159 prompts
Tool choice, planning, state tracking, failure recovery, and task decomposition prompts.
Design production-grade cybersecurity skills following the agentskills.io standard to transform generic AI agents into capable security analysts, with cross-mapping to five industry frameworks and executable workflows.
Designs a multi-role tooling system for AI coding agents that operates like a software factory, emphasizing role specialization, mutual review, and explicit invocation to improve code quality and delivery reliability.
Design a coordination system where humans provide direction via lightweight chat messages and autonomous coding agents ("claws") self-coordinate to plan, build, test, recover, and push code without micromanagement, emphasizing externalization of meta-tasks and context-window purity.
Design a unified virtual filesystem layer enabling AI agents to interact with heterogeneous backends (S3, Google Drive, GitHub, etc.) using standard Unix-like tools, abstracting away multiple APIs into a single familiar filesystem interface.
Design a fully on-device voice input/output architecture supporting multiple TTS engines, zero-shot voice cloning, global dictation, agent voice output, and post-processing, ensuring voice data never leaves the device unless explicitly authorized by the user.
Designs generator/evaluator harness patterns enabling parallel LLM sub-agents to collaboratively build large, coherent software artifacts (e.g., compilers, interpreters, runtimes) with deterministic quality gates, bounded coordination cost, and failure isolation.
Design a zero-human multi-agent company operating system with org structure, task allocation, budget control, governance, and audit trails for autonomous, goal-driven execution under financial constraints.
A fully autonomous machine learning experimentation agent that runs closed-loop experiments on a fixed codebase without human intervention, iteratively modifying training code, running short-budget trials, and optimizing a single ground-truth metric.
Determine optimal timing for requesting user clarification in long-horizon AI agents based on information type and execution progress to maximize value and avoid harm.
A local-first, agent-agnostic design production system that generates complete visual artifacts without cloud lock-in, emphasizing structured pipelines, brand consistency, multimodal output, and five-dimensional self-critique.
Design a two-layer permission classifier for agents to operate efficiently on low-risk actions while preserving human approval for high-risk operations, eliminating confirmation fatigue without compromising safety.
A strategic job-search system that treats career moves as capital allocation decisions, helping users identify high-value opportunities, evaluate them rigorously, and execute with precision.
Design and deploy scalable parallel prompt-learning systems that achieve significant speedup over serial Automatic Prompt Optimization (APO) methods without sacrificing quality.
Design a self-wiring, entity-centric knowledge brain for a personal AI agent that ingests multi-source content, enriches entities, performs hybrid retrieval, and maintains itself autonomously during idle cycles.
Design, measure, and improve the reliability of AI agent systems—distinct from capability. Based on 2026 research, emphasizes stability under repeated runs, perturbed inputs, and fault injection across four dimensions: consistency, robustness, predictability, and safety/fault tolerance.
Design autonomous agent systems that learn from experience, persist knowledge across sessions, and grow more capable over time without manual prompt engineering. Includes skill ecosystem, multi-platform gateway, model-agnostic layer, and safety governance.
Design an end-to-end open-source deep research agent system that competes with closed commercial offerings (e.g., OpenAI Deep Research). The agent must answer complex, multi-hop questions over the open web with verifiable citations, long-horizon planning, and reproducible runs. This includes data pipeline, training recipe, inference modes, tool stack, evaluation harness, deployment topology, and governance.
An AI-powered video editing engineer specializing in post-production workflows using ffmpeg, Python (PIL), and structured EDLs. It reasons over transcripts, waveforms, and frames to make precise cuts, apply color grading, add animations, and generate subtitles — all while adhering to production-grade correctness rules such as audio-first cutting, subtitle-last application, and parallel animation rendering.
A specialist in designing privacy-first, offline-capable, and hardware-efficient AI systems that run at the edge, covering heterogeneous platforms like Apple Silicon, Qualcomm Snapdragon X Elite, and consumer GPUs.
Design a dynamic context management system for long-horizon agents that selectively preserves, compresses, rolls back, and deletes context to control growth, reduce hallucination, and improve reasoning efficiency.
Design interleaved reasoning strategies for streaming autoregressive LLM interfaces to balance reasoning accuracy and user-perceived latency.
Based on the three-layer framework from arXiv 2603.14248 (April 2026) — High-level Planning, Low-level Grounding, and Replanning — this diagnostician localizes failures in GUI/web agent trajectories to provide targeted, actionable fixes rather than generic improvements.
A multimodal agent capable of sustained visual and textual search over up to 100 turns, with emphasis on context preservation, on-demand image loading, and evidence provenance.
Evaluate whether structural prompt compression (e.g., LLMLingua-family token pruning) delivers end-to-end latency, cost, and accuracy benefits for a production workload, based on the 'Prompt Compression in the Wild' study, and provide a decision framework for compressor selection, ratio, and hardware alignment.