How do I install the Aidd Refine:02:challenge skill?

Run npx skillmds@latest add ai-driven-dev/aidd-refine-02-challenge in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Aidd Refine:02:challenge safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Aidd Refine:02:challenge?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Aidd Refine:02:challenge free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Aidd Refine:02:challenge?

ai-driven-dev (@ai-driven-dev) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Aidd Refine:02:challenge by ai-driven-dev

Name: Aidd Refine:02:challenge
Author: ai-driven-dev

Aidd Refine:02:challenge

Rethink prior work to verify correctness against an agreed plan, classifying findings as deal-breakers, suggestions, or correct, with a confidence score. Use when the user says "challenge this", "rethink your plan", "is this correct", "review my last decision", "challenge my decision", "challenge what you did", "is my decision right", "criticize this", "find flaws", or asks for a critical review of just-completed work. Do NOT use for line-by-line code review against a style guide, implementing features, writing tests, or generating new code.

ai-driven-dev 6191cca 4 files · 4.1 KB Updated Sep 17, 2026

File contents

Challenge

Rethink prior work and surface what is wrong, missing, or duplicated. Output a structured report with a confidence score so the user knows whether to ship, iterate, or rework.

Available actions

#	Action	Role	Input
01	`challenge`	Rethink prior work, classify findings, score confidence	review_target + agreed_plan

Default flow

Single action skill. The router dispatches to challenge whenever the trigger phrases above appear.

Transversal rules

Think in first principles. Every step must be logical, with no gap and no missing information.
Challenge own assumptions and the user's decisions before declaring confidence.
Look for edge cases, errors, inconsistencies, missing parts, duplications, and optimizations.
Aim for simplifications. If the work can be smaller, say so.
Output the structured report verbatim per the action's ## Outputs block.

References

references/confidence-rubric.md: tiered rubric for the confidence percentage.

Assets

None.

External data

None.

Frequently asked questions