21 skills · sorted by relevance
Guides experiments that inspect and change internal model values using nnsight. Covers local PyTorch models and remote experiments through NDIF, including replacing intermediate values to test how particular layers affect a model’s predictions.
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Set up, debug, and extend PicoClaw using its own commands and configuration structure. Get guidance on model authentication, external tool connections, scheduled tasks, and how conversations are routed and stored.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Builds and edits Simulink, System Composer, Stateflow, and Simscape models. Use when modifying model structure, parameters, ports, connections, or Stateflow chart internals.
The English summary is being prepared. Showing the original description.
Fornece orientação para interpretar e manipular internals de redes neurais usando nnsight com execução remota NDIF opcional. Use quando precisar executar experimentos de interpretabilidade em modelos massivos (70B+) sem recursos locais de GPU, ou ao trabalhar com qualquer arquitetura PyTorch.
The English summary is being prepared. Showing the original description.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
The English summary is being prepared. Showing the original description.
Use DreamerV3 for world-model reinforcement learning training, embodied environment dataflow, JAX model internals, result operations, and troubleshooting.
The English summary is being prepared. Showing the original description.
Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.
The English summary is being prepared. Showing the original description.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
The English summary is being prepared. Showing the original description.
Authoritative reference for Pi (@earendil-works/pi-coding-agent): install, configure, run, and extend it. Use for the CLI and configuration, providers and models, extensions, skills, MCP, codemode, the SDK/RPC, security and trust, design philosophy, and the pi repository's internals and contribution rules.
The English summary is being prepared. Showing the original description.
Use when keeping imp's docs and config examples coherent after a change - updating docs/internals/ARCHITECTURE.md / README / docs/GOAL.md / docs/MODELS.md / docs/ROADMAP.md / imp.conf.example / CHANGELOG / MISSION_JOURNAL, or "is this doc stale", "document this change", "the example config is out of date", "the README says X but the code does Y", "add a roadmap ledger row". Do NOT use for layer/frontmatter/lint questions (docs-layers), structural code audits (codebase-audit), measuring perf or refreshing the perf baseline (benchmark-cuda), or the agent's private memory (MEMORY.md).
The English summary is being prepared. Showing the original description.
Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using the Helius blog, SIMDs, and Agave/Firedancer source code.
The English summary is being prepared. Showing the original description.
Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.
The English summary is being prepared. Showing the original description.
Use when an ISV or consulting partner is creating, pricing, publishing, or maintaining an AgentExchange listing through the Partner Console — covers the listing plan, the 5-step Listing Builder workflow (Fill in the Basics, Set Pricing, Add Details, Link Your Solution, Grow Your Business), commercialization models (revenue share vs. annual fee vs. freemium), AgentExchange Checkout setup (Stripe connection, pricing plans, fees, geographic eligibility), Private Offers, Security Review gating, and post-publish listing updates. NOT for building the agent or managed package itself (use agentforce/agentforce-agent-creation and devops/second-generation-managed-packages), NOT for LMA/Trialforce licensing internals (use devops/isv-license-management-and-trialforce), and NOT for the customer-side install experience.
The English summary is being prepared. Showing the original description.
Fornece orientação para pesquisa de interpretabilidade mecanística usando TransformerLens para inspecionar e manipular internals de transformers via HookPoints e caching de ativações. Use ao fazer engenharia reversa de algoritmos de modelos, estudar padrões de atenção ou realizar experimentos de activation patching.
The English summary is being prepared. Showing the original description.
Use when designing, reviewing, modifying, migrating, optimizing, securing, operating, troubleshooting, or decommissioning data architectures across data model exploration, SQL, ISO SQL conformance, NoSQL, vector, graph, document, time-series, NewSQL, search, in-memory, SQLite, CDC/Debezium, DBMS storage/query/recovery internals, database incident prevention, hardware acceleration, cache, big-data, lakehouse, and warehouse systems.
The English summary is being prepared. Showing the original description.
Knowledge base from the FAA Requirements Engineering Management Handbook (DOT/FAA/AR-08/32). Use for writing requirements for real-time, embedded control systems — the avionics/medical slant — via the Handbook's eleven recommended practices: system overview and boundary (monitored/controlled variables), operational concepts (use cases), environmental assumptions, change-tolerant functional architecture (dependency diagrams), safety-driven architecture revision (FHA/PSSA/fault tree), system modes, detailed behavior and performance requirements (ideal value + tolerance + latency), the four-variable model bridge to software requirements (MON/CON/NAT/REQ, IN'/REQ'/OUT', DO-178B mapping), subsystem allocation, and rationale. Carries the Isolette Thermostat and Flight Control System worked examples. Slanted toward control systems with sensors and actuators; thin on information-system / enterprise / agile requirements, on requirements-management tooling, and on the formal-methods internals of SCR/RSML/SpecTRM (it names them, does not re-teach them). Does not reproduce the IEEE/DO-178B/ARP standards it cites.
The English summary is being prepared. Showing the original description.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
The English summary is being prepared. Showing the original description.