菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
Manage and standardize project conda environment usage as an auxiliary utility skill, including env discovery, package availability checks, explicit env selection, and reproducible `conda run -n ...` integration for scripts and workflows.
| name | workflow-research-chain |
| description | 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. |
Use this skill when the user asks for an end-to-end research workflow, not a single isolated experiment step.
This skill is the workflow owner for the full research chain and delegates each stage to specialized skills.
Global governance still follows AGENTS.md.
workflow-scoped-execution is not the owner of this workflow. It is only a delegated subworkflow when one chain stage needs governed execution.
Provide or derive:
eda-context-accessor.eda-context-accessor returns kb_feedback_decision != none, carry that feedback into chain artifacts and schedule KB/infrastructure follow-up instead of dropping it.control-knowledge-explorer when evidence is fragmented or stale and needs deeper gap mapping rather than simple context loading.docs/knowledge_base/90_HYPOTHESIS_VALIDATION_LOG.md for tested hypotheses,eda-experiment-phenomenology-analyst so later chain stages and future chains can reuse result/conclusion/experience artifacts without reparsing raw logs.Run a full research chain to explore gate-sizing strategies for power reduction on the skywater130 PDK.
This should trigger the full workflow: chain setup, knowledge-gap mapping, literature retrieval and summarization, idea debate, hypothesis design, implementation, git-based versioning, validation, and retrospective closeout.
Load when needed:
references/chain-checklist.md when checking required stage artifacts or deciding whether the chain can be considered complete.references/stage-flow.md when you need the concrete stage order, delegated skill at each stage, or the required artifact path for a stage.references/milestone-reporting.md when deciding whether a validated improvement is strong enough to justify milestone summary output.