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 Avinava/document-design-system --skill analytical-document-designgit clone --depth 1 https://github.com/Avinava/document-design-systemWrote 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/avinava/document-design-system/analytical-document-design)<a href="https://agentmods.dev/skills/avinava/document-design-system/analytical-document-design"><img src="https://agentmods.dev/badge/skills/avinava/document-design-system/analytical-document-design/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/avinava/document-design-system/analytical-document-design"><img src="https://agentmods.dev/badge/skills/avinava/document-design-system/analytical-document-design.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00156 | $0.02097 |
| Opus 5.5 | $0.00062 | $0.00839 |
| Sonnet 5.5 | $0.00031 | $0.00419 |
| Haiku 4.5 | $0.00016 | $0.00210 |
Grade A, and why
analytical-document-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 21d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytical Document Design
Create documents that help a reader understand what happened, where it is concentrated, why it matters, and what deserves review.
This skill is about the document, not the system that supplies its data. It applies to engineering portfolios, financial reviews, operational audits, inventory analyses, compliance summaries, and product metrics.
The core standard
A strong analytical document has three layers:
- Decision layer — the headline, current state, material risks, notable opportunities.
- Explanation layer — concentration, time, ownership, composition, comparisons.
- Evidence layer — detailed tables, source records, methodology, caveats.
Do not make every fact equally prominent. The document should be understandable in 30 seconds and defensible after 30 minutes. That tension is the whole design problem — a document that only satisfies the first is a poster, and one that only satisfies the second is a data dump.
Workflow
1. Establish the evidence model
Before designing anything, pin down what the numbers actually mean: the unit being measured, the population included and excluded, which values are counts versus estimates, which fields are facts versus inferred classifications, what the dates mean, and whether the dataset is a snapshot or a series.
Write these distinctions into the report. Never depend on the reader guessing them.
Read references/evidence-semantics.md for the full set of distinctions and the traps in each.
2. Reconcile totals
Calculate the control totals before deriving any chart. Included groups must sum to the reported total, excluded populations must appear separately, every percentage needs a named denominator, and rounded labels must not conceal material discrepancies.
Stop and investigate unexplained differences. Styling inconsistent data into apparent authority is the single most damaging thing this skill can do.
3. Derive views that answer distinct questions
Each view should answer something the others do not: current-state ledger, functional concentration, ownership concentration, creation cohorts, recent activity, staleness, version posture, largest units, review candidates.
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.
- core/a11y.md 2.9 KB
- core/base.css 7.5 KB
- core/print.css 4.3 KB
- core/themes/brand-template.css 4.1 KB
- core/themes/console-violet.css 3.5 KB
- core/themes/editorial-coral.css 1.3 KB
- core/themes/executive-navy.css 1.0 KB
- core/themes/field-notes.css 1.0 KB
- core/themes/horizon.css 1.9 KB
- core/tokens.md 8.6 KB
- references/evidence-semantics.md 6.5 KB
- references/implementation.md 3.4 KB
- references/print-production.md 10 KB
- references/quality-gate.md 3.1 KB
- references/visual-system.md 4.6 KB
- scripts/build_document.py 2.7 KB runs code
- scripts/export_pdf.mjs 4.2 KB runs code
- scripts/inline_fonts.py 4.3 KB runs code
- scripts/render_chart.mjs 17 KB runs code
- scripts/render_diagram.mjs 7.6 KB runs code
- templates/document.html 12 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.
- 21d ago Changed · -2 lines 51eaaf4466bf
- 1mo ago First seen · 194 lines · 156 tokens per session scan A 9c8355666c86
analytical-document-design is a skill published in the GitHub repository Avinava/document-design-system (2 stars, last pushed 22d ago), licensed MIT. It adds 156 tokens to every session and 2,097 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
ppt-report-generator
A browser-based presentation tool that turns data and conclusions into 16:9 report slides. It can show slides full screen and export them as a PDF.
design-export-repair
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…
csv-excel-merger
Merges, appends, joins, and deduplicates multiple CSV, TSV, and Excel files (including multi-sheet workbooks) with pandas - mapping mismatched column names to one schema, normalizing keys, resolving conflicting values, tracking which file each row came from, and verifying the row math. Use when the user wants to…
financial-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
brand-consistency-checker
Scan documents and slides for off-brand colors, fonts, and logos. Validate against brand guidelines and suggest corrections.
strategy-consulting-visualization
Use when turning content into clear strategy-consulting visualizations, including board slides, reports, diagrams, quiet animated decks, or explicit dynamic and interactive decks with clickable evidence, scenario controls, what-if sliders, and deterministic presenter demos.