Challenge logo

Challenge

Community
oliver-kriska
challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

Overview

Publisheroliver-kriska
Repositoryclaude-elixir-phoenix
Skill namechallenge
Stars
555
Forks
40
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by oliver-kriska on GitHub. Read the source before you install it.

Installation

Install the Challenge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/claude-elixir-phoenix
mkdir -p .claude/skills
cp -r /tmp/claude-elixir-phoenix/plugins/elixir-phoenix/skills/challenge .claude/skills/challenge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Challenge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Challenge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Challenge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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)

  1. "What Would Break This?" — Production failure modes under load, during deploys, with unexpected data
  2. "Assumption Stress Test" — List every assumption; which are most fragile?
  3. "Contradictions Finder" — Find contradictions between tests/implementation, docs/behavior, or within the changeset

Challenge Modes

Ecto Challenge (/phx:challenge ecto)

Grill the developer on database changes:

Migration Safety

  • Will this migration lock the table in production?
  • What happens to existing records without the new field?
  • Is the migration reversible?
  • Are there any unsafe operations (column removal, type change)?

Query Performance

  • Have you introduced any N+1 queries?
  • Are there missing indexes for new WHERE clauses?
  • Will this query scale with data growth?

Schema Integrity

  • Are all constraints enforced at database level?
  • What happens during rolling deployment (old code, new schema)?
  • Are foreign key cascades correct?

Backward Compatibility

  • Will old code work during deployment?
  • Are there any breaking changes to the context API?

LiveView Challenge (/phx:challenge liveview)

Prove the LiveView handles all cases:

Event Coverage

  • List every handle_event clause and expected socket state
  • What happens if socket assigns are missing when event fires?
  • Are there race conditions between user events and server pushes?

PubSub Handling

  • List every handle_info clause and when it's triggered
  • Do all PubSub subscriptions have corresponding handlers?
  • What happens if a message arrives before mount completes?

State Transitions

  • Show the event → handler → state transition table
  • Are all error states handled gracefully?
  • What's the recovery path from each error state?

Memory & Performance

  • Are large lists using streams?
  • Is transient data using temporary_assigns?
  • What's the memory footprint per connected user?

PR Challenge (/phx:challenge pr)

Senior engineer review checklist:

Must Pass

  • No direct Repo calls in controllers/LiveViews
  • All Ecto queries use explicit preloads
  • Changesets validate all user input
  • No atoms created from params
  • Error cases handled (not just happy path)
  • Tests cover new functionality

Performance

  • No queries in Enum.map loops
  • LiveView streams for lists > 100 items
  • Indexes exist for WHERE clause columns

OTP

  • GenServers have supervision
  • Timeouts set for GenServer.call
  • No unbounded process spawning

Security

  • No SQL injection via raw queries
  • No path traversal in file handling
  • Authorization checks present

Prior Findings Deduplication (MANDATORY)

CRITICAL: Prevents re-discovering identical issues across consecutive runs.

  1. Search .claude/plans/*/reviews/ and .claude/reviews/ for prior findings
  2. Read ALL prior findings before analyzing code
  3. Check each finding against priors:
    • Fixed → SKIP | Still present → PERSISTENT (one line) | New → NEW (full analysis) | Reintroduced → REGRESSION
  4. Present: NEW first (full), then PERSISTENT (one-line), then REGRESSION

Example Challenge Output

markdown
## Challenge: Ecto — Orders Migration

### FINDING 1: Table lock risk (HIGH)
AddColumn on `orders` (2.1M rows) will lock table during deploy.
**Proof needed**: Run `SELECT count(*) FROM orders` — if >1M, use
`ALTER TABLE ... ADD COLUMN ... DEFAULT NULL` (no lock).

### FINDING 2: Missing index (MEDIUM)
New `WHERE status = ?` query on line 45 has no index.
**Action**: Add `create index(:orders, [:status])` to migration.

### Status: BLOCKED — 2 unresolved findings

Usage

Run /phx:challenge [mode] to initiate a rigorous review. The reviewer will not approve until all concerns are addressed with evidence.

Example workflow:

  1. Run /phx:challenge ecto after migration changes
  2. Answer each question with code references or test results
  3. Address all concerns before proceeding to PR

Frequently asked questions

What does the Challenge AI skill do?

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

Why use Challenge on TypingMind?

Because you install it once and use it with any model. Challenge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Challenge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/challenge. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Challenge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Challenge?

As many as you like. As long as a model supports skills, you can use Challenge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Challenge AI skill free?

Yes. It is published on GitHub by oliver-kriska under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