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 Evidence And Sources

ASecurity

Use when assembling and handling the non-visual evidence for an Art Bulletin article — objects, archives, primary documents, provenance, and technical findings — and citing them rigorously. Art-historical claims must rest on verifiable sources, not assertion. Guides evidence handling; it does not fabricate documents or attributions.

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill artbull-evidence-and-sources --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Artbull Evidence And Sources?

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

Security grade badge for Artbull Evidence And Sources
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-artbull-evidence-and-sources/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-artbull-evidence-and-sources)

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

Download with Pro
Files
SKILL.md
---
name: artbull-evidence-and-sources
description: Use when assembling and handling the non-visual evidence for an Art Bulletin article — objects, archives, primary documents, provenance, and technical findings — and citing them rigorously. Art-historical claims must rest on verifiable sources, not assertion. Guides evidence handling; it does not fabricate documents or attributions.
---

# Evidence & Sources (artbull-evidence-and-sources)

Beyond the object itself, an Art Bulletin argument rests on **documentary and material evidence**:
archives, inventories, contracts, letters, sale records, provenance chains, and technical/conservation
findings. This skill governs how you gather, weigh, and cite that evidence so an expert reviewer
trusts it. The looking lives in `artbull-visual-analysis`; here you handle everything else.

## When to trigger

- Building the documentary basis for dating, attribution, patronage, or reception
- Reconstructing a provenance or ownership history
- Weighing conflicting documents or an uncertain attribution
- A reviewer questioned a source, a transcription, or a chain of provenance

## Handling the evidence

1. **Go to primary sources.** Archival documents, inventories, contracts, wills, correspondence,
   sale and exhibition records — cite the **repository, collection, and shelf/inventory mark** so
   another scholar can find them.
2. **Quote and translate carefully.** Give original-language quotations where the wording matters,
   with accurate translations; note editorial interventions in transcriptions.
3. **Build provenance rigorously.** Document the ownership chain with sources for each link; flag
   gaps honestly, and surface any **spoliation / restitution** concerns rather than burying them.
4. **Weigh attribution evidence.** Combine documentary, visual, and technical grounds; state the
   degree of certainty ("attributed to," "circle of," "documented as") and what would change it.
5. **Use technical art history where it bears.** X-radiography, infrared reflectography, pigment and
   support analysis, dendrochronology — cite the report and who performed it; do not overstate what
   science proves.
6. **Distinguish evidence from inference.** Separate what a document *says* from what you *infer*;
   keep silent documents from being made to speak.

## Anti-patterns

- Asserting a date or attribution with no documentary or technical basis
- Citing a source you have not seen (or a digital surrogate as if it were the original) without saying so
- Provenance with unexplained gaps presented as continuous
- Over-claiming what a scientific report establishes
- Burying a restitution / authenticity problem the evidence raises

## Output format

```
【Claim supported】dating / attribution / patronage / reception
【Primary sources】repository + collection + shelf-mark
【Provenance】chain with sources; gaps flagged
【Technical evidence】report + analyst (if any)
【Certainty】documented / attributed / circle-of, and what would change it
【Next】artbull-images-and-permissions
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — archives, provenance indexes, technical-art-history resources
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — Chicago notes citation (CMOS ch. 14)

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 →