skills/bspdn-physical-contract-auditor/SKILL.md
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.
npx skillsauth add mr-fang-vlsi/edagent bspdn-physical-contract-auditorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when the question is not "did the run improve QoR?" but "is the physical/topological contract behind the run actually coherent?"
Use this skill when:
nTSV / BPR / BM1 / BM2 / M0 / M1 connectivity assumptions need to be checked,This skill owns:
GO / CONDITIONAL / NO-GO style topology judgment.It does not own:
BPR still best interpreted as PDN-only in the local flow?BM2 -> BM1 -> M0 -> M1 for signal entry?BM1 -> M1 shortcut?Emit the smallest useful audit package:
*.topology_audit.md*.topology_matrix.tsv*.experience_delta.md when a reusable physical-contract lesson is learnedCONDITIONAL plus micro-test over false certainty.references/background-knowledge-links.md for the current summarized knowledge contract and its KB anchors.references/update-mechanism.md when deciding whether the knowledge summary or local assumptions must be refreshed.development
Create immutable stage checkpoints for Innovus flows. Use when users ask for fixed golden files or restart-from-stage workflows (place/cts/route) with matched DEF+V+SDC and reproducible manifests.
tools
Capture and maintain reusable script-writing experience across wrappers, helpers, parsers, validators, and runtime shims so future script work can reuse proven patterns and avoid repeated anti-patterns.
testing
Summarize local paper PDFs into structured, citation-grounded evidence notes. Use when the user provides local PDF paths and asks for methods/assumptions/results/limitations extraction or wants evidence mapped to current EDA hypotheses.
development
Fetch primary-source paper metadata when evidence is missing or weak for EDA/model/flow claims. Use for requests like building reproducible paper candidate lists, generating user-download queues, and recording citation metadata for local validation.