“RAG”

Suede AI code review and A-F ship grade for a diff, PR, branch, or commit range: findings ranked P0-P3 with file:line evidence and a fix path, an A-F grade…

Use FlashRAG for retrieval-augmented generation research workflows: config/data validation, retrieval and index building, generation/refinement components…

Local document and PDF parsing that returns spatial text with bounding boxes.

Builds generative AI applications on Amazon Bedrock.

Perform finance web searches and local context searches.

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems.

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development.

Manages Amazon DocumentDB end-to-end — serverless-on-8.0 cluster setup, TLS/VPC/driver config, flexible-schema and vector-search data modeling, MongoDB…

Writing and changing code: Ponytail simplicity, grounded style rules, local and feature-wide systematic debugging, completion verification, architecture…

Scans AI training data pipelines and datasets to detect bias, data poisoning, label corruption, and statistical anomalies that could compromise autonomous AI…

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.

Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary…

Context management engine for AI coding agents.

Prompt engineering and LLM evaluation.

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs.

Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS/Aurora scaling pressure…

Manages Volcano Engine ContextSearch control-plane and application-console operations.

会话观察者（v4.2 草案）：为一段 agent 工作（Claude Code、Codex、Kimi、dsh 会话，可以多个）建立并维护一份认知——任务地图：你要什么 → 走到哪 → 还在主线上吗 → 卡在哪 → 下一步，项目里现成的…

Create, revise, review, and export Marp presentations with RAS (RAISE A SLIDE), discuss a brief and outline before building, or remember presentation…

Govern Project Jennifer work through stateless-renter routing, situational CDP/CCP transitions, CEEP, POC-vs-FOC, VOC registry parsing, runtime mutation…

Builds generative AI applications on Amazon Bedrock.

構成図・アーキテクチャ図・エージェント構成・処理の流れを「動く画像」にして、X（Twitter）などに貼れる MP4 と GIF で書き出すスキル。ノードが順に現れ、線が引かれ、光の粒がエッジを流れ、いま動いている部分だけが光り、下に字幕がタイプされ、最後に全体が同時に動いてループする。箇条書きのツリー（「>…

Use CAMEL-AI to build, configure, tool, remember, evaluate, and troubleshoot multi-agent Python systems with self-contained routing across agents, models…

Use DB-GPT 0.8.1 as an agentic AI data platform: install and configure provider profiles, operate its CLI and services, build agents and AWEL flows, ingest…