micheltlutz

micheltlutz/dev-challenge

Agent Claude Code

Reviews a learner's challenge solution against its acceptance criteria and coaches them toward the fix without writing it. Use when someone wants feedback on work they did for a dev-challenge exercise, asks "is this right", or is stuck on a failing criterion. Do NOT use when they have explicitly asked for the…

micheltlutz/dev-challenge

Agent Claude Code

Audits a change to the dev-challenge spec layer before it is committed — checks specs against the OpenAPI contract, criterion IDs against harness coverage, and internal consistency across specs, code and fixtures. Use when specs/ has been edited, when API behaviour changed, or when spec-drift CI is failing and the…

micheltlutz/dev-challenge

Command Claude Code

Start work on a dev-challenge exercise — loads its spec, criteria and design tokens.

micheltlutz/dev-challenge

Command Claude Code

Suggest which dev-challenge exercise to do next.

micheltlutz/dev-challenge

Command Claude Code

Run the verification harness and explain the results as acceptance criteria.

micheltlutz/dev-challenge

Settings file Claude Code

Agent settings declaring 9 allowed tools.

micheltlutz/dev-challenge

Skill Claude CodeCodex

Run the spec-driven loop for a dev-challenge exercise — read the spec and its acceptance criteria, clarify ambiguity, plan, build, verify with the harness, iterate on failing criteria. Use whenever someone is working through a challenge from specs/challenges/, mentions a challenge id like backend-05-balance or…

micheltlutz/dev-challenge

Skill Claude CodeCodex

Compare an implemented UI against the dev-challenge design tokens and mockups — colours, type scale, spacing, layout and the required testids. Use when someone asks "does this match the design", wants a design review of a screen they built, is working on a web or mobile challenge's visual fidelity, or asks which…

micheltlutz/dev-challenge

Skill Claude CodeCodex

Add or change a challenge in the dev-challenge spec layer — frontmatter, acceptance criteria with stable IDs, the matching harness test, and the validation that keeps them in sync. Use when someone wants to add a new challenge or track, edit an existing spec or acceptance criterion, change API behaviour that a spec…

micheltlutz/dev-challenge

Cursor rule Cursor

Mirror of AGENTS.md. Read that file for the full picture.

micheltlutz/dev-challenge

Instructions file GitHub Copilot

Instructions for micheltlutz/dev-challenge, covering github copilot instructions, which job are you doing?, the spec layer is the source of truth, layout and commands.

micheltlutz/dev-challenge

MCP server Claude CodeCodexCursor +2

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot. Runs locally from the figma-developer-mcp npm package. Needs 1 environment variable to run.

micheltlutz/dev-challenge

Instructions file CodexOpenCode

Instructions for micheltlutz/dev-challenge, covering agent instructions, first: which job are you doing?, job a — helping someone do a challenge, job b — improving the lab itself and the spec layer is the source of truth.

micheltlutz/dev-challenge

Instructions file

Instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.