Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Artbull Visual Analysis

ASecurity

Use when performing the close visual and formal analysis that anchors an Art Bulletin article — describing and interpreting composition, form, medium, facture, scale, and viewing conditions of specific works, tied to numbered figures. Close looking is the discipline's core method. Guides the analysis; it does not invent what is not in the object.

1,052 stars
0 votes
0 copies
0 views
Added 6/5/2026
ai-agentsreact

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill artbull-visual-analysis --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Artbull Visual Analysis?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Artbull Visual Analysis
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-artbull-visual-analysis/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-artbull-visual-analysis)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: artbull-visual-analysis
description: Use when performing the close visual and formal analysis that anchors an Art Bulletin article — describing and interpreting composition, form, medium, facture, scale, and viewing conditions of specific works, tied to numbered figures. Close looking is the discipline's core method. Guides the analysis; it does not invent what is not in the object.
---

# Visual & Formal Analysis (artbull-visual-analysis)

Close looking is the **method that distinguishes art history**. An Art Bulletin article must make the
reader *see* the work and then show how what is seen carries meaning. Every visual claim must be
checkable against a **numbered figure** the reader can hold in view — which is why this skill is
inseparable from `artbull-images-and-permissions`.

## When to trigger

- Writing the close-analysis passages that anchor the argument
- Moving from formal description to interpretation (form → meaning)
- Deciding which works, details, and comparanda must be reproduced as figures
- A reviewer said the looking is "thin," "impressionistic," or "not supported by the image"

## Doing the looking

1. **Describe precisely, then interpret.** Composition, line, color, light, space, scale, format,
   medium, and **facture** (handling, surface, marks of making) — then say what the description
   *means* for the argument. Description without interpretation is a caption; interpretation without
   description is assertion.
2. **Tie every claim to a figure.** "Figure 3 shows…"; if a detail carries weight, reproduce a
   **detail crop** so the reader can verify it. No visual claim without a visible warrant.
3. **Attend to the material object.** Original scale, support, technique, condition, and later
   alteration matter — a reproduction flattens them, so name what the image cannot show.
4. **Use comparison deliberately.** Comparanda should do argumentative work (attribution, influence,
   convention, difference), not decorate. Each comparison is a figure that earns its slot.
5. **Reconstruct viewing conditions.** Original site, scale, light, ritual or social use, and
   beholder position often change the reading — make these explicit where they bear on meaning.
6. **Respect the limits of looking.** Distinguish what the object shows from what documents or context
   supply (see `artbull-evidence-and-sources`); do not over-read style into intention.

## Anti-patterns

- Adjective-piling ("powerful," "dynamic") that describes your reaction, not the work
- Visual claims with no figure, or claims a reader cannot see in the supplied image
- Treating a reproduction as the object — ignoring scale, surface, and condition
- Comparanda chosen for prestige rather than argumentative necessity
- Reading biography or intention directly off the brushwork without warrant

## Output format

```
【Work + figure】what is reproduced, figure number
【Description】composition / medium / facture / scale (precise)
【Interpretation】what the looking means for the thesis
【Detail crops needed】which details must be reproduced to verify the claim
【Comparanda】each comparison + the work it does
【Next】artbull-evidence-and-sources
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — high-resolution image sources, IIIF deep-zoom, technical imaging
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — figure/caption conventions and the 20-illustration limit

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →