Use BEFORE writing or editing any code that calls an external HTTP API or imports a third-party SDK (e.g.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.
Use when a task needs the judgment of a Nanotechnology Engineering Technician — running or qualifying an RCA wet-clean sequence, diagnosing atomic layer deposition…
Interactive viewer for microscopy. Displays 2D/3D/4D arrays as Image, Labels, Points, Shapes, Tracks layers; supports annotation, plugin analysis, headless screenshots.
Apply NASA's battle-tested framework for building complex, mission-critical systems where failure has catastrophic consequences
Knowledge base from the NASA Digital Engineering Acquisition Framework Handbook (NASA-HDBK-1004). Use for acquiring digital/model-based data under contract: the Data Requirements…
Knowledge base from the NASA Fault Management Handbook (NASA-HDBK-1002, Draft 2, April 2012). Use for the systems-engineering discipline of designing what a system does when it…
Knowledge base from NASA Human Systems Integration (HSI) Practitioner's Guide (NASA/SP-2015-3709). Use for HSI process implementation, lifecycle phase activities, function…
NASA Systems Engineering methodology mapped to cloud operations. Use when planning, executing, verifying, or documenting OpenStack cloud infrastructure following NASA SP-6105 and…
Knowledge base from the Expanded Guidance for NASA Systems Engineering (NASA/SP-2016-6105-SUPPL, Volume 1, March 2016) — the practitioner-depth supplement to the NASA SE Handbook.
Set up and operate a personal knowledge system using Supabase (pgvector) and OpenRouter. Five structured tables — thoughts (inbox log), people, projects, ideas, admin — with…
Deploy a temporary n8n test instance (or generate a local docker run command) via the internal "Nathan" bot, from the repo instead of Slack.
บุคคลเข้าไปยึดถือครอบครอง แผ้วถาง เผา บุกรุก หรือทำไม้ในเขตป่าสงวนแห่งชาติโดยไม่ได้รับอนุญาต เช่น ตัดไม้หวงห้าม เปิดที่ดินเกษตร สร้างที่อยู่อาศัย หรือยึดครองพื้นที่ป่าสงวนแห่งชาติ
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo — from…
Use when debugging native programs or ELF binaries with gdb breakpoints, backtraces, and memory inspection. Triggers:
Route a native Apple-platform task to the right skill among the iOS specialists — Swift 6.2 concurrency, SwiftUI architecture, actor persistence, protocol-based DI/testing,…
Query and manage Linear issues, projects, cycles, and teams via the Linear GraphQL API. Use when you need to list or create issues, check cycle status, manag...
Create native modules with sequential native-bridge-builder then code-reviewer agents
Rozwija aplikacje desktopowe z użyciem NativePHP Desktop v2. Aktywuje się przy pracy z oknami (Window), paskiem menu (MenuBar), menu aplikacji (Menu), powiadomieniami, dialogami,…
Use when a task needs a real browser — navigating JavaScript-heavy sites, interacting with logged-in accounts, clicking/typing/filling forms, taking screenshots, inspecting…
NATS JetStream messaging for Vigil Guard 2.0+ migration. Use when implementing message queues, detection workers, request-reply API, async processing, Dead Letter Queues, or…
Generer Architecture Decision Records (ADR) med flerperspektiv-review tilpasset Nav
Use when setting up CI/CD pipelines that validate Navan API integrations, run booking data health checks, or generate automated compliance reports.
Diagnose and fix common Navan API errors with targeted fix procedures. Use when an API call returns an unexpected HTTP error or when debugging production failures.
Extract and transform Navan booking and transaction data using pagination, filtering, and data pipeline connectors.
Implement incremental sync strategies for Navan BOOKING and TRANSACTION data with ETL pipeline patterns.
Use when collecting diagnostic data from a Navan API integration — OAuth token inspection, API response capture, connectivity testing, and request/response logging.
Use when deploying Navan integrations with ERP systems (NetSuite, Sage Intacct, Xero), HRIS platforms (Workday, BambooHR), or identity providers (Okta, Azure AD).
Set up a local development environment for Navan API integrations with token caching and request logging. Use when starting a new Navan project or debugging API issues locally.
Use when optimizing Navan API call patterns for high-volume integrations — caching, batching, connection pooling, and pagination strategies.
Implement adaptive rate-limiting for the Navan REST API with exponential backoff and request queuing. Use when building bulk data operations or encountering 429 errors from Navan.
Use when designing a production Navan API integration architecture — API gateway, token management, data sync pipelines, ERP connectors, and monitoring stack.
Use when the user wants to run commands inside a navaris sandbox — one-shot exec, persistent interactive sessions, or attaching a terminal.
SwiftUI navigation architecture patterns including NavigationStack, NavigationSplitView, TabView, programmatic navigation, and custom transitions.
Browser automation using Playwright and Chrome DevTools. Automates data collection, form interaction, screenshot capture, and network monitoring.
Use for survey-based structural equation modeling in 《南开管理评论》 (Nankai Business Review) — CFA/SEM fit indices, mediation and moderation, moderated mediation with bootstrap indirect…
Referência técnica para NBR 15808 (extintores portáteis) e NBR 12693 (instalação em edificações). Use quando o usuário mencionar: extintores portáteis, NBR 15808, NBR 12693,…
Use when asked to analyze content for manipulation, propaganda, disinformation patterns, or when user provides a URL or text asking "is this manipulative?", "analyze this for…
Use whenever writing or editing Python code in a project that depends on the `nclutils` package. Trigger on any `import nclutils` or `from nclutils.*` line, and whenever about to…
NDA fuer SaaS-/IT-Vendor-Pitches: Cloud-Hosting, Datentrennung, Subprozessoren, Audit-Rechte, Penetration-Testing-Erlaubnis.
Use when processing LC-MS metabolomics studies with >10 samples where sample count and memory constraints make pairwise mass alignment infeasible.
Use when you have extracted mass tracks (EICs) from individual samples at 0.001 amu m/z resolution and need to align them into a composite mass grid for feature detection.
Use when when analyzing spatial molecular data (e.g., from tissue sections or microscopy) where you need to build k-nearest neighbor graphs on high-dimensional coordinate arrays…
Use when you have millions of MS/MS spectra to cluster and have already constructed nearest neighbor indexes (partitioned Voronoi diagrams of spectrum vectors bucketed by…
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots.
Use when asked to fix, build, refactor, review, verify, or release software and the work is non-trivial — including delivering a change request (issue, ticket, or request) from…
Needle-in-a-Haystack context placement testing for LLM retrieval accuracy. Context window stress tests, information placement strategies, lost-in-the-middle avoidance, and optimal…
Evaluate systems through an entropy/negentropy lens — is this system decaying or growing? Use when making architecture decisions, evaluating system health, or when the user…
Overview and information about Neki, the sharded Postgres product by PlanetScale. Load when working with Neki-related tasks and the need to scale or shard postgres.
Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or…
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors,…
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs,…
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples. — from NVIDIA/skills
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container set — from…
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes,…
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron…