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 agentmods add skills/danielrosehill/claude-data-analyst-plugin/data-dictionary-creatornpx skills add danielrosehill/Claude-Data-Analyst-plugin --skill data-dictionary-creatorgit clone --depth 1 https://github.com/danielrosehill/Claude-Data-Analyst-pluginWrote 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/danielrosehill/claude-data-analyst-plugin/data-dictionary-creator)<a href="https://agentmods.dev/skills/danielrosehill/claude-data-analyst-plugin/data-dictionary-creator"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-data-analyst-plugin/data-dictionary-creator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00062 | $0.00704 |
| Opus 5 | $0.00031 | $0.00352 |
| Sonnet 5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
data-dictionary-creator 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Dictionary Creator
Produce a data dictionary by merging schema inspection with the user's semantic description of the dataset.
Inputs
- Path to a dataset file or folder.
- The user's description of the dataset: what it represents, how it was collected, what each column means (can be partial — infer the rest).
- Optional: output format (
markdowndefault,csv, orjson).
Recommended CLI tooling
duckdb -c "DESCRIBE SELECT * FROM '<file>'"— fast schema + inferred types.csvstat— null counts, uniqueness, min/max per column.uv run --with pandas python -c '...'— for dtype coercion and sampling.
Procedure
Step 1 — Auto-profile every column
For each column, collect:
- Inferred data type (int, float, string, date, boolean, category)
- Null count and percentage
- Unique count (and full value list if <20 distinct)
- Min / max / mean (numeric) or top-5 modes (categorical)
- Sample values (3 random non-null)
Step 2 — Merge with the user's description
Parse the user's description and map sentences to columns. For each column, fill:
- Name (as in the file)
- Display name / human-readable label
- Description — one-sentence semantic meaning
- Type
- Unit (currency code, SI unit, %, count, etc.)
- Allowed values — enumerated list if categorical with small cardinality
- Nullable — yes/no and what a null means (missing vs. not-applicable)
- Source — where this field originated if the user mentioned it
- PII — none / direct / quasi-identifier (cross-check with
pii-flagheuristics) - Notes — caveats, known issues, derivation formulas
If a column isn't covered by the user's description, mark the Description field as [NEEDS REVIEW] rather than guessing, and list these at the end for user confirmation.
Step 3 — Add dataset-level metadata
At the top of the dictionary:
- Dataset name and path
- Purpose (from user description)
- Row count, column count
- Primary key(s) — infer from uniqueness; ask if ambiguous
- Collection period if derivable from timestamp columns
- Last modified timestamp
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.
- 4d ago First seen · 85 lines · 62 tokens per session scan A a05615c3394e
data-dictionary-creator is a skill published in the GitHub repository danielrosehill/Claude-Data-Analyst-plugin (11 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 704 once invoked, about $0.0003 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
ppt-analysis
PPT (.pptx/.ppt) 全量解析。覆盖：所有 slide 文本/表格/图表提取、嵌入图片 caption、纯图片 slide 渲染识别、数据标签提取。.
large-file-conditional-formatting
根据Excel总行数自动切换Parquet加速读取，计算特定维度的时间序列平均值，并使用openpyxl输出带有条件格式（如低于均值标绿）和自定义样式的分析报告。.
trend-analysis
基于多维度数据进行分级评估与趋势预测，通过设定差异化增长率计算预测值，并生成对比可视化图表，适用于绩效评估、目标设定等场景。.
outlier-detection-and-quality-assessment
执行全面的异常值检测与数据质量评估，利用 IQR 方法识别异常值并结合偏度、峰度分析数据分布特征，适用于非正态分布数据的预处理阶段。.
pie-chart-data-analysis
Step1 读取文件并统计所有 Sheet 的行数，确认数据规模以决定处理策略。.
multi-sheet-reading-and-analysis
用于读取多工作表Excel文件，动态评估数据量以启用Parquet大文件优化，并执行正则清洗、分类汇总、线性拟合及生成带格式的图表与结果文件。.