skills/eda-stage-checkpoint-golden/SKILL.md
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.
npx skillsauth add biswajit56546/edagent eda-stage-checkpoint-goldenInstall 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 to freeze reusable checkpoints and avoid rerunning all stages.
ROOT=/mnt/research/Hu_Jiang/Students/Fang_Donghao/TAMU-ASAP07-BSPDN-BPR-V0.00
cd "$ROOT"
bash scripts/debug/create_stage_golden_checkpoint.sh \
--design=<design> \
--tag=<golden_tag> \
--tech-profile=<tech_profile> \
--place-run-dir=<run_dir_for_placed_def> \
--cts-run-dir=<run_dir_for_postcts_def> \
--route-run-dir=<run_dir_for_routed_def>
Output root:
regression/stage_checkpoints/<tag>/<design>/Check:
manifest.tsvsha256.tsvrestore_examples.shDo not edit files in an existing tag after creation.
Update a stable symlink when a new golden is approved:
ln -sfn <tag> regression/stage_checkpoints/<design>_stagegolden_current
Use generated restore templates in:
regression/stage_checkpoints/<tag>/<design>/restore_examples.shLoad references/tagging_policy.md for tag naming and source policy.
testing
Apply and validate GT3 backside routing policy in Innovus. Use when configuring CTS/PDN/signal layer usage, submitting GT3 consistency runs, diagnosing zero-backside-nets, or enforcing BPR-reserved-for-PDN constraints.
testing
Use git to version-control local research/EDA iterations with reproducible checkpoints, clear commit/tag structure, and explicit per-version differentiation records. Use when users ask to create baselines, compare versions, snapshot experiment states, prepare rollback points, or document each version's characteristics and distinguishing deltas.
development
Theory-level veto skill for EDA plans. Use before expensive experiment submissions or major flow/model changes to identify logically unsound assumptions, contradiction with known physics/policy, and high-risk invalid comparisons. Produces GO/CONDITIONAL/NO-GO with evidence.
tools
Package the agent+skill infrastructure into a standalone, portable repository-ready bundle with skill-local tool mirrors.