🔎
QualityPython

Challenge Mode Reviews

by oliver-kriska

Challenge Mode Reviews is a Quality skill for Claude Code, published by oliver-kriska in claude-elixir-phoenix.

533 stars38 forkson oliver-kriska/claude-elixir-phoenixAdded 2026/08/26+1% in starsRepository updated 2026/08/19
ai-agentsai-coding-assistantautomationclaudeclaude-codeclaude-code-pluginclaude-code-skillsclaude-skillscode-reviewdeveloper-toolsectoelixirelixir-langelixir-phoenixliveviewobanphoenixphoenix-frameworktidewavevibe-coding
Install in seconds
Install Challenge Mode Reviews
Copy Challenge Mode Reviews into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/challenge ~/.claude/skills/challenge

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/oliver-kriska/claude-elixir-phoenix.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/elixir-phoenix/skills/challenge/SKILL.md in oliver-kriska/claude-elixir-phoenix
Installs to
~/.claude/skills/challenge
Collection
One of 25 skills cataloged from this repository
Category
Quality1354 skills

What Challenge Mode Reviews does

Challenge Mode Reviews pushes for rigorous scrutiny before approving changes. Use it to question Ecto migrations, LiveView events, OTP designs, and PR readiness with proof and edge-case checks.

Challenge Mode Reviews is cataloged under Quality on DirSkills. Challenge Mode Reviews comes from a repository tagged ai-agents, ai-coding-assistant, automation, claude and claude-code.

Documentation

README

Challenge Mode Reviews

Rigorous, critical review patterns inspired by Boris Cherny's "Grill me" approach. Push beyond first solutions to ensure quality.

Iron Laws - Never Violate These

  1. No approval without verification - Don't approve until all concerns addressed
  2. Assume bugs exist - Look for edge cases, race conditions, missing handlers
  3. Question everything - Even "obvious" code can hide issues
  4. Demand proof - Ask for tests, show state transitions, verify behavior

Adversarial Lenses (Apply to ALL Modes)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Challenge Mode Reviews

  • What else does oliver-kriska publish alongside Challenge Mode Reviews?

    Challenge Mode Reviews is one of 25 skills that DirSkills catalogs from oliver-kriska/claude-elixir-phoenix, the repository it ships in. Its siblings there include Ash Framework, Autoresearch and Brainstorm. Each one is a separate skill with its own page in this directory, installs the same way Challenge Mode Reviews does, and is maintained by oliver-kriska in that same repository. The rest of the collection is listed on the oliver-kriska/claude-elixir-phoenix page.

  • How does Challenge Mode Reviews compare to other Quality skills?

    Challenge Mode Reviews ranks #1180 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Challenge Mode Reviews against them. Open each page to compare what they document and how they install.

More from oliver-kriska/claude-elixir-phoenix

Challenge Mode Reviews is one of 25 skills cataloged on DirSkills from oliver-kriska/claude-elixir-phoenix.

See all 25 skills
🧩
5d ago

Ash Framework

Ash Framework guides generating and editing Ash resources, actions, policies, validations, and code interfaces in Phoenix and LiveView apps. Use it when working with Ash codegen, domain interfaces, or AshPhoenix.Form.
AI Engineering
53338
🔁
5d ago

Autoresearch

Autoresearch runs a loop that mutates one plugin skill at a time, evaluates it with deterministic checks, and keeps or reverts the change. Use it for targeted or overnight improvement runs.
AI Engineering
53338
💡
5d ago

Brainstorm

Brainstorm gathers and structures Elixir/Phoenix requirements through an interactive interview, then saves an interview.md file for later planning. Use it when an idea is vague, the approach is unclear, or you want to compare options before planning.
AI Engineering
53338
📝
5d ago

Catchup

Catchup summarizes what changed while you were away by collecting recent PRs, commits, Linear tickets, and meetings into one prioritized brief. Use it after time off to review missed work without reading every update.
Automation
53338
📝
5d ago

Claude Code Changelog Assistant

Claude Code Changelog Assistant tracks new Claude Code releases, extracts versions since the last check, and maps breaking changes, opportunities, deprecations, and fixes to plugin components. Use it before releases or on a schedule.
AI Engineering
53338
🔁
5d ago

Codex Loop

Codex Loop runs a bounded Codex CLI review, applies approved fixes, verifies them, and re-reviews until clean or rounds run out. Use it before a PR when you want an external critic on Elixir/Phoenix changes.
Quality
53338