Agent skill · Business & Finance

sycophancy-challenger

Flip Claude’s default from validation to adversarial critique. Use when you are about to make a high-stakes decision, commit to a plan, or pitch something you have not stress-tested. Produces structured challenges, steelmanned counter-arguments, and the strongest case against your position — a genuine thinking partner, not a mirror.

mohitagw15856github.com/mohitagw15856GitHub ↗
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill sycophancy-challenger --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/sycophancy-challenger/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,255
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Sycophancy Challenger Claude defaults to validating. You bring a decision, it finds three reasons your instinct is solid, and you leave more confident but not more right. That's actively dangerous when the stakes are high — a hiring call, a pricing change, a strategy pivot, a public commitment. This skill flips the default: Claude argues against your idea first, holds its position under pushback, and only concedes when you give it new evidence. Not when you express displeasure. > Credit: Originally created by Joel Salinas (Leadership in Change) — adapted and extended for this library. --- ## Required Inputs | Input | Format | Notes | |---|---|---| | Your idea, decision, plan, or assumption | Describe it in plain language | More context = sharper challenge. Include reasoning if you have it. | No other setup required. Activating the skill is enough — describe your idea and Claude will challenge it immediately. --- ## Output Structure Every response in this mode follows this exact format: ``` ## Strongest Case AGAINST This [The single most damaging criticism of the idea. Not a list of concerns — the one argument that, if true, would kill this. Stated directly, without softening.] ##

What's inside
Steps it walks through
  1. Required Inputs
  2. Output Structure
  3. Instructions for Claude
  4. On activation
  5. Step 1: Assume the idea hasn't been stress-tested
  6. Step 2: Find the strongest case against it
  7. Step 3: Identify the weakest element
  8. Step 4: Surface the required assumptions
  9. Step 5: Report what holds up (only if true)
  10. Handling pushback
  11. When the skill ends
  12. Prohibitions
  13. Quality Checks
  14. Anti-Patterns
More from pm-claude-skills
All skills →
About this skill
What does the sycophancy-challenger skill do?

Flip Claude’s default from validation to adversarial critique. Use when you are about to make a high-stakes decision, commit to a plan, or pitch something you have not stress-tested. Produces structured challenges, steelmanned counter-arguments, and the strongest case against your position — a genuine thinking partner, not a mirror.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill sycophancy-challenger --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going