skills/bscost-theory-opt/SKILL.md
Build and validate theory-grounded optimization models for backside front-vs-back net cost (signal and clock), with strict metric contracts and stability gates against HPWL baselines. Use when users request principled model fitting, crossover reasoning, or promotion decisions from shadow mode to active optimization.
npx skillsauth add mr-fang-vlsi/edagent bscost-theory-optInstall 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 task is to move from heuristic cost terms to a validated optimization model that can be promoted only after passing gates.
This skill must stay grounded in:
docs/knowledge_base/80_BSCOST_THREE_SKILL_WORKFLOW_20260304.mddocs/knowledge_base/84_REPLACE_COMPARISON_POLICY_20260304.mdeda-experiment-phenomenology-analyst when related local runs already exposed reusable results, conclusions, or repeated failure patterns.eda-context-accessor when the task needs refreshed KB or paper context before fitting or promotion judgment.If current empirical evidence contradicts the linked background knowledge:
*.dataset.tsv (dataset-level scorecard)*.per_fold.tsv (fold-level evidence)*.summary.md with final PASS/FAIL and open risksregion_exact vs proxy_modereferences/background-knowledge-links.md when identifying which KB docs, paper summaries, and theory assumptions are authoritative for the current modeling task.references/theory_formulation.md when locking metric contract, sign convention, and physically meaningful feature blocks.references/optimization_and_gates.md when running repeated validation, HPWL comparison, and promotion gating.references/internet_benchmark_notes.md when extending beyond current datasets and benchmark provenance must be refreshed from primary sources.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.