Install
$ agentstack add skill-mr-fang-vlsi-edagent-bspdn-physical-contract-auditor ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
BSPDN Physical Contract Auditor
Use this skill when the question is not "did the run improve QoR?" but "is the physical/topological contract behind the run actually coherent?"
When to use
Use this skill when:
nTSV / BPR / BM1 / BM2 / M0 / M1connectivity assumptions need to be checked,- a paper claim and the local GT3/PDK expression may disagree,
- a backside conclusion might be invalid because the local physical contract is unclear,
- a topology-validity gate is needed before expensive experiments or paper-grade claims.
Scope boundary
This skill owns:
- physical-contract auditing for backside topology assumptions,
- mapping paper-side claims to local techlef / layer-index / via-rule reality,
- identifying whether the current local PDK expression is decision-complete enough for experiments,
- producing a clear
GO / CONDITIONAL / NO-GOstyle topology judgment.
It does not own:
- general workflow routing,
- full experiment execution ownership,
- PDN sufficiency batch execution,
- final benefit attribution by itself,
- rewriting GT3 routing policy without evidence.
Core questions
- Is
BPRstill best interpreted as PDN-only in the local flow? - Does the local stack really support
BM2 -> BM1 -> M0 -> M1for signal entry? - Is there any evidence for a direct
BM1 -> M1shortcut? - Do current techlef / via rules / run-time layer indices match the paper narrative closely enough to support mechanism claims?
Expected outputs
Emit the smallest useful audit package:
*.topology_audit.md*.topology_matrix.tsv- optional
*.experience_delta.mdwhen a reusable physical-contract lesson is learned
Hard rules
- Do not promote a connectivity assumption from "likely" to "fact" without explicit tool or collateral evidence.
- Keep paper claims and local PDK claims separate until they are reconciled.
- When the local stack is incomplete or ambiguous, prefer
CONDITIONALplus micro-test over false certainty. - If the local collateral contradicts the intended paper narrative, surface the contradiction explicitly instead of silently forcing policy.
Operational references
- Load
references/background-knowledge-links.mdfor the current summarized knowledge contract and its KB anchors. - Load
references/update-mechanism.mdwhen deciding whether the knowledge summary or local assumptions must be refreshed.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Mr-Fang-VLSI
- Source: Mr-Fang-VLSI/EDAgent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.