SkillAgentSearch skills...

awesome-chatgpt

Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.

Install / Use

npx skills add taishi-i/awesome-ChatGPT-repositories

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

90/100

Supported Platforms

Claude Code

Our assessment of awesome-chatgpt

awesome-chatgpt scores 90/100 on our quality scale, 370th of 950 AI & Machine Learning skills we index (top 39%).

Its Claude Commands is 8.8 KB long, well organised into 11 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.

With 3,261 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
20/20
Description
12/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so awesome-chatgpt is actively maintained.
  • Our last check on 2026-10-30 found the source still online.
  • It is released under the CC0-1.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

awesome-chatgpt compared with similar skills

All 4 of these similar skills score higher than awesome-chatgpt; compare them before choosing.

SkillScoreStarsUpdatedFormat
awesome-chatgpt (this skill)by taishi-i903.3k59d agoClaude Commands
claude-memby thedotmack100117.6ktodayCLAUDE.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
Understand-Anythingby Egonex-AI10092.8k1d agoCLAUDE.md

Frequently asked questions

How do I install awesome-chatgpt?
Run npx skills add taishi-i/awesome-ChatGPT-repositories. The install tabs above show the steps for each supported agent.
Which AI agents does awesome-chatgpt work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is awesome-chatgpt safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is CC0-1.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is awesome-chatgpt still maintained?
The repository was last updated about 2 months ago, so awesome-chatgpt is actively maintained.

Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.

The user's query is: $ARGUMENTS


Instructions

Step 1 — Interpret the query

Supported modifiers:

  • category:<name> — filter to one category
  • language:<lang> — filter by programming language
  • list categories / categories — show category list instead
  • Plain text — keyword search

The data descriptions are in English. Convert non-English queries to English keywords before searching.

Keyword tips:

  • Use stems, not full words. Substring match catches variants: embed → embedding/embeddings, retriev → retrieval/retrieve, fine-tun → fine-tune/fine-tuning, summari → summarize/summarization, classif → classification/classifier, orchestrat → orchestration/orchestrate.
  • Add domain-specific names. For common LLM/AI domains, include well-known tool names present in the database:

| Domain (query hint) | Stem keywords | Tool/library names to add | |---|---|---| | RAG / 検索拡張生成 | retriev, rag, embed, vector | langchain, llamaindex, haystack, faiss, chroma, pinecone | | Agent / エージェント | agent, autonom, orchestrat | autogpt, langchain, langgraph, crewai | | Fine-tuning / ファインチューニング | fine-tun, lora, peft, finetun | lora, peft, qlora | | Code generation / コード生成 | code, coding, copilot, autocomplet | copilot, codex, interpreter | | Chatbot / チャットボット | chat, bot, dialog, convers | discord, telegram, slack | | Prompt engineering | prompt, few-shot, chain-of-thought, jailbreak | promptflow, dspy | | Evaluation / 評価 | evaluat, benchmark, metric | evals, lm-eval, deepeval |

  • Aim for 3–6 keywords. Too few miss items; too many inflate low-quality partial matches.

Step 2 — Search the data files with grep

Data files are in plugins/awesome-chatgpt-search/data/ (relative to repo root / PWD). Each file is a JSON array with one repo record per line, so grep can pull only the matching repos instead of loading whole files (much lower token cost).

| Category | File(s) | |----------|---------| | Awesome-lists | repos-awesome-lists.json | | Prompts | repos-prompts.json | | Chatbots | repos-chatbots-a.json, repos-chatbots-b.json | | Browser-extensions | repos-browser-extensions-a.json, repos-browser-extensions-b.json | | CLIs | repos-clis-a.json, repos-clis-b.json | | Reimplementations | repos-reimplementations.json | | Tutorials | repos-tutorials.json | | NLP | repos-nlp-a.json, repos-nlp-b.json | | Langchain | repos-langchain.json | | Unity | repos-unity.json | | Openai | repos-openai-a.json, repos-openai-b.json | | Others | repos-others-a.json, repos-others-b.json |

Record fields: u (URL), n (name), d (description), c (category), l (language, optional), t (topics comma-separated, optional), sc (quality score 0–8), st (star count, optional), ns (normalized star score 0–10, optional).

Which files to search — pick only what the query needs:

Rule A — category: specified: grep only that category's file(s). Match the name case-insensitively and accept common variants (cli/clis → CLIs, chatbot/bot → Chatbots, browser/extension → Browser-extensions, prompt → Prompts, tutorial → Tutorials, reimpl → Reimplementations, awesome/lists → Awesome-lists). If it matches no category, fall back to keyword routing (Rule C).

Rule B — list categories: no file reads, jump straight to the output.

