Menu
Execute one scoped EDA task under governed gates: run bootstrap checks, validate artifacts, and return execution evidence.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Creates and refines academic presentations from research papers. Use this skill for tasks involving the conversion of scientific or technical documents into slide decks for conferences, seminars, lectures, thesis defenses, or academic reviews. Supports beamer LaTeX (.tex), PowerPoint (.pptx), and Markdown output formats.
Execute delay-model validation gates against HPWL baselines. Use when evaluating model consistency, running Gate-0 contract checks, building Gate-1 bucketed scorecards, performing wirelength-aware correlation checks, or deciding readiness for active optimization.
Run a full EDA research chain from knowledge exploration and paper triage to idea debate, hypothesis experiment design, implementation, git versioning, validation, and retrospective. Use when the user requests an end-to-end EDA research workflow rather than a single isolated execution step.
Audit and refine academic manuscripts for structure, terminology consistency, LaTeX hygiene, and high-signal grammar fixes. Use this skill for theses, papers, proposals, and technical reports when the task is manuscript writing rather than experiment execution.
Diagnose and implement backside-routing realization paths, including targeted reroute, local DEF/OpenDB patching, and OpenROAD-backed net-level rerouter bring-up, when theory predicts benefit but the current flow does not realize BM2/BM1 usage.
Audit whether the local BSPDN physical contract is coherent across paper assumptions, GT3 tech collateral, layer/via topology, and current flow policy before promotion or expensive attribution experiments.
| name | workflow-scoped-execution |
| description | Execute one scoped EDA task under governed gates: run bootstrap checks, validate artifacts, and return execution evidence. |
workflow-scoped-execution is the scoped execution workflow owner.
It owns:
It does not own:
workflow-scoped-execution should be used only when:
Use workflow-scoped-execution for experiment, debug, flow, baseline, handoff, monitoring, or infrastructure tasks that already have a scoped execution brief and need explicit gates and artifacts.
Provide or derive:
eda-context-accessor instead of re-specifying retrieval logic locally.eda-context-accessor returns kb_feedback_decision != none, record that feedback in the execution summary and route KB/infrastructure follow-up to eda-infra-maintainer when the change is not purely local.workflow-scoped-execution focused on execution hygiene:scripts/common/knowledge_gate.sh for governed execution startup,slurm_logs/00_meta/knowledge_tool_maintenance_log.md,docs/knowledge_base/90_HYPOTHESIS_VALIDATION_LOG.md when a hypothesis was actually tested.log -> result -> conclusion -> experience extraction to eda-experiment-phenomenology-analyst before handing off to control-postrun-retro or a future control-theory-veto.scripts/debug/progress_monitor.py or scripts/debug/progress_monitor.sh) over ad hoc markdown.vanilla_replace as primary baseline.Return or update:
Load only the parts needed for the current task:
references/workflow-scoped-execution-checklist.md when starting or closing a normal workflow-scoped-execution execution and you need the full bootstrap/pre-submit/post-run checklist.references/execution-gates.md when the task involves submission gating, route/CTS preflight, testcase-backed DC/Innovus checks, or root-cause mode for non-convergence.references/output-and-stop-policy.md when deciding whether the task is complete, whether reporting is sufficient, or whether a hard-stop condition blocks closeout.references/postrun-improvement.md when the current loop exposed a repeated execution gap and you need to decide the smallest acceptable improvement action.