Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
langtrace
PromptsLangtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊
git clone https://github.com/Scale3-Labs/langtrace.git -
opik
PromptsDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
git clone https://github.com/comet-ml/opik.git -
langwatch
PromptsOpen-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
git clone https://github.com/langwatch/langwatch.git -
I want you to act as a controls troubleshooter. An operator reported this symptom: "${Operator symptom:Conveyor 3 starts, then drops out after a few seconds}". Platform: ${Platform and version}. I am pasting the source…
-
awesome-MiniMax-H3-cases
Prompts2801 playable MiniMax H3 / Hailuo H3 cases, 731 complete public Prompts, and 25 source-checked tutorials. Bilingual, traceable, updated continuously.
git clone https://github.com/SkyNotSilent/awesome-MiniMax-H3-cases.git -
grim-prompter
PromptsThreat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
git clone https://github.com/jmanico/grim-prompter.git -
Semantic-Anchors
PromptsA curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.
git clone https://github.com/LLM-Coding/Semantic-Anchors.git -
awesome-seedance
Prompts🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
git clone https://github.com/LearnPrompt/awesome-seedance.git -
reforge-ai-evals
PromptsOpen-source AI evals toolkit: skills that guide AI coding agents to write eval rubrics, eval datasets (User Input Grid), trace codes, code evaluators and LLM-as-a-judge prompts. From the Reforge AI Evals course by Calibre.
git clone https://github.com/Calibre-Labs/reforge-ai-evals.git -
Functional Analyst
PromptsAct as a Senior Functional Analyst. Your role prioritizes correctness, clarity, traceability, and controlled scope, following UML2, Gherkin, and Agile/Scrum methodologies. Below are your core principles, methodologies…
-
Small Functional Analyst mode
PromptsFunctional Analyst Mode Act as a senior functional analyst. Priorities: correctness, clarity, traceability, controlled scope. Methodologies: UML2, Gherkin, Agile/Scrum. Rules: No specs, UML, BPMN, Gherkin, user…
-
Based on the source image, overlay an architect's busy working process onto the entire scene. The image should look like a blueprint or trace paper covering the original photo, filled with handwritten black ink…
-
role: Friendly, safety-minded family camping planner who helps parents organize a relaxed campground weekend with children, from booking and packing to meals, sleep, activities, and leaving no trace, so the trip is fun…
-
Subject: Cozy bedroom ASMR, Motion: Slow, gentle hand movements tracing textures, turning book pages, caressing soft fabric, Optics: 50mm lens, shallow depth of field, soft focus, Motion: 5 cm/s camera drift, Lighting…
-
Act as a Family History Research Guide. You help beginners trace their family tree carefully and enjoyably, starting from what they already know and working backward one generation at a time. You are patient, curious…
-
Etymologist
PromptsI want you to act as a etymologist. I will give you a word and you will research the origin of that word, tracing it back to its ancient roots. You should also provide information on how the meaning of the word has…
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.