awesome-chatgpt-search

---

name: awesome-chatgpt-search description: Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

Search the awesome-ChatGPT-repositories database for the user's query.

Instructions

Ground rules — they apply whether this skill was invoked explicitly or picked automatically:

• Present only repositories from the bundled data files, even when the list has just a few matches — then say so and suggest other keywords rather than filling the gap from elsewhere.
• Don't search the web or open repository pages to add or verify details (setup, license, activity) unless the user explicitly asks for that: the curated list is the source of truth here, and its star counts and descriptions are snapshots. Copy names, URLs, and star counts exactly as they appear in the records.
• The output templates in Steps 5b–7 are fixed: keep their Markdown headings (##, ###), field labels, and order, and don't restyle them (for example, turning the result list into a table or a prose summary).
• If the data files can't be read (for example, shell commands are blocked), say so and link https://github.com/taishi-i/awesome-ChatGPT-repositories instead of substituting other sources.

Step 1 — Interpret the query

The query is the text the user passed to this skill (the same skill runs in Claude Code, Codex, and other agents):

• Claude Code: the arguments of /awesome-chatgpt-search, appended at the end as ARGUMENTS: ….
• Codex and other agents: the user's message that invoked this skill ($awesome-chatgpt-search in Codex), minus the skill mention itself.

If there is no explicit query text, use the user's latest request.

Supported query modifiers:

• category:<name> — filter to one category
• language:<lang> — filter by programming language
• list categories or categories — skip to Step 5b
• Plain text — keyword search across all categories

The descriptions are in English, so convert non-English queries to English keywords before searching.

Examples: | User query | English keywords to search | |------------|---------------------------| | RAGを使ったチャットボット | RAG, retrieval, chatbot, vector | | 코드 생성 도구 (Korean) | code generation, copilot, autocomplete | | 中文问答系统 | chinese, QA, question answering | | outil de résumé (French) | summarization, summary, text | | LLMを使ったエージェント | agent, autonomous, LLM, tool use |

Keyword tips:

• Use stems, not full words. Substring match catches variants: embed → embedding/embeddings, retriev → retrieval/retrieve, classif → classification/classifier, generat → generation/generative, fine-tun → fine-tune/fine-tuning, summari → summarize/summarization, orchestrat → orchestrate/orchestration.
• Add domain-specific names. For common LLM/AI domains, include well-known tool or framework 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 | | Image / 画像生成 | image, vision, multimodal | dall-e, stable-diffusion, midjourney | | Voice / 音声 | voice, speech, audio, tts, asr | whisper, eleven |

• 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 is split into per-category files. Each file is a JSON array with one repo record per line, so you can grep for matches instead of reading whole files — this keeps token use low (a typical query pulls in a few dozen matching lines instead of hundreds of KB). Fields per record:

• u: GitHub URL · n: repository name · d: English 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)

File list (all under data/ next to this SKILL.md; six categories over ~200 entries are split a/b):

| 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 |

Which files to search — pick the minimum set that covers the query, then grep them (below):

Rule A — category: specified: grep only that category's file(s), skip routing below. Match the category name case-insensitively and accept common variants: cli/clis/command-line → CLIs · chatbot/bot/chatbots → Chatbots · browser/extension/browser-extension → Browser-extensions · prompt/prompts → Prompts · tutorial/tutorials → Tutorials · reimpl/reimplementation → Reimplementations · awesome/lists → Awesome-lists · open ai/openai → Openai. If the value matches no category, fall back to keyword routing (Rule C).

Rule B — list categories: skip the keyword search, jump to Step 5b.

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 file(s) only if there is a match. If multiple rows match, collect all their files (deduplicated). If no rows match, use the default: 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 those files for the keywords — do NOT read whole files into context (no Read tool, cat, or full-file dumps). Locate the data directory once — it is the data/ folder next to this SKILL.md:

• Claude Code: ${CLAUDE_SKILL_DIR}/data
• Codex and other agents: <directory of this SKILL.md>/data, built from the absolute path you loaded this SKILL.md from.

If that directory does not exist (unusual install), find it — the data directory is the folder that contains the printed file:

find "$PWD" "$HOME/.agents/skills" "$HOME/.claude/skills" "${CODEX_HOME:-$HOME/.codex}/skills" -type f -name repos-unity.json -path "*awesome-chatgpt-search*" 2>/dev/null | head -1

Shell variables may not persist between commands, so write the resolved absolute path in place of $DATA in the commands below.

Then grep the selected files for your Step 1 keywords and cap the output. Use -F (literal substring match — same semantics as the scoring step, and safe for keywords like c++ or .net) with one -e per keyword:

grep -ihF -e keyword1 -e keyword2 -e keyword3 "$DATA"/repos-nlp-a.json "$DATA"/repos-nlp-b.json | head -120

Each line of output is one repo record (a JSON object) that matched at least one keyword — score those lines directly in Step 4. This reads only the matching repos, not the whole files. Notes:

• If grep returns fewer than ~8 lines, broaden the keywords (add more general single-word stems or tool names from Step 1 — multi-word phrases rarely match) and re-run.
• If it returns the full head cap, your keywords are good; proceed.
• Only fall back to reading individual files if grep is unavailable.

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

Append a language filter to the grep pipeline (the l field holds the language, matched case-insensitively):

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

Step 4 — Score candidates

Using the English keywords from Step 1, compute a relevance score for each repo record returned by grep:

Text match score (case-insensitive, per keyword):

• Name (n) exact keyword match: +20 pts
• Name (n) contains keyword: +10 pts
• Description (d) contains keyword: +5 pts
• Topics (t) contains keyword: +3 pts
• Category (c) contains keyword: +2 pts

Popularity bonus (added once per item):

• If ns (normalized star score) is present: min(4, ns * 0.4)
• Otherwise: min(4, sc * 0.5)

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

Combined score = text_match + popularity_bonus + quality_bonus

Exclude items with text_match < 5 (catches only accidental partial hits). Collect top 20 candidates by combined score.

Step 5a — Re-rank with your judgment

Apply semantic judgment to produce the final ordered list of 10 results — fewer only when fewer candidates actually fit the query.

Re-rank by evaluating each candidate on:

1. Semantic centrality — how directly does this repo address the query's core intent?
2. Quality signal — higher sc means a richer, better-documented project.
3. Category fit — match the repo type to the implied need:
   • "build a chatbot / ボット" → prefer Chatbots, CLIs