Borrowing it
Nothing to install: this file belongs to irahardianto/awesome-agv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irahardianto/awesome-agv/main/.agents/skills/ml-engineering/SKILL.mdgit clone --depth 1 https://github.com/irahardianto/awesome-agvWrote 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/irahardianto/awesome-agv/ml-engineering)<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/ml-engineering"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/ml-engineering/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/irahardianto/awesome-agv/ml-engineering"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/ml-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Agent Snooping · line 74 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 75 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00029 | $0.00601 |
| Opus 5 | $0.00015 | $0.00300 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
ml-engineering 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ml-engineering — 92% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Engineering Principles
Guidelines for building reliable, reproducible machine learning systems.
When to Invoke
- Designing ML pipelines (training, serving)
- Feature engineering and data preparation
- Model evaluation and validation
- MLOps infrastructure decisions
ML Pipeline Design
Stages
Data Collection → Feature Engineering → Training → Evaluation → Deployment → Monitoring
Principles
- Reproducibility — versioned data, code, and config. Same inputs = same model.
- Experiment tracking — every run logged (MLflow, W&B, Neptune).
- Feature stores — centralized feature computation, reusable across models.
- Model registry — versioned models with metadata, promotion workflow.
Feature Engineering
- Compute features once, reuse everywhere — feature store pattern.
- Training-serving skew prevention — same transformation code in training and inference.
- Feature documentation — every feature has description, source, freshness requirement.
Model Validation
Checklist
- Performance metrics meet threshold (accuracy, F1, AUC, etc.)
- No data leakage (target info in features)
- Fairness evaluation across protected groups
- Performance on edge cases and out-of-distribution data
- Latency meets serving SLA
- Model size within deployment constraints
Model Serving
| Pattern | When |
|---|---|
| Batch inference | Scheduled predictions, large volumes, latency-tolerant |
| Real-time API | Low-latency, per-request predictions |
| Streaming | Continuous predictions on event streams |
| Edge | On-device, offline-capable |
Monitoring
- Data drift detection — statistical tests on input distributions.
- Model performance monitoring — track prediction accuracy over time.
- Feature importance drift — alert when feature contributions shift.
- Automated retraining triggers — retrain when performance degrades below threshold.
Tools Ecosystem
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.
- 10d ago First seen · 77 lines · 29 tokens per session scan A 610d5c977833
ml-engineering is a skill published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 601 once invoked, about $0.0001 per session on Opus 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
prompt-engineering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic…
compressed-system-prompts
How to refactor wordy, repetitive system prompts into high-density imperative token structures, cutting baseline system prompt costs by 70% while improving instruction adherence.
add-provider
Checklist for adding a new AI provider (image, video, text, audio) that satisfies all 5 integration principles — ACL, bulkhead, idempotency, observability, and contract test. Load when integrating any new external AI API. Prevents the most common mistake of pasting httpx calls directly into a service.
ai-engineering
Building production features powered by LLMs — model selection, prompt design as engineering, structured output, RAG, evals, cost/latency budgets, and guardrails. Use when adding AI features to a product (chat, extraction, summarization, classification, search), designing prompts that ship to production, building RAG…
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.