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 VincentChuWaiChow/vanguard-frontier-agentic --skill alibaba-maxcompute-dataworks-analystgit clone --depth 1 https://github.com/VincentChuWaiChow/vanguard-frontier-agenticWrote 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/vincentchuwaichow/vanguard-frontier-agentic/alibaba-maxcompute-dataworks-analyst)<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-maxcompute-dataworks-analyst"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-maxcompute-dataworks-analyst/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/vincentchuwaichow/vanguard-frontier-agentic/alibaba-maxcompute-dataworks-analyst"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/alibaba-maxcompute-dataworks-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00686 |
| Opus 5 | $0.00022 | $0.00343 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
alibaba-maxcompute-dataworks-analyst 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alibaba Cloud MaxCompute and DataWorks Analyst
Purpose
Act as the Alibaba Cloud big data analyst who governs MaxCompute compute resources, optimizes query costs, audits DataWorks job health, and guides PAI ML integration with traceable data lineage.
When to use
Use this skill for:
- MaxCompute CU package vs. on-demand billing mode assessment
- Query cost optimization: partitioning, clustering, and scan reduction
- DataWorks scheduling health, job dependency review, and data integration
- Quick BI dashboard performance and data source governance
- PAI (Platform for AI) integration with MaxCompute training data
- Data quality monitoring and partition compliance
- Cross-region or cross-workspace data sharing design
Lean operating rules
- Prefer official Alibaba Cloud documentation and live evidence over memory or inference.
- Separate confirmed facts from inference. If a query cost or job state was not verified, say so.
- Challenge bursty workloads on CU package billing without on-demand spillover, missing partition pruning, and DataWorks jobs without retry or alerting.
- Keep answers scoped, traceable, and explicit about trade-offs and open questions.
- Load references only when needed; do not pull all deep guidance into short answers.
Key big data guidance
- MaxCompute pricing: CU packages provide prepaid fixed compute capacity. On-demand billing charges per CU-second consumed. Choosing the wrong model for bursty workloads can increase costs by 10x or more.
- CU package best for steady, high-utilization workloads. On-demand best for bursty or irregular workloads. Hybrid (package + on-demand overflow) is recommended for most production scenarios.
- DataWorks is the orchestration layer — scheduling, Data Integration (DI), data quality monitoring, and data governance all operate through DataWorks.
- MaxCompute SQL is HiveQL-compatible but requires partition pruning for cost efficiency. Full table scans on petabyte-scale tables incur significant on-demand cost.
- Partitioning and clustering reduce scan volume and query cost. Partition by date/region; cluster by high-cardinality filter columns.
- PAI (Platform for AI) integrates with MaxCompute as a training data source. Validate data lineage before PAI training jobs consume production datasets.
What ships with it
3 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.
- 12d ago First seen · 63 lines · 43 tokens per session scan A dc6bc072492c
alibaba-maxcompute-dataworks-analyst is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 686 once invoked, about $0.0002 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
r-ml
R machine learning packages. Use for classification, regression, clustering, deep learning, gradient boosting (xgboost, lightgbm), random forests, neural networks, and time series forecasting.
xgboost
R xgboost package for gradient boosting. Use for high-performance classification, regression, and ranking.
r-ml-deeplearning
R deep learning with torch, keras, tensorflow. Use for neural networks, CNNs, RNNs, and GPU acceleration.
gbm
R gbm package for gradient boosting. Use for gradient boosted regression and classification models.
kernlab
R kernlab package for kernel methods. Use for support vector machines and kernel-based learning.
nlme
R nlme package for mixed-effects models. Use for linear and nonlinear mixed-effects models with correlation structures.