Results for “latent-space”

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations from Arize AI.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Runs R statistics analyses on local datasets, producing NLSS-format tables, narratives, and JSONL logs from CSV, SAV, RDS, RData, or Parquet files.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Space (agai-space)

Design loading, skeleton, and progressive content reveal patterns that maintain user confidence and perceived performance.

Generates award-level UI with GSAP motion, bento grids, and Python-driven randomization for layout variety.

Skeleton loading placeholders — gray-shape stand-ins that mirror final content dimensions, use subtle shimmer/pulse animation, and prevent layout shift. Use when replacing generic spinners with content-shaped placeholders, reducing perceived latency on slow routes, or preventing CLS on image-heavy cards.

Spacing component for consistent gaps between elements. Invoke when user needs to add spacing between components or create layouts with gaps in Naive UI.

Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.

Structured memory system with domains, decay, and links for AI agents, replacing flat memory files with a weighted, interconnected memory palace.

Space (afai-space)

Design and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.

融合潜能蒸馏与空间抽象能力，从空间维度提取和转化潜能，构建基于空间的潜能发展框架。

Space (adai-space)

The layers trade timeliness against definitiveness.

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

A complete tour of the intelli-verse-x 5-layer stack — Leantime/GitHub at the top, Beads/Bernstein/Claude-Squad in the middle, Gas Town as the multi-project fabric, and LiteLLM/Infisical/Langfuse/n8n/GH-Actions underneath. Use whenever the user asks "what does X service do", "where does Y data live", "how do I get to Z", or you need to understand which tool to reach for. This is the architecture map.

Whitespace

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

丁磊（互联网创业）认知与表达框架（压缩蒸馏）：佛系老板、游戏与音乐品味人设 触发：网易、养猪梗 等。非替网易发言

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Generate award-level landing pages with cinematic GSAP motion, gapless bento grids, and strict AIDA structure.

Builds multi-tenant Laravel SaaS applications with stancl/tenancy v3, covering tenant identification, data isolation, bootstrappers, queues, and production patterns.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.

Anchors work at the current moment and places events as spatial distances ahead or behind to improve temporal reasoning.

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。

Space (ahai-space)

融合分类系统与空间抽象能力，构建空间化的分类体系，支持空间相关的分类需求和空间关系分析。

Exploit Active Directory environments using Pass-the-Hash (PtH). This skill details how to authenticate to remote systems using the NTLM hash of a user's password instead of the plaintext password, enabling lateral movement and privilege escalation without cracking hashes.