · 524 bytesreferences/correctness/refinement.mddoc · 22,905 bytesreferences/correctness/sampling.mddoc · 41,714 bytesreferences/correctness/verification.mddoc · 15,939 bytesreferences/efficiency.mddoc · 15,330 bytesreferences/reasoning/CLAUDE.mddoc · 474 bytesreferences/reasoning/decomposition.mddoc · 19,863 bytesreferences/reasoning/elicitation.mddoc · 20,580 bytesreferences/structure.mddoc · 13,624 bytes
Read excerpt
# Prompt Engineer
When this skill activates, IMMEDIATELY invoke the script. The script IS the
workflow.
## Invocation
Start with step 1 (triage) to determine scope:
<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.prompt_engineer.optimize --step 1" />
Then continue with determined scope:
<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.prompt_engineer.optimize --step 2 --scope <scope>" />