agentic_coding_lab

Generates an experiment-overview snapshot of all research questions under research/_archive/. Invoke when a new point-in-time report across all RQs should be produced.

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 N starten", or names a specific RQ-N directory in research/.

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, ESLint config).

TDD Green Phase - Implement minimal code to make the failing test pass

TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions

TDD Test List Phase - Create a comprehensive test list covering every example and rule from the specification

Generates an experiment-overview snapshot of all research questions under research/_archive/. Invoke when a new point-in-time report across all RQs should be produced.

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), copies it, applies the HITL transformation using the canonical template in this skill, and writes README + VERSION inside .claude/ so the snapshot can be dropped straight into a consumer project. Trigger when the user says "exact-coding baseline export", "neue exact-coding baseline", "exact-coding-baseline-export", or asks to refresh the baseline snapshot.

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, ESLint config).

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 N starten", or names a specific RQ-N directory in research/.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

TDD Green Phase - Implement minimal code to make the failing test pass

TDD Red Phase - Activate ONE test from the test list and make it fail with explicit predictions

TDD Refactor Phase - Improve code while keeping tests green using Simple Design Rules and APP mass

TDD Test List Phase - Create a comprehensive test list covering every example and rule from the specification

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), copies it, applies the HITL transformation using the canonical template in this skill, and writes README + VERSION inside .claude/ so the snapshot can be dropped straight into a consumer project. Trigger when the user says "exact-coding baseline export", "neue exact-coding baseline", "exact-coding-baseline-export", or asks to refresh the baseline snapshot.

TDD Red Phase. Activates exactly one it.todo() test, records compile-error and runtime-error predictions, verifies the test fails for the predicted reason. The prediction block this skill emits is parsed by the experiment's measurement pipeline.

TDD Green Phase. Writes the smallest possible implementation to turn the currently failing test green. Hardcoded returns and obviously-incomplete logic are preferred to over-implementation. No refactoring here.

TDD Red Phase. Activates exactly one it.todo() test, records compile-error and runtime-error predictions, verifies the test fails for the predicted reason. The prediction block this skill emits is parsed by the experiment's measurement pipeline.

TDD Test List Phase. Creates an it.todo() list for a feature, scoped to base functionality (no edge cases, no advanced features). First step of the TDD cycle; invoked once per feature before the red phase.