eda-research-chain
Run a full EDA research chain from knowledge exploration and paper triage to idea debate, hypothesis experiment design, implementation, git versioning, validation, and retrospective.
EDA Research Chain
When to use
Use this skill when the user asks for an end-to-end research workflow, not a single isolated experiment step.
Scope
This skill orchestrates the full chain and delegates each stage to specialized skills.
Global governance still follows AGENTS.md.
Stage flow
- Bootstrap chain workspace:
python3 scripts/common/init_research_chain.py --tag <tag>
- Knowledge exploration:
- use
eda-knowledge-explorerto map local knowledge gaps, - produce
01_knowledge/knowledge_gap_map.md.
- Literature retrieval + local parsing:
- use
eda-paper-fetchto generate download queue, - use
eda-pdf-local-summaryafter local PDFs are available, - produce
02_literature/paper_download_queue.tsvand02_literature/local_paper_summary_index.md.
- Idea brainstorming and debate:
- use
eda-idea-debate-lab, - produce
03_idea_debate/idea_brainstorm.mdand03_idea_debate/pro_con_debate.md.
- Hypothesis -> experiment design:
- use
eda-hypothesis-experiment-designer, - run
eda-preflight-reflectbefore expensive submissions, - produce
04_hypothesis_design/hypothesis_experiment_matrix.tsv.
- Method implementation:
- use
eda-method-implementer, - produce
05_implementation/implementation_plan.md.
- Multi-version development and integration:
- use
git-version-control, - produce
06_versioning/version_plan.mdand version delta notes.
- Validation and decision:
- execute via
eda-loop, - use validation tools/skills (
delay-model-gate-evaluator, execution contract), - produce
07_validation/validation_summary.md.
- Retrospective:
- use
eda-retro, - produce
08_retro/research_retro.md.
- Version milestone summary slides (conditional):
- do not generate slides for every process stage by default.
- generate a PDF summary only when a new version achieves a validated milestone improvement (e.g., first reach
>=2%power reduction with non-worse area/timing, then higher milestones). - summary should include: method delta, key conclusion, evidence table, and next-step plan.
- Guard completeness:
python3 scripts/common/research_chain_guard.py --chain-dir <chain_dir> --out-prefix <prefix>
Hard rules
- Do not skip the hypothesis design stage before implementation.
- Do not promote a method without explicit validation artifact.
- Keep each stage artifact path explicit and auditable.
- If critical guard checks fail, block chain completion.
Reference
Load when needed:
references/chain-checklist.md