Rule C — keyword routing for general queries:

Use the English keywords from Step 1 (not the original query text) for routing. For each row below, check if any English keyword contains or matches the listed terms (case-insensitive substring). Use that row's files only if there is a match. Collect all matching rows' files (deduplicated). If no rows match, default to: repos-chatbots-a.json, repos-nlp-a.json, repos-openai-a.json, repos-others-a.json.

| If query mentions… | Search these files | |--------------------|-----------------| | chatbot, bot, chat, dialog, conversation, assistant, discord, slack | repos-chatbots-a.json, repos-chatbots-b.json | | RAG, retrieval, vector, embed, semantic, FAISS, Chroma, Pinecone, similarity, index | repos-nlp-a.json, repos-nlp-b.json, repos-langchain.json | | NLP, text, classify, classification, NER, POS, sentiment, translation, extraction, summariz | repos-nlp-a.json, repos-nlp-b.json | | agent, agentic, workflow, autonomous, orchestrat, tool use, function call, multi-agent | repos-others-a.json, repos-others-b.json, repos-langchain.json | | OpenAI, GPT-3, GPT-4, gpt4, gpt3, completion, fine-tun, API key, endpoint | repos-openai-a.json, repos-openai-b.json | | browser, extension, Chrome, Firefox, sidebar, popup, Tampermonkey | repos-browser-extensions-a.json, repos-browser-extensions-b.json | | CLI, terminal, shell, command-line, command line | repos-clis-a.json, repos-clis-b.json | | tutorial, learn, course, beginner, guide, example, cookbook, sample | repos-tutorials.json | | prompt, prompting, few-shot, chain-of-thought, jailbreak, injection | repos-prompts.json | | Unity, game engine, 3D, game development | repos-unity.json | | LangChain, LlamaIndex, Haystack, chain, index, LangGraph | repos-langchain.json | | lora, peft, qlora, finetun, fine-tuning, quantiz | repos-reimplementations.json, repos-nlp-a.json, repos-openai-a.json | | evaluat, benchmark, metric, assess, leaderboard | repos-nlp-a.json, repos-nlp-b.json, repos-others-a.json | | reimplement, from scratch, reproduce, train, training, PyTorch | repos-reimplementations.json | | awesome list, curated, collection, survey, compilation | repos-awesome-lists.json | | code, coding, IDE, VS Code, copilot, autocomplete, interpreter | repos-others-a.json, repos-others-b.json, repos-clis-a.json | | image, vision, multimodal, DALL-E, Stable Diffusion, drawing | repos-others-a.json, repos-nlp-a.json | | voice, speech, audio, TTS, ASR, Whisper | repos-others-a.json, repos-nlp-b.json |

Then grep the selected files for the keywords — do NOT Read whole files. Use -F (literal substring, safe for keywords like c++/.net) with one -e per keyword, and cap the output:

D=plugins/awesome-chatgpt-search/data
grep -ihF -e keyword1 -e keyword2 -e keyword3 "$D"/repos-nlp-a.json "$D"/repos-nlp-b.json | head -120

Each output line is one matching repo record (JSON object) — score those in Step 4. If grep returns fewer than ~8 lines, broaden the keywords and re-run.

Step 3 — Filter by language (if language:<lang> given)

Append a language filter to the grep pipeline (case-insensitive; the l field holds the language):

grep -ihF -e keyword1 -e keyword2 "$D"/repos-clis-a.json "$D"/repos-clis-b.json | grep -iF '"l":"<lang>"' | head -120

Step 4 — Score candidates

Per keyword (case-insensitive):

  • Name exact match: +20 pts
  • Name contains: +10 pts
  • Description contains: +5 pts
  • Topics contains: +3 pts
  • Category contains: +2 pts

Popularity bonus (once per item):

  • If ns present: min(4, ns * 0.4)
  • Otherwise: min(4, sc * 0.5)

Quality bonus (always): min(2, sc * 0.25)

Exclude items with text_match < 5. Take top 20 by combined score.

Step 5 — Re-rank and output

Apply semantic judgment: prefer repos that directly address the query's core intent, with the right category and higher quality score when otherwise tied.

Present up to 10 results:

## Search results for "$ARGUMENTS"

*(Searched for: keyword1, keyword2, ...)*

Found N result(s).

### 1. [name](url)
**Category:** category  ·  **Language:** language  ·  ⭐ {st} stars
Description.
*Topics: tag1, tag2*

Omit ⭐ stars if st is absent.

For list categories, present:

## Available categories

| Category | Count |
|----------|-------|
| Awesome-lists | 98 |
| Prompts | 190 |
| Chatbots | 383 |
| Browser-extensions | 257 |
| CLIs | 268 |
| Reimplementations | 42 |
| Tutorials | 21 |
| NLP | 425 |
| Langchain | 180 |
| Unity | 17 |
| Openai | 329 |
| Others | 477 |
| **Total** | **2,687** |

If no results, suggest alternate keywords and link to https://github.com/taishi-i/awesome-ChatGPT-repositories

Step 6 — Output use-case selection guide

After the search results, append a guide table to help users pick the right repo.

Match the heading and table language to the query language (e.g., Japanese query → Japanese heading and headers).

## Use-case Selection Guide

| Use case | Recommended | Score | Why |
|---|---|---|---|
| ... | [name](url) | sc=N | short reason |

Rules:

  • List 3–6 distinct use cases from the top results (different scenarios, not restatements of the query).
  • Select the single best repo per row from the top 10 results.
  • Score: show sc=N using the item's quality score.
  • Why: 10–15 words in the query language explaining the practical benefit.
  • Merge rows that map to the same repo; drop the weaker one.

Related Skills

View on GitHub
GitHub Stars3.3k
CategoryAI
Updated1mo ago
Forks471

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions