npu-verification

MindStudio-Modeling performance evaluation framework for Ascend NPUs. Provides tensor-cast for model-level analysis and serving-cast-simulation for LLM serving parameter tuning.

3 skills

AISBench evaluation framework — accuracy benchmarks (GSM8K, MMLU, AIME) and performance benchmarks against vLLM services.

1 skill

Ascend NPU hardware entry point — health check, environment setup, shell script template. Starting point for any Ascend workflow.

1 skill

Structured Git commits with WHAT/WHY/HOW format, optimized as AI context for future sessions.

1 skill

Model quantization on Ascend NPUs — W4A8/W8A8/W4A4, one-click and custom YAML, MoE mixed precision, VLM support, accuracy recovery.

1 skill

Concise, idiomatic Rust patterns for implementation, review, testing, and required quality checks.

1 skill

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

Find and verify professional email addresses, search contacts by domain, and enrich company data -- directly in Claude.

13 skills · 1 MCP server

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

Core financial modeling and analysis tools: DCF, comps, LBO, 3-statement models, competitive analysis, and deck QC

13 skills · 7 commands · 12 MCP servers

Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.

8 skills · 1 command · 16 MCP servers

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.

35 skills · hooks