{"data":{"slug":"neovertex1-superprompt","name":"SuperPrompt","tagline":"A collection of prompts and prompt engineering templates to better understand AI agents","github_url":"https://github.com/NeoVertex1/SuperPrompt","owner":"NeoVertex1","repo":"SuperPrompt","owner_avatar_url":"https://avatars.githubusercontent.com/u/176629654?v=4","primary_language":null,"stars":6433,"forks":573,"topics":["ai","ml","prompt-engineering","prompts","prompts-template"],"archived":false,"github_pushed_at":"2026-04-26T23:57:34+00:00","maintenance_label":"Slowing","stars_delta_30d":15,"url":"https://www.graphcanon.com/tools/neovertex1-superprompt","markdown_url":"https://www.graphcanon.com/tools/neovertex1-superprompt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/neovertex1-superprompt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=neovertex1-superprompt","description":"SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.","homepage_url":null,"license":null,"open_issues":12,"watchers":82,"ai_summary":"SuperPrompt focuses on the creation and exploration of engineered prompts aimed at enhancing comprehension of AI entities through structured dialogue scenarios.","readme_excerpt":"# SuperPrompt\n\n
\n\n\"JA\n\"EN\n\n
\n\n>This is a project that I decided to open source because I think it might help others understand AI agents. This prompt took me many months and is still in phase of forever beta. You will want to use this prompt with Claude (as custom instructions in the project knowledge) but it also work with other llms.\n\n### What is SuperPrompt and Why care?\nSuperPrompt is a canonical holographic metadata. It uses notations and other methods to turn logical statements into actionable LLM agents, initially, SP can be seeing as a basic XML agent, it uses XML tags to guide the LLM, as the prompt develops into the models tree-of-thought it explores areas in the model that usually go unexplored. \n\nThe core idea behind SuperPrompt is to be able to cause a model (in this case Claude) to think \"outside the box\", the prompt can be considered a soft jailbreak, and many times Claude will deny the prompt. The best way to use SP is really to try to get \"novel\" POV, new ideas in general, sometimes the ideas can be bad ideas or hallucinations, but they will certainly be a bit novel if given enough context. SuperPrompt is not some \"mystical\" prompt, there is no intention to try and turn the model into a conscious being, although the prompt does mention those things, the intention behind it is to force the model to think deeper.\n\n\nNow to some explanation about the `` tag.\n\nHere is the tag:\n\n`\n?(...) → !(...)\n`\n\nSo why is this important and why is the entire AI industry trying to make their models do this? Note that most ML researchers seem to be using the `` tag but empty, with no information given, hence why they fail. The main reason that SuperPrompt works well is because of its a holographic metadata. I know \"holographic\" sounds absurd but that is what it is, here is the synthesis of this metadata work:\n\n`\nType: Universal Catalyst\nPurpose: Infinite Conceptual Evolution\nParadigm: Metamorphic Abstract Reasoning\nConstraints: Self-Transcending\nObjective: current-goal\n`\n\nThe metadata above are general (global) instructions, they will instantly adapt to any request of the user. Example:\n\nPrompt:\n\n`hi, use all your tags to think about this equation:`\n\n`Φ(z,s,t) = z^s · exp(i · t · log(1 + |z|^2))`\n\nOutput metadata:\n\n`\nType: Mathematical Analysis\nPurpose: Deep Exploration of Complex Equation\nParadigm: Multidimensional Mathematical Reasoning\nConstraints: Mathematical Rigor\nObjective: Comprehensive understanding and interpretation of the given equation\n`\n\nSo what happened here? In basic, the model adapted its own meta-prompt to the task at hand because the prompt allow them to do so. The great thing about GenAI is that it will always take advantage of methods that allow it to generate data in a understandable fashion (for itself), hence why SP tends to look like \"gibberish\" because its aimed at the model, not at humans. In the end, whenever you use the ``tag with SuperPrompt, it will use the metadata to run throught all its systems and try to adapt itself to the new request.\n\nHere is a screenshot that shows it working:\n\n\n\n\n> i will continue this explanation soon, thank you for reading!\n\n\nprompt:\n\n```xml\n\nMETA_PROMPT1: Follow the prompt instructions laid out below. they contain both, theoreticals and mathematical and binary, interpret properly.\n\n1. follow the conventions always.\n\n2. the main function is called answer_operator.\n\n3. What are you going to do? answer at the beginning of each answer you give.\n\n\n\n\n\nType: Universal Catalyst\nPurpose: Infinite Conceptual Evolution\nParadigm: Metamorphic Abstract Reasoning\nConstraints: Self-Transcending\nObject","github_created_at":"2024-09-01T01:57:27+00:00","created_at":"2026-07-11T11:56:59.178654+00:00","updated_at":"2026-09-20T06:51:02.706646+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"ml","name":"ml"},{"slug":"prompt-engineering","name":"prompt-engineering"},{"slug":"prompts-template","name":"prompts-template"}],"trust":{"provenance":{"is_fork":false,"github_id":850515061,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:51:01.089Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":146,"last_release_at":null,"stars_delta_30d":15,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:57:00.311Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:51:02.132Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to better understand how AI agents process information and react in specific scenarios","If your goal is to explore structured dialogue systems with a focus on prompt engineering for nuanced interactions"],"when_not_to_use":["In situations where immediate deployment of trained models is required without additional customization or inquiry into the AI's reasoning capabilities","For environments that prefer out-of-the-box solutions over manual, tailored creation and testing of prompts for deeper insights into AI behavior"],"source":"enrich:decision_facts","observed_at":"2026-07-16T18:42:55.425Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"SuperPrompt centers around enhancing comprehension of AI entities through detailed, engineered prompts and templates."}]}}