skills/eda-infra-maintainer/SKILL.md
Maintain and evolve the EDA infrastructure stack (agent policy, knowledge base, tool registry, and skill system) with auditable guardrails and minimal-risk updates.
npx skillsauth add biswajit56546/edagent eda-infra-maintainerInstall 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 user asks to:
knowledge_base, tool_registry, skills, agent policy),init_research_chain, research_chain_guard, chain templates/skills).This skill owns infrastructure governance and integrity. It does not own domain experiment conclusions (timing/power/route/model physics).
use: consume existing infra only.maintain: repair consistency/integrity.develop: add infra capability with boundary + rollback note.python3 scripts/common/infra_stack_guard.py --out-prefix slurm_logs/00_meta/infra_stack_guard_<tag>
python3 scripts/common/skill_system_audit.py --out-prefix slurm_logs/00_meta/skill_system_audit_<tag>
python3 scripts/common/tool_catalog.py query <keyword1> <keyword2>
python3 /home/grads/d/donghao/.codex/skills/.system/skill-creator/scripts/quick_validate.py <skill_path>
Load when needed:
references/maintenance-checklist.mdtesting
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.