adr-writer
Generates Architecture Decision Records capturing context, rationale, alternatives, and consequences in numbered status-tracked format. Triggers on: "write an…
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my
$ npx -y skills add Mathews-Tom/armory --skill manuscript-typography --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/manuscript-typographyContext preview
The summary Claude sees to decide when to auto-load this skill.
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my
name: manuscript-typography description: 'Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic review", "make it look professional", "check tables", "fix captions". Companion to manuscript-review (content) and arxiv-preflight (compliance).' metadata: version: 1.0.0 complements: [manuscript-review, arxiv-preflight, figure-table-quality] category: review tags: [typography, latex, formatting, booktabs, polish] difficulty: advanced phase: review
**Pipeline position:** Phase 2b (polish audit). Runs in parallel with manuscript-provenance. Depends on: content settled after Phase 1 fixes. See `/manuscript-pipeline` for full execution order.
Audit a LaTeX manuscript for widely-accepted academic typographic conventions that directly affect readability and professional appearance. These are not venue-specific formatting rules — they are cross-venue norms from decades of academic publishing that experienced readers and reviewers notice.
A paper with solid content but poor typography signals inexperience. Reviewers form impressions from visual presentation before reading a single sentence.
| Concern | manuscript-review | manuscript-typography (this) | arxiv-preflight | |---------|-------------------|------------------------------|-----------------| | Table content | Data quality, significant figures (§12) | Design: booktabs, alignment, headers, caption placement | Format compliance | | Figure content | Colorblind, axis labels, chartjunk (§12) | Design: font matching, backgrounds, subfigure style | Format/size compliance | | Rendered output | Legibility, float proximity, page breaks (§23) | Layout: widows, column balance, spacing, float specifiers | N/A | | Math notation | Notation consistency, operator formatting (§15) | Spacing, delimiter sizing, display vs inline choices | N/A | | Cross-refs | Citation hygiene (§11) | Reference style consistency, non-breaking spaces | N/A | | Typography | N/A | Dashes, quotes, units, micro-typography | N/A | | Polish | N/A | TODOs, placeholders, metadata, bookmarks | N/A |
**Rule:** This skill audits design and typography. manuscript-review audits content and communication. arxiv-preflight audits submission compliance. No overlap — each reads different signals from the same document.
Read all `.tex` files (main + `\input`/`\include` targets). Identify:
If compiled PDF is available, use it for rendered inspection checks.
For each check:
---
**1.1 Rule structure**
% BAD
\begin{tabular}{|l|c|r|}
\hline
Method & Accuracy & F1 \\
\hline\hline
Ours & 0.94 & 0.91 \\
\hline
\end{tabular}
% GOOD
\begin{tabular}{lcr}
\toprule
Method & Accuracy & F1 \\
\midrule
Ours & 0.94 & 0.91 \\
\bottomrule
\end{tabular}**1.2 Column alignment**
**1.3 Header formatting**
**1.4 Best-result indication**
**1.5 Table notes**
**1.6 Caption placement**
**1.7 Caption formatting**
\usepackage[font=small, labelfont=bf]{caption}
% label ("Table 1:") = bold, description = \small
% applies uniformly to all figures AND tables**1.8 Caption style**
**1.9 Spacing**
Curated, production-grade skills, agents, hooks, rules, commands, utilities, and presets for AI coding agents. No magic, no demos — battle-tested workflows built for developers who use AI seriously.
Repo: Mathews-Tom/armory
Generates Architecture Decision Records capturing context, rationale, alternatives, and consequences in numbered status-tracked format. Triggers on: "write an…
Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python SDK, claude -p, SDK MCP servers, hooks,…
Audits and enhances FastAPI and REST API documentation: missing descriptions, response codes, examples, docstrings, Pydantic models, OpenAPI spec. Triggers on:…
Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or hand-drawn generic icons for everything else.…
Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on:…
Optimize and prepare figures for arXiv submission: format conversion (EPS/PDF/PNG/JPG), size reduction, metadata stripping, processor compatibility (DVI vs…