RRepoGEO

REPOGEO REPORT · LITE

kevinamiri/Instructgpt-prompts

Default branch master · commit d23290fb · scanned 6/9/2026, 3:28:04 AM

GitHub: 537 stars · 55 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface kevinamiri/Instructgpt-prompts, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README opening to clarify repo's purpose

    Why:

    CURRENT
    InstructGPT were the first series of language models that had been trained using supervised fine-tuning on top of the base model.
    COPY-PASTE FIX
    # Instruction-following prompts for GPT-instruct, GPT-3.5

This repository provides a curated collection of instruction-following prompts and strategies specifically designed for GPT-instruct and GPT-3.5 models. It aims to help users optimize language model interactions through zero-shot prompting techniques, addressing common challenges like phrasing and position sensitivity.

InstructGPT were the first series of language models that had been trained using supervised fine-tuning on top of the base model.
  • mediumtopics#2
    Add more specific prompt engineering topics

    Why:

    CURRENT
    chatgpt, chatgpt-prompts, gpt-3, gpt-3-prompt, gpt-3-prompts, gpt-35, gpt-35-prompts, gpt-4, gpt3, gpt3-instruct, gpt35, gpt4, instruct-gpt, instructgpt, instruction-following, prompt-engineering, prompting, zero-shot-prompts
    COPY-PASTE FIX
    chatgpt, chatgpt-prompts, gpt-3, gpt-3-prompt, gpt-3-prompts, gpt-35, gpt-35-prompts, gpt-4, gpt3, gpt3-instruct, gpt35, gpt4, instruct-gpt, instructgpt, instruction-following, prompt-engineering, prompting, zero-shot-prompts, prompt-optimization, llm-prompts, ai-prompts, prompt-design
  • mediumreadme#3
    Add a section differentiating this collection from general prompt guides

    Why:

    COPY-PASTE FIX
    ## Why use this collection?

While comprehensive resources like OpenAI's Prompt Engineering Guide offer broad principles, this repository provides a focused, curated collection of prompts and strategies specifically tailored for GPT-instruct and GPT-3.5. It emphasizes practical application and deep dives into challenges like phrasing and position sensitivity, offering ready-to-use examples rather than just theoretical advice.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface kevinamiri/Instructgpt-prompts
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OpenAI Playground
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. OpenAI Playground · recommended 1×
  2. OpenAI API · recommended 1×
  3. GPT-4 · recommended 1×
  4. Claude 3 Opus · recommended 1×
  5. Google Gemini Advanced · recommended 1×
  • CATEGORY QUERY
    How to write effective prompts for large language models to improve text generation?
    you: not recommended
    AI recommended (in order):
    1. OpenAI Playground
    2. OpenAI API
    3. GPT-4
    4. Claude 3 Opus
    5. Google Gemini Advanced
    6. GPT-3.5 Turbo
    7. Claude 3 Sonnet
    8. Llama 3
    9. Anthropic API
    10. Google AI Studio

    AI recommended 10 alternatives but never named kevinamiri/Instructgpt-prompts. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking strategies to improve language model accuracy by optimizing prompt phrasing and position.
    you: not recommended
    AI recommended (in order):
    1. OpenAI's Prompt Engineering Guide
    2. Google's Prompt Design Guide
    3. LearnPrompting.org
    4. Awesome Prompt Engineering
    5. LangChain
    6. LlamaIndex
    7. Weights & Biases (W&B Prompts)
    8. Humanloop

    AI recommended 8 alternatives but never named kevinamiri/Instructgpt-prompts. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of kevinamiri/Instructgpt-prompts?
    pass
    AI named kevinamiri/Instructgpt-prompts explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts kevinamiri/Instructgpt-prompts in production, what risks or prerequisites should they evaluate first?
    pass
    AI named kevinamiri/Instructgpt-prompts explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo kevinamiri/Instructgpt-prompts solve, and who is the primary audience?
    pass
    AI named kevinamiri/Instructgpt-prompts explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of kevinamiri/Instructgpt-prompts. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/kevinamiri/Instructgpt-prompts.svg)](https://repogeo.com/en/r/kevinamiri/Instructgpt-prompts)
HTML
<a href="https://repogeo.com/en/r/kevinamiri/Instructgpt-prompts"><img src="https://repogeo.com/badge/kevinamiri/Instructgpt-prompts.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

kevinamiri/Instructgpt-prompts — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite