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

Ci Evidence And Objects

ASecurity

Use to choose and read the objects a Critical Inquiry (CI) essay analyzes — texts, images, artworks, films, performances, events, or cases. In CI the "evidence" is not data but objects read closely through theory; this skill helps select objects that test and earn the intervention and handle images to journal standard. It guides selection and reading; it does not run statistics or build datasets.

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Ci Evidence And Objects?

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

Security grade badge for Ci Evidence And Objects
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-ci-evidence-and-objects/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-ci-evidence-and-objects)

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

Download with Pro
Files
SKILL.md
---
name: ci-evidence-and-objects
description: Use to choose and read the objects a Critical Inquiry (CI) essay analyzes — texts, images, artworks, films, performances, events, or cases. In CI the "evidence" is not data but objects read closely through theory; this skill helps select objects that test and earn the intervention and handle images to journal standard. It guides selection and reading; it does not run statistics or build datasets.
---

# Evidence & Objects (ci-evidence-and-objects)

In *Critical Inquiry* there are **no datasets** — the evidence is **objects read closely**: literary
and philosophical texts, paintings, photographs, films, buildings, performances, archival documents,
political or historical cases. This skill helps you pick objects that actually test the intervention,
read them so the claim is earned, and prepare images to the journal's standard.

## When to trigger

- Choosing which texts/images/cases the essay will read
- An argument that asserts more than its objects can demonstrate
- A reading that is rich but not visibly tied to the claim
- Preparing figures and image permissions for submission

## Choose objects that do work

1. **The object must test the claim.** Pick cases that could in principle resist the argument, not
   only ones that flatter it. A reading earns trust when the object pushes back and the claim survives.
2. **Few and deep over many and thin.** CI prizes close reading; one object read to the hilt beats a
   catalog of examples skimmed. Let the analysis go far into the particular.
3. **Right scale of object.** Match the object to the claim — a single image for a claim about seeing;
   a passage for a claim about a concept's grammar; a case for a claim about a practice.
4. **Interdisciplinary objects welcome.** CI essays routinely cross media — a poem and a painting, a
   film and a treatise — when the juxtaposition earns the conceptual point.

## Read so the claim is earned

- **Show the work.** Walk the reader through the text/image; do not assert what it "obviously" means.
- **Quote and describe precisely.** Exact language, exact visual detail — the analysis lives here.
- **Let the object talk back.** Note the friction, ambiguity, or counter-evidence and incorporate it;
  honesty about the object strengthens the intervention (see `ci-argument-and-intervention`).
- **Tie every reading to the turn.** Each analysis should advance the claim, not display erudition.

## Images to journal standard

- Supply images as **separate files**, **300 ppi**, **JPEG or TIFF** — not embedded in the Word file.
- Keep a numbered **figure list with captions and full credit lines**.
- **Secure permissions** for in-copyright images yourself, before publication — budget time and money
  (see `ci-submission` and `ci-citation-and-style`).
- Use figures the argument reads; an image in CI is an object of analysis, not decoration.

## Anti-patterns

- Cherry-picking only confirming examples; ignoring the recalcitrant object
- A pile of thin examples instead of one deep reading
- Asserting a text's meaning without showing the reading
- Embedding low-res images or leaving permissions to the last minute

## Output format

```
【Objects】the texts / images / cases the essay reads
【Why these】how each tests (not just illustrates) the claim
【Depth check】close reading, not a catalog? [Y/N]
【Counter-evidence】where the object resists, and how handled
【Images】separate 300 ppi JPEG/TIFF + permissions plan
【Next】ci-theory-and-method
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — archives, text and image sources, image-prep specs
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — image format / permissions requirements

Attribution

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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', ...

693161 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 →