Skip to content
Agentmart
Submit a tool

red-teaming

Explicitly invoked only when the user asks to adversarially test a named plan, claim, draft, or decision; attack its premises with evidence and report what…

Skill by DearCaat

IndexedMIT★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dearcaat-red-teaming

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Explicitly invoked only when the user asks to adversarially test a named plan, claim, draft, or decision; attack its premises with evidence and report what breaks or survives.

Use cases: documents, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/red-teaming

What's inside

Skill name
red-teaming
Description
Explicitly invoked only when the user asks to adversarially test a named plan, claim, draft, or decision; attack its premises with evidence and report what breaks or survives.
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Red-teaming

Treat the user-named target as something to break. Choose attack methods freely; do not substitute confirmation for adversarial testing.

## Success conditions

Deliver one of two falsifiable forms:

- **Broken:** list each broken premise or claim, with evidence, actual values, or a failure scenario that can be independently checked.
- **Not broken:** provide an auditable report naming which premises were attacked, what evidence or actual values were checked, and why each survived.

“It looks good” or “basically reasonable” is not a valid result.

## Boundary

Attack only the target named by the user. Report discovered problems honestly; propose fixes only when separately requested.

From DearCaat/research-foundation-skills, MIT.

More from DearCaat/research-foundation-skills

Signals

Stars
4
Forks
0
Open issues
0
Last commit (this folder)
Sep 2, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from DearCaat

Cite this page

red-teaming skill. Agent Mart. https://agentmart.dev/skills/dearcaat-red-teaming (last updated 2026-10-24)