科研 Skill
数据集版本哈希校验
version-dataset
Builds a content-hash manifest of a dataset and verifies later copies for drift. Use when an analysis must prove it ran on the intended, unchanged data version.
SKILL.md
Version Dataset Skill
An analysis must run on the data it claims to, with a fixed seed. This skill makes drift between runs loud instead of silent: it records a deterministic fingerprint (file SHA-256 plus, for tabular files, schema and per-column value hashes; no timestamp unless explicitly passed) so a later run can prove the inputs are unchanged. It never alters data, and manifests hold hashes, not the data itself. Provenance notes are in English.
Deterministic Script
# Build a manifest (record the analysis seed + provenance)
python "scripts/version_dataset.py" manifest data.csv \
--out manifest.json --seed 42 --provenance "KNHANES 2018 extract v1"
# Verify a later copy against it (CI / pre-analysis gate)
python "scripts/version_dataset.py" verify --manifest manifest.json --strict
# Compare two manifests (what changed between versions)
python "scripts/version_dataset.py" diff --old v1.json --new v2.json
File hashing is stdlib-only; tabular schema/column hashing uses pandas when present.
--ignore-cols excludes volatile columns; --base makes manifest keys relative.
Workflow
Step 1: Lock the version (gate)
Build the manifest at the moment the dataset is frozen for analysis. Gate: confirm with the user the seed and provenance note are correct before locking — the manifest is the record they will cite as "this is the data the results came from." The provenance note is the user's text; never invent it.
Step 2: Verify before each run (gate)
Before re-running an analysis (or in CI), verify --strict. Never say a dataset is unchanged
without running verify. Gate: if drift is reported (MANIFEST_DRIFT, exit 1), stop and
show the user the drift report exactly as computed — never downplay a changed column hash. Do not
proceed on changed data without their explicit acknowledgement and a re-lock. Silent re-run on
drifted data is the failure this skill exists to prevent.
Read references/manifest_schema.md before interpreting drift — it defines
each drift category. A CSV/TSV file is compared on its logical content (schema + per-column
value hashes), not raw bytes, so re-quoting, reordering columns, or an --ignore-cols volatile
column does not trip a false drift. Binary tabular files (Parquet/Stata/SAS/Excel) are also
checked at the byte level, since labels, metadata and other sheets are not in the column hashes,
unless an --ignore-cols column is present in the file (its changes alter the bytes).
Step 3: Diff across versions
When a dataset is intentionally updated, diff the old and new manifests and
present the change set (added/removed/changed columns, row-count delta) so the
user can record what changed and re-lock. Gate: the user approves the new
version before it replaces the locked one.
Non-Deterministic Artifacts
Do not put PPTX/DOCX or figure binaries under strict byte verification — they embed timestamps
or render metadata and change on every build. Manifest only the deterministic inputs and tabular
outputs (data files, result CSVs), or use --ignore-cols for volatile columns; the policy is in
references/manifest_schema.md. Each bundled demo/*/ carries a manifest.lock.json (input data
- deterministic result tables) that
verify --strictchecks; the reference gives the demo command.
Scope
- Run
/deidentifybefore a manifest is shared: example values are not stored, but provenance notes may carry context. - Cleaning, profiling or de-identifying the data →
/clean-data,/generate-codebook,/deidentify./generate-codebookdocuments what is in the data; this skill locks which version.
示例提示词
帮我给这份数据集生成哈希清单,确保分析用的是同一版本。
所属插件
安装该插件会一并获得同领域的 58 个 Skill / MCP。
同插件的其他科研 Skill
- 医学AI论文检索优化Optimizes a medical AI paper’s title, abstract and metadata for AI search engines. Use when a paper should be findable and citable by RAG tools and AI search.
- 临床数据统计分析与建模Generates reproducible Python or R code for clinical statistics and tables. Use when collected data needs Table 1, regression, survival or agreement analysis.
- 作者发表记录与策略分析Analyzes a PubMed author record to classify study types and authorship patterns. Use when planning a publication strategy from a researcher’s track record.
