Menü
TDD-based code implementation for analysis pipeline and infrastructure
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Reference for configuring, launching, and monitoring research iteration loops and analysis polish loops
Verifies the analysis pipeline runs end-to-end, outputs match expectations, and LaTeX compiles
Hands-on QA of the research analysis pipeline. Use whenever the user asks to verify the pipeline end-to-end, check output file integrity, validate table and figure generation, test data processing, or verify LaTeX compilation. Triggers on phrases like "test the pipeline", "QA the analysis", "check the outputs", "verify the tables", "run end-to-end", "does the paper compile", or any request to validate a research pipeline.
Define research question, hypotheses, methodology outline, and literature gap
Decompose a research question into cook-it-ready epic beads with methodology specifications
Comprehensive playbook for building rigorous, publication-quality research papers. Covers the full research output sequence from paper structure and statistical reporting through table formatting, figure design, LaTeX conventions, academic writing quality, and pre-submission review.
| name | Work Code |
| description | TDD-based code implementation for analysis pipeline and infrastructure |
Execute code tasks using strict Test-Driven Development. Write tests first, then implement the minimum code to pass them. This sub-skill is invoked by the work router -- it does not run standalone.
Deploy test-writer + implementer agents via AgentTeam:
.claude/skills/drl/agents/test-writer/SKILL.md -- writes tests from acceptance criteria.claude/skills/drl/agents/implementer/SKILL.md -- writes the minimum code to pass testsSpawn the test-writer agent:
tests/ following existing patterns (conftest.py for fixtures)test_<behavior>_<condition>_<expected>Run the test suite to confirm tests fail for the right reason (missing implementation, not syntax errors):
uv run python -m pytest tests/<test_file>.py -v
Spawn the implementer agent:
uv run python -m pytest{{QUALITY_GATE_TEST}} passes (full test suite green){{QUALITY_GATE_LINT}} passes (no lint violations)src/data/src/analysis/src/visualization/src/orchestrators/