AI Agent & Automation Workflows

Reference for agile software process frameworks — the Agile Manifesto's actual principles, Extreme Programming (XP) practices, Scrum ceremonies and roles, and Kanban flow — covering what problem each solves and common misapplications. Use this whenever the user asks about sprint planning, standups, backlog management, choosing between Scrum and Kanban, XP practices like pair programming, or is setting up or critiquing a team's process.

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA)…

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead…

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration,…

Autonomous AI agent platform for building and deploying continuous agents.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.

Minimal BAML skill. BAML is a statically-typed, expression-oriented language with first-class LLM functions — TypeScript-like, snakecase methods, etc. Useful for building ai workflows, agents, evals.

Vision-language pre-training framework bridging frozen image encoders and LLMs.

Reference for build system philosophy (task-based vs. artifact-based, module granularity) and dependency management theory (semantic versioning's real limitations, diamond dependencies, the live-at-head alternative). Use this whenever the user is configuring a build system, debugging a dependency conflict, arguing about module boundaries or build file structure, deciding how to version a library, or asking why a dependency upgrade broke something SemVer said it wouldn't.

Reference for immutable infrastructure, container security fundamentals, and core Kubernetes concepts (pods, deployments, services, health checks). Use this whenever the user is containerizing an application, setting up or debugging a Kubernetes deployment, deciding between mutable server management and immutable infrastructure, or reviewing container configuration for security issues.

Expertise in deployment automation, container orchestration, and infrastructure as code. Activates when working with "deploy", "kubernetes", "docker", "terraform", "helm", "k8s", "container", or cloud infrastructure.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Document and type a Sentry API endpoint. Write or fix @extendschema decorators, specify response TypedDicts, type request parameters, correct type drift between the declared schema and the runtime response, and validate the generated spec. Use when asked to "document an endpoint", "add OpenAPI docs", "add/fix @extendschema", "type an endpoint response", "fix the response type", "fix type drift", "reuse a response type", "split an overloaded endpoint", "specify the response schema", "add a TypedDict response", "migrate a legacy api-docs path", "fix a parameter type", or "make an endpoint public" / "promote an endpoint" (promotion is one section here).

Reference for writing effective technical documentation — matching document type to purpose (reference, design doc, tutorial, conceptual), knowing your audience, and treating docs as a maintained artifact rather than a one-time write. Use this whenever the user is writing a README, design doc, API reference, tutorial, or any technical documentation, deciding what kind of doc a situation calls for, or complaining that existing docs are stale, confusing, or unused.

Build or refresh engineering culture and produce an Engineering Culture Operating System Pack (capability map, culture code, org↔architecture alignment, clock-speed/DevEx backlog, workflow contract, rollout + measurement). Use for engineering culture, DevOps capabilities, DevEx, clock speed, Conway's Law, and engineering principles. Category: Engineering.

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments.

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms.

Provides guidance for experiment tracking with SwanLab.

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on…

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO…

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

Half-Quadratic Quantization for LLMs without calibration data.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).