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 Argument And Intervention

ASecurity

Use to forge the central argument of a Critical Inquiry (CI) essay into a genuine intervention. CI rewards a bold claim that reorients a conversation in criticism and theory, with stakes that cross disciplines — not a competent reading, a survey, or a method demonstration. Sharpens the thesis and its stakes; it does not fabricate evidence or theory.

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Ci Argument And Intervention?

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

Security grade badge for Ci Argument And Intervention
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-ci-argument-and-intervention/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-ci-argument-and-intervention)

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

Download with Pro
Files
SKILL.md
---
name: ci-argument-and-intervention
description: Use to forge the central argument of a Critical Inquiry (CI) essay into a genuine intervention. CI rewards a bold claim that reorients a conversation in criticism and theory, with stakes that cross disciplines — not a competent reading, a survey, or a method demonstration. Sharpens the thesis and its stakes; it does not fabricate evidence or theory.
---

# Argument & Intervention (ci-argument-and-intervention)

This is the heart of the pack. A *Critical Inquiry* essay lives or dies on its **intervention** — a
claim that changes how readers think, not merely a reading they had not happened to do. Use this skill
to turn an interesting observation into an argument with teeth and stakes.

## When to trigger

- You have objects, theory, and positioning but no single sharp claim
- A reader said the piece is "interesting" but "so what?"
- Drafting the introduction's thesis and stakes paragraph
- Writing a Critical Response, where the whole point is the argumentative move

## What counts as an intervention

A CI intervention does at least one of these, explicitly:

1. **Reconceives** a concept (what we mean by *medium*, *world*, *image*, *freedom*).
2. **Overturns or complicates** a settled reading or critical commonplace.
3. **Crosses a boundary** so that one field's objects reframe another's problem.
4. **Names something new** — coins or reanimates a concept that does analytic work afterward.
5. **Historicizes** a category we took to be natural, showing how it came to be.

State which one (or which combination) you are making — and what is no longer tenable once you are
done.

## Build the claim

- **Thesis in one sentence.** If you cannot say it in a sentence, it is not yet an intervention.
- **Stakes paragraph.** Spell out what changes for readers — and for which fields. CI readers expect
  the "so what" early and ambitiously (see `ci-structure-and-exposition`).
- **The turn.** Identify the moment the essay pivots from setup to claim; everything serves it.
- **Scope conditions.** Say where the claim holds and where it does not — ambition with honesty, not
  overreach.

## Calibrate the ambition

- Too small: a reading with no consequence beyond its object → raise the conceptual stakes.
- Too large: a sweeping pronouncement with no object to test it → anchor it on a case (see
  `ci-evidence-and-objects`).
- Right: a large claim made answerable through a precisely read object and a concept doing work.

## Anti-patterns

- "This essay examines / explores / considers…" framing that promises a survey, not a claim
- Theory paraphrase substituting for an argument of your own
- A reading that is correct but inconsequential
- Over-claiming beyond what the objects can bear
- A Critical Response that summarizes the target instead of contesting it

## Output format

```
【Thesis】one sentence
【Intervention type】reconceive / overturn / cross / name / historicize
【Stakes】what changes, for which field(s)
【The turn】where the essay pivots to the claim
【Scope conditions】where it holds / where it does not
【Next】ci-evidence-and-objects
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — theory shelf for sharpening the conceptual claim
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — CI's "cutting-edge thought" remit and formats

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 →