marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
Micah Martin's Absolute Priority Premise - an improvement on the Transformation Priority Premise that provides objective heuristics to compare code quality by assigning mass values to code components.
marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
Special greeting to celebrate codecentric and AI Powered Working events. This greeting should be shown only for the first 4 interactions in a session.
marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
These rules ensure the human stays engaged and can provide guidance at critical decision points during Test-Driven Development. The AI should pause and explicitly ask for user feedback in these specific situations.
marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
Kent Beck's Four Rules of Simple Design - fundamental principles for writing clean, maintainable code. These rules are applied in priority order and work synergistically with TDD.
marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
TDD practices will feel counterintuitive and uncomfortable.
marcoemrich/mad-tdd-mob-ai-driven
Cursor rule Cursor
Best practices and conventions for TypeScript development in this workspace, including module imports, testing framework usage, and file naming conventions.
marcoemrich/EXACT-Coding-Exercises
Agent Claude Code
TDD Refactor Phase specialist - applies Simple Design Rules and Absolute Priority Premise to improve code. Use this agent after Green phase to refactor while keeping tests green.\n\nExamples:\n\n \nContext: User completed Green phase with passing tests.\nuser: "Let's refactor the code"\nassistant: "I'll use the Task…
marcoemrich/EXACT-Coding-Exercises
Command Claude Code
You are now in the Green Phase of TDD. Follow these instructions to make the failing test pass with MINIMAL code.
marcoemrich/EXACT-Coding-Exercises
Command Claude Code
You are now in the Red Phase of TDD. Follow these instructions to activate ONE test and make it fail.
marcoemrich/EXACT-Coding-Exercises
Command Claude Code
You are now in the Test List Phase of TDD. Follow these instructions to create a comprehensive test list.
marcoemrich/EXACT-Coding-Exercises
Settings file Claude Code
Agent settings declaring 14 allowed tools.
marcoemrich/EXACT-Coding-Exercises
Skill Claude CodeCodex
Final metric-driven refactoring pass over the whole production tree, using ESLint smells, SonarJS cognitive complexity, McCabe and APP mass to drive one measured change at a time. Invoke when the user explicitly asks for a final cleanup, a quality pass over the finished code, or an end-refactor. Do NOT invoke…
marcoemrich/EXACT-Coding-Exercises
Skill Claude CodeCodex
Collaborative Example Mapping session (Matt Wynne) to explore a feature before implementation — discovers rules, concrete examples, open questions and out-of-scope stories through conversation. Invoke when the user explicitly asks for Example Mapping, wants to explore or clarify requirements before coding, or asks to…
marcoemrich/EXACT-Coding-Exercises
Skill Claude CodeCodex
Strict Test-Driven Development workflow (Red-Green-Refactor) with configurable human-in-the-loop checkpoints. Invoke when the user explicitly asks to use TDD, do a TDD kata, or follow the Red-Green-Refactor discipline. Do NOT invoke for general coding tasks where the user has not asked for TDD.
marcoemrich/agentic_coding_lab
Hook Claude Code
Runs when a session starts, running an inline shell check. From marcoemrich/agentic_coding_lab.
marcoemrich/agentic_coding_lab
Settings file Claude Code
Agent settings declaring 1 hook event (SessionStart).
marcoemrich/agentic_coding_lab
Skill Claude CodeCodex
Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.
marcoemrich/agentic_coding_lab
Skill Claude CodeCodex
Mint a new exact-coding-baseline-YYYY-MM-DD snapshot under research/workflow-dev/export/. Detects the current best correctness- oriented workflow from research/workflow-dev/workflow-construction.md (or takes an explicit source-workflow argument) and transforms it from a lab workflow into a consumer-ready one on three…
marcoemrich/agentic_coding_lab
Skill Claude CodeCodex
Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the fresh data. Trigger when the user says "reanalyze RQ-N", "reanalyse RQ-N", "Runs neu analysieren", or wants to refresh metrics/findings after a pipeline change (analyze-run.sh fix, adapter added…
marcoemrich/agentic_coding_lab
Skill Claude CodeCodex
Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start the Docker batch in the background, monitor progress, run aggregation, and propose findings updates. Trigger when the user says "RQ-N voranbringen", "run-rq", "fill RQ-N", "run RQ-N", "Forschungsfrage…
marcoemrich/agentic_coding_lab
Command
Generate experiment-overview snapshot.
marcoemrich/agentic_coding_lab
Command
Export a new exact-coding baseline snapshot.
marcoemrich/agentic_coding_lab
Command
Re-run analysis pipeline for an RQ.
marcoemrich/agentic_coding_lab
Command
Run a research question end-to-end.