218 skills
Export a single SolidWorks part (.sldprt) to Parasolid (.x_t) format. Uses the active document if no path is given. Accepts optional part path and output directory arguments. Use for single-part export or as the per-item step in LLM-orchestrated batch workflows.
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
Web search across 7 engines in parallel with browser impersonation. Use when the agent needs current information from the web — news, documentation, recent events, or anything beyond training data. Returns structured JSON (SearXNG-compatible) with title, URL, and content. Uses curl_cffi to mimic re…
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, …
CRITICAL: Use for Makepad shader system. Triggers on: makepad shader, makepad draw_bg, Sdf2d, makepad pixel, makepad glsl, makepad sdf, draw_quad, makepad gpu, makepad 着色器, makepad shader 语法, makepad 绘制
AI media generation via deAPI. Transcribe YouTube/audio/video, generate images from text, text-to-speech, OCR, remove backgrounds, upscale images, create videos, generate embeddings. 10-20x cheaper than OpenAI/Replicate.
Query Skool community content using RAG pipeline with vector search. Use when user asks to search Skool knowledge, find community answers, or query Skool content.
Guidelines and instructions for LangChain text vector store integrations
Nightly memory consolidation ("REM"/sleep) for the agent using the current three-tier memory model: Tier 1 instincts (~500 injected gist facts), Tier 2 RAG-class graph+vector recall (~2500, MEMORY_TIER2_MAX), and Tier 3 uncapped bookshelf archive. Dream ingests the harness, preserves detail for rec…
Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.
Vector embeddings, CloudFormation generation, and OAuth validation for AI workflows
Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.
This benchmark evaluates text anonymization methods by measuring both span-level masking accuracy and subject-level privacy leakage. It probes whether anonymized text successfully prevents adversarial LLMs from inferring personal identifiable information (PII) and sensitive attributes, while mainta…
Draft a new task tracking file at doc/tasks/NNNN-<short-slug>.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing. Use when the user wants to create, draft, scaffold, or open a task, ticket, work item, or backlog entry tracked in the repo. Status starts at proposed.
Retrieval-Augmented Generation patterns on Oracle Cloud Infrastructure — embeddings, vector stores, hybrid search, reranking, and production RAG architecture
OpenTofu/Terraform pattern for GitHub Actions OIDC trust with AWS IAM. Covers the non-obvious `job_workflow_ref` condition (vs just `sub` for repo+branch), the Bedrock inference profile ARN patterns, required `aws-marketplace` permissions alongside Bedrock, and the ReadOnlyAccess + explicit Deny pa…
Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating grad…
Quick start for standalone app at livecodes.io, embedding playgrounds with CDN or npm, and self-hosting basics. Load this skill for initial setup and basic usage patterns.
Bayesian theory of attention pattern emergence in transformers — derives closed-form posterior over attention matrices, reveals first-order phase transitions in training data amount for copy head emergence, contrasts softmax vs linear attention behavior.
Local semantic memory with Qdrant and Transformers.js. Store, search, and recall conversation context using vector embeddings (fully local, no API keys).
Evaluates real-time urban pathfinding algorithms under dynamic traffic and weather conditions. It measures how well traditional graph search methods and deep learning models predict optimal routes and minimize travel time in a simulated Berlin city environment. Use when the user wants to benchmark …
用于软件开发岗校招、实习和大厂求职辅导：岗位检索与核验、公司招聘流程查询、JD 分析、岗位匹配、投递策略、简历诊断与改写、面试准备和模拟面试。适用于互联网大厂、AI 公司、云厂商、智能硬件、新能源、游戏、SaaS、金融科技等公司的前端、后端、客户端、全栈、AI 应用、大模型应用、算法、数据、测试开发、SRE、安全、游戏开发、嵌入式等技术岗位。
Add PBR texture loading with separate roughness/metallic support to an SDL GPU project using forge_scene.h
Use when the user mentions a thumbs-down, asks "what went wrong with this nudge/chat/coach/insight", references a specific feedback id, or asks to look at recent feedback. Covers the triage flow (how to walk an LLM call trace), how to localize a bug across the source/verify/rewrite chain, how to cr…
Use Outlines when you need to: - Guarantee valid JSON/XML/code structure during generation - Use Pydantic models for type-safe outputs - Support local models (Transformers, llama.cpp, vLLM) - Maximize inference speed with zero-overhead structured generation - Generate against JSON schemas automatic…
Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
The Pan-Cancer Multi-Omics Agent integrates multi-omics data across cancer types to identify shared oncogenic drivers, discover novel subtypes, and enable cross-cancer therapeutic insights. It leverages TCGA, CPTAC, and other pan-cancer resources with deep learning for comprehensive cancer characte…
Protein grouping and inference from peptide identifications. Use when resolving protein ambiguity from shared peptides. Handles protein groups and protein-level FDR control using parsimony and probabilistic approaches.
Make text more genuine, natural, and feel not written by an AI or LLM by removing AI tropes and cliches. Use when asked to deslopify, naturalize, or remove AI tropes from text.