Clojure work can become fragile when changes are made without fast feedback. This skill guides Claude, Codex, and Claude Code through REPL-first development, style checks, and careful refactoring.

Clojure pull requests can miss project-specific style and architecture rules. This skill gives Claude, Codex, and Claude Code a focused Metabase review checklist.

Metabase endpoints can fail when request and response schemas do not match runtime data. This skill guides accurate Malli schemas using established project patterns.

MCP server work often fails when tools, resources, prompts, widgets, and authentication are mixed without clear patterns. This skill gives Claude, Codex, and Claude Code focused mcp-use guidance for implementation, review, and deployment.

ChatGPT app builders need clear patterns for MCP servers, widget state, and Apps SDK metadata. This deprecated skill provides mcp-use references and migration guidance for interactive widget projects.

Unfamiliar code is hard to change when modules, callers, and domain terms are unclear. This skill prompts Claude, Codex, or Claude Code to explain the broader map before implementation.

Large plans are difficult to divide into independent engineering work. This skill creates approved vertical-slice issues with dependencies, acceptance criteria, labels, and tracker links.

Test-first work often becomes brittle when teams test internals or write too many tests upfront. This skill guides Codex, Claude, and Claude Code through behavior-focused red-green-refactor cycles.

Deep imports expose internal TypeScript package code and weaken architecture. This skill installs dependency-cruiser rules, validates failures, and documents stable entry-point boundaries.

Engineering skills need consistent repository conventions before they can manage work reliably. This skill gathers user choices and creates the required agent guidance files.

Course exercise setup can be slow and inconsistent across sections. This skill helps Claude, Codex, and Claude Code create lint-ready exercise folders with clear variants and readme stubs.

Merge and rebase conflicts often hide competing design intentions. This skill guides Claude, Codex, and Claude Code through research, resolution, validation, and completion.

Large refactors often fail because scope, testing, and sequencing remain unclear. This skill inspects the repository and creates an incremental plan for a GitHub issue.

Bug reports often lack reproducible details and clear scope. This skill clarifies each report, applies project terminology, and files structured GitHub issues.

Design decisions are difficult to evaluate before users can interact with them. This skill builds disposable prototypes that expose state behavior or compare interface variants.

Type assertions can hide incomplete or invalid test fixtures. This skill converts common assertions to Shoehorn helpers while preserving test intent and type feedback.

Architecture reviews often miss shallow modules, scattered decisions, and weak test surfaces. This skill guides AI agents to find practical refactoring opportunities using project language.

Detailed requirements can still produce inconsistent implementation and verification. This skill executes PRD or issue work with regular checks, final testing, review, and commit.

Hard bugs waste time when investigation starts without a reliable reproduction. This skill builds a tight feedback loop, tests hypotheses, and verifies durable fixes.

Hard bugs waste time when teams guess before reproducing the failure. This skill guides Claude, Codex, or Claude Code from reproduction to regression test.