- 批量队列暴露结局分析Generates one cohort-analysis script per exposure-outcome pair from one template. Use when a validated method must run across many variable combinations at once.
- 样本量估算与检验效能Walks a decision tree to the right test and computes sample size with IRB text. Use when planning how many patients a study needs before data collection.
- 因果推断方法设计Runs DAG-based, instrumental-variable, difference-in-differences or RD analyses. Use when an association in observational data must support a causal claim.
- 报告规范逐条核查Audits a manuscript item by item against 49 reporting and risk-of-bias checklists. Use when checking a draft against STROBE, CONSORT, TRIPOD or similar guidelines.
- 临床数据清洗与画像Profiles a clinical dataset and generates cleaning code in staged, approved steps. Use when a CSV or Excel dataset needs missing-value and outlier checks before analysis.
- 跨国队列数据协调对比Harmonizes variables and runs parallel weighted analyses across national surveys like KNHANES and NHANES. Use when comparing one exposure-outcome link across countries.
- 变量定义与截断值溯源Maps exposure, outcome and covariate definitions to a cited guideline and DB columns. Use when variable cutoffs need a citable basis before the study protocol.
- 本地化临床数据脱敏Runs a local, network-free script that detects and removes identifiers from clinical data. Use when data may contain PHI and must be de-identified before LLM analysis.
- AI对标专家基准研究设计Plans the arms, rubrics, calibration probes and reviewer panel for an AI-vs-expert benchmark. Use before data collection when designing an AI-vs-human rating study.
- 放射影像AI研究设计审查Reviews a study’s analysis unit, cohort logic, leakage risk and reporting-guideline fit. Use when checking a clinical or medical-AI study design before drafting.
- 传染病仓室模型拟合Builds and fits SIR, SEIR and SEIHR compartmental models with Rt estimation. Use when an outbreak or epidemic’s spread needs mathematical modeling in Python.
- ICMJE利益冲突声明填写Clones a pre-filled synthetic ICMJE COI form, replacing only date, name and title. Use when each author on a submission needs a disclosure form filled quickly.
- 机构Word表单内容填充Fills an institutional Word form, such as an IRB protocol, without breaking its layout. Use when drafted content must be rendered into a CJK-aware .docx template.
- 队列数据库选题挖掘Profiles a longitudinal cohort database and ranks research-topic proposals with gap evidence. Use when looking for a question an available cohort or registry can answer.
- 投稿期刊匹配推荐Matches a manuscript abstract against curated journal profiles and ranks candidates. Use when choosing where to submit, or re-targeting after a rejection.
- DOI全文批量获取Batch-downloads open-access PDFs for a list of DOIs via Unpaywall, PMC and OpenAlex. Use when full texts are needed for a screening set such as a meta-analysis.
- 数据集编码本自动生成Profiles every variable in a tabular dataset into a structured, citable codebook. Use when a CSV, Excel or Stata dataset needs a data dictionary before analysis.
- 全球卫生数据获取分析Accesses and analyzes global health data from WHO GHO, IHME GBD and Our World in Data. Use when DALYs, age-standardized rates or choropleth maps are needed.
- 医学AI项目基金申请书撰写Structures a grant proposal’s significance, innovation, approach, aims and milestones. Use when drafting a research funding proposal, including a Korean grant plan.
- 卫生经济学评价建模Builds Markov cohort models with QALYs, PSA and cost-effectiveness planes. Use when a health intervention needs a formal cost-effectiveness evaluation.
- AI写作痕迹识别改写Scans a manuscript for AI writing patterns and rewrites flagged passages carefully. Use when a draft or response letter reads as obviously AI-written.
常见问题
数据集版本哈希校验能做什么?
Builds a content-hash manifest of a dataset and verifies later copies for drift. Use when an analysis must prove it ran on the intended, unchanged data version。
如何安装数据集版本哈希校验?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「数据集版本哈希校验」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
数据集版本哈希校验需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
数据集版本哈希校验经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。