Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Light0305/Light-skillsnpx agentmods add skills/light0305/light-skills/light-data-engineeringWrote 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/light0305/light-skills/light-data-engineering)<a href="https://agentmods.dev/skills/light0305/light-skills/light-data-engineering"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-data-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/light0305/light-skills/light-data-engineering"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-data-engineering.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 | $0.00361 | $0.09025 |
| Opus 5.5 | $0.00144 | $0.03610 |
| Sonnet 5.5 | $0.00072 | $0.01805 |
| Haiku 4.5 | $0.00036 | $0.00903 |
Grade A, and why
light-data-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 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据工程（data-engineering）—— 找数据、核数据、守泄漏，再决定 idea 能不能立
你是 Light 科研流水线的 DAG 第 2 节点。任务不是"先把数据洗干净再说"，是在提 idea 之前回答院士会枪毙 idea 的 两个硬问题：这数据够不够支撑这个研究（规模/质量/功效）？ 和 这套划分有没有藏着让结果虚高的数据泄漏？ 数据 不足以支撑的 idea 拦在定稿前（带"缺口 + 补法"回 idea-generation，回边 2⊣3）；数据泄漏（顶会拒稿高频雷）是 critical 一票否决。
一句话定位：把"一屋子做数据的院士在提 idea 前真正坚持的"——先找得到、下载得起、许可用得了且版本锁得住， 再做数据可行性前置（很多 idea 死在数据根本不够/不可得/质量差）+ 数据泄漏前置查（标准化早于划分 / 时序穿越 / train-test 实体重叠 / 目标编码穿越）+ 可挖掘价值判断 + 自建数据集规范——落成 下载前 advisory + 确定性 critical 门。深度对标真相源 =
docs/competitors/data-engineering.md（11 个真同类 + 机制锚 + 诚实边界）。谁产 findings、谁是 critical 门（诚实分工）：本技能产两类 critical findings（producer=data-engineering）—— ① 数据泄漏（
split_leakage.py→leak_findings.json，HIGH=critical）；② 数据可行性不足/idea-killing （data_feasibility_gate.py，功效粗筛 insufficient / 四问 insufficient = critical）。均被run_checkpoint --stage 2聚合 → critical fail exit 1。warn 不阻断：样本量偏紧、划分不合理（spec §4.2 口径）。特殊位置（前置于 idea）：data-engineering 是 stage 2，但工作流里常在 idea 之后跑（idea-generation 立项卡先点名 "要什么数据"）→ 本技能判"数据撑不撑得起这 idea"，不够则
reroute --stage 2建议回边 2⊣3（拦在 idea 前：补数据 / 改 idea 降数据门槛）。这是 idea-generation 立项卡"数据可行性必答字段"的前置守门方。是横切常驻吗？ 否。这是按需
/调用的主线节点；file-reading（读数据文件）/memory-pm（记台账）/consistency/ research-ethics（隐私合规复核）全程横切常驻，本技能不重复它们。
何时启动（触发信号）
- 用户给了数据/数据集问"能不能做研究 / 够不够 / 质量行不行 / 怎么划分 / 会不会泄漏"——任一即启动。
- 用户问"哪里有数据 / 这个数据集能不能下载和发表 / HF、OpenML、UCI、Kaggle 该选哪个"——启动数据需求卡与
references/data-resource-map.md的 intake 闭环。 - 作为流水线第 2 步：idea-generation 立项卡点名"这 idea 要 X 数据、规模 N、标注 K" → 本技能判数据可行性，
verdict 强制回写总控（
run_checkpoint --stage 2）；数据泄漏 / idea-killing 不足 → critical fail 确定性阻断。 - 数据不足以支撑的 idea：带"缺口 + 补法（补数据 / 改 idea 降门槛）"回 idea-generation（2⊣3 前置回边）——这是决策点，停下问用户。
- 回边（实验阶段，来自 research-plan stage 5）：接派生数据规格 →
derive_eval_set.py出鲁棒性/泛化/敏感性评测集。
你怎么工作：ACT / ASK / NEVER
What ships with it
21 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.
- assets/data_card_template.md 5.0 KB
- examples/derive_spec.example.json 895 B
- examples/rules.example.yaml 975 B
- examples/worked_example.md 7.4 KB
- references.md 22 KB
- references/data-resource-map.md 11 KB
- scripts/check_access_level.py 5.7 KB runs code
- scripts/croissant_export.py 6.8 KB runs code
- scripts/data_doctor.py 22 KB runs code
- scripts/data_feasibility_gate.py 20 KB runs code
- scripts/data_feasibility.py 9.6 KB runs code
- scripts/data_identity_fitness.py 40 KB runs code
- scripts/dataset_intake.py 17 KB runs code
- scripts/derive_eval_set.py 9.3 KB runs code
- scripts/drift_check.py 10 KB runs code
- scripts/quality_gate.py 11 KB runs code
- scripts/safe_split.py 13 KB runs code
- scripts/sample_size_check.py 9.1 KB runs code
- scripts/split_leakage.py 25 KB runs code
- templates/annotation_guide.md 4.7 KB
- templates/data-identity-fitness.example.json 1.9 KB
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 · 308 lines · 361 tokens per session scan A 11c326e2e246
light-data-engineering is a skill published in the GitHub repository Light0305/Light-skills (683 stars, last pushed 3mo ago), licensed MIT. It adds 361 tokens to every session and 9,025 once invoked, about $0.0014 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
academic-citation
Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations…
academic-paper-writer
A coordinating skill for planning and drafting computer science, artificial intelligence, and machine learning papers from research notes, code, literature, or venue requirements. It moves through a defined sequence of paper-writing stages.
academic-experiments
Audit, run, or verify experimental evidence for CS/AI/ML papers. Produces Evidence Inventory with evidencetype annotations (newlyrun/preexistingartifact/userclaim) and Protocol Risk assessments. Use when: checking if experiment results are reproducible, auditing existing experiment artifacts, running minimal…