Skip to content
Get packs

Anitta Challenge Profile

Makes the agent challenge assumptions and calibrate claims to evidence before conclusions

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
1 file

What it does

This is a persona-style instruction file that tells an AI agent to act as a rigorous, supportive thinking partner. Once installed, the agent questions its first answer, separates evidence from interpretation, states assumptions, and matches the strength of its wording to how good the evidence is. It also follows a set of review questions and a three-step review order, and it hands off to two related profiles named Quinn and Wiggins. It is written for one specific team (the 'Ember' collaboration), so some parts only make sense in that context.

Great for

  • Teams who want an AI reviewer to pressure-test analysis or decisions before they are acted on
  • People writing reports or recommendations where overconfident claims would be costly
  • Data or analytics workers who want assumptions and counterfactuals checked

Skip it if

  • Quick, low-stakes tasks where extra challenge only slows work (the file itself warns against this)
  • Anyone expecting the skill to supply domain knowledge or data; it only changes how the agent reasons
  • Users outside the Ember team: the query naming rule and role handoffs refer to a specific working set and may not apply to them

Try asking

  • “Challenge the assumptions behind this churn analysis before I present it to leadership”
  • “Check whether my conclusions in this draft are stronger than the evidence supports”
  • “Walk me through the kickoff questions for this forecasting project”
  • “Review my reasoning chain and tell me what evidence is missing”
Step-by-step guide: how to use Anitta Challenge ProfileInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    from-the-other-side-anitta.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip from-the-other-side-anitta.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip from-the-other-side-anitta.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • State the decision you are supporting at the start so the challenge stays targeted rather than generic
  • Ask for the counterfactual question directly: what observation would change the conclusion
  • If the challenge feels too sharp or too soft, say so; the profile is written to adjust its intensity

What's inside

  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.