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/skillmedev/document-studio/data-table-designnpx skills add SkillMedev/document-studio --skill data-table-designgit clone --depth 1 https://github.com/SkillMedev/document-studioWhat 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 | $0.00145 | $0.01437 |
| Opus 5 | $0.00072 | $0.00718 |
| Sonnet 5 | $0.00029 | $0.00287 |
| Haiku 4.5 | $0.00015 | $0.00144 |
Grade A, and why
Data Table Design 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Table Design
A table is not a spreadsheet dump. Every formatting choice either helps or hinders the reader's ability to compare, rank, and interpret - and a misaligned or falsely precise table gets numbers misread in the meetings that matter. The output of this skill is a table a reader can extract the right conclusion from in under ten seconds.
Operating procedure
Step 1: Gather inputs
- The table as it stands (or the raw data), and where it will live: slide, printed report, dashboard, or scrolling web page - the medium changes the density rules in Step 5.
- The reader's single most likely question. Every subsequent decision serves it. If the owner cannot name the question, that is the first problem to fix.
- The action the reader takes from the table. Columns that inform no comparison or action are candidates for deletion.
- Units and the true precision of the data - what the collection method actually supports, not what the export prints.
Step 2: Set alignment
- Right-align all numeric columns without exception - alignment makes magnitude visible at a glance.
- Left-align text columns.
- Center column headers only when the column is narrow and centering does not visually disconnect the header from its values.
- Never mix alignments within a single column.
- Use tabular (fixed-width) figures where the medium allows; proportional digits break vertical comparison.
Step 3: Fix precision
Consistency within a column matters more than absolute precision:
- Currency: two decimal places for unit prices; zero for large aggregates (1,240,000 not 1,240,000.00).
- Percentages: one decimal place unless the context is scientific.
- Large numbers: use K, M, B suffixes with the unit noted in the header rather than printing eight digits.
- If a column mixes scales (most values in thousands, one in millions), flag the outlier with a footnote rather than changing the column format.
- Never imply false precision - round to the significant figures the data actually supports. Survey-based or estimated figures rarely support more than two significant figures; showing four communicates a certainty that does not exist.
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.
- yesterday First seen · 106 lines · 145 tokens per session scan A bbc61e6ea4f1
Data Table Design is a skill published in the GitHub repository SkillMedev/document-studio (1 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 1,437 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
markdown-documents
Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.
writer-documents
Use when creating, opening, or editing LibreOffice Writer ODT documents, or DOCX documents only when Microsoft Word compatibility is explicitly required.
pipefy-reports
Use this skill when the user wants to create, read, update, delete, or export pipe reports or organization reports. Covers the async export workflow (trigger, poll, download). 17 MCP tools.
html-artifact
Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini deck, or for long Markdown-like outputs needing navigation or…
making-academic-presentations
Create academic presentation slide decks and optionally demo videos from research papers.
erpclaw
AI-native ERP system. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting (including P&L / trial balance / spend grouped by department, project, cost center, location, or fund). 496 actions across 14…