HVE Core is a collection of agents, prompts, coding instructions, and skills for building repeatable software-development workflows with GitHub Copilot. It is intended for individuals and teams that want structured AI-assisted research, planning, implementation, and review, while the catalogue entries provide many of its reusable workflow components.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/hve-core --skill data-science-engineering-foundationgit clone --depth 1 https://github.com/microsoft/hve-coreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/hve-core/data-science-engineering-foundation)<a href="https://agentmods.dev/skills/microsoft/hve-core/data-science-engineering-foundation"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/data-science-engineering-foundation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/hve-core/data-science-engineering-foundation"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/data-science-engineering-foundation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00754 |
| Opus 5.5 | $0.00017 | $0.00302 |
| Sonnet 5.5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
data-science-engineering-foundation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Science and Engineering Foundation
Goal
Keep Data Science and Engineering Coach orchestration consistent across job changes and sessions without duplicating job-specific guidance. The coach loads this index at initialization and resume, then reads the reference for the current coaching moment.
Reference index
| Reference | When to read |
|---|---|
| job-registry.md | Before offering or selecting a job, routing to a skill or specialist, or naming a durable output |
| lifecycle-classes.md | When starting, pausing, resuming, completing, or re-invoking a job |
| transition-protocol.md | When a topic shift, explicit request, or completion suggests moving between jobs |
| session-state.md | Before initialization, validation, mutation, resume, recovery, or reconstruction of coaching state |
| flow-state.md | Before interrupting work, crossing a gate, writing a durable artifact, or offering post-job choices |
Success criteria
- Each orchestration rule has one owner in this package.
- State and lifecycle mechanics remain independent of job-specific methods.
- The coach reads the applicable reference before acting on its contract.
Constraints
- Keep catalog guidance in
data-catalog, the durable data-catalog workflow for entities, declared relationships, lineage, and ERD-ready model semantics. - Keep feasibility guidance in
feasibility, the evidence-led data and ML feasibility-study workflow with lifecycle and interchange traceability. - Keep pipeline and testing guidance in
dataops, the DataOps reference for tier behavior, pipeline invariants, validation placement, tests, drift, and operational signals. - Keep general experiment guidance in
experiment-design, the reusable workflow for candidate selection, hypotheses, vetting, minimum scope, and result evaluation. - Keep ML-specific experiment guidance in
ml-experimentation, the reference for ML environments, reproducibility, tracking, evaluation, abstractions, and production readiness. - Keep notebook and dashboard guidance in
analysis-authoring, the reference for EDA notebook and analytical dashboard composition, visualization selection, and dashboard validation. - Keep AI-system evaluation guidance in
evaluation-design, the reference for evaluation dataset design, difficulty balance, metric selection, and tooling fit. - Treat this package as internal foundation knowledge, not a user-selectable workflow.
- Preserve the skill authority boundaries and cross-cutting concerns defined in the job registry.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 75 lines · 43 tokens per session scan A 56242c2ab6fe
data-science-engineering-foundation is a skill published in the GitHub repository microsoft/hve-core (1,564 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 754 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
nanogpt
Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
kaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
learning-notes-automation
A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.