AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Gt3 Backside Net Selector

skill-mr-fang-vlsi-edagent-gt3-backside-net-selector · by Mr-Fang-VLSI

Select backside-routing candidate nets after placement/postCTS using power-first criteria with timing-safety vetoes. Use when the task is to build or validate reusable net lists/patterns for targeted GT3 backside reroute, especially when dynamic-power reduction is the primary objective.

No reviews yet
0 installs
26 views
0.0% view→install

Install

$ agentstack add skill-mr-fang-vlsi-edagent-gt3-backside-net-selector

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-mr-fang-vlsi-edagent-gt3-backside-net-selector)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Gt3 Backside Net Selector? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

GT3 Backside Net Selector

Role Boundary

This skill owns net-selection only:

  • consume placement/postCTS DEF and existing scorer evidence,
  • run a power-first candidate screen,
  • emit reusable net lists/patterns for targeted backside reroute,
  • summarize why nets were selected.

This skill does not own:

  • actual reroute execution,
  • CTS/route submission,
  • final PPA claims.

Those remain in gt3-backside-route-policy and workflow-scoped-execution.

Use This Skill When

Use it for requests such as:

  • "which nets should be moved to backside?"
  • "select backside candidates after placement"
  • "use dynamic power as the primary migration criterion"
  • "prepare a targeted backside net list for Innovus reroute"

Inputs

Provide or derive:

  1. a DEF checkpoint (placed.def or postcts.def),
  2. GT3 techlef if scorer PDK timing terms are wanted,
  3. optional criticality/slack file,
  4. optional activity file,
  5. backside capacity contract.

Knowledge And Tool Interaction

  1. If the task needs shared KB/tool lookup before defining selection assumptions, delegate that step to eda-context-accessor.
  2. Use existing scorer evidence and prior route summaries as the primary local evidence source for selector setup.
  3. Record which selector assumptions, capacity contract, and evidence inputs produced the emitted net list.

Output Contract

Return:

  1. selected net list path,
  2. escaped pattern list path,
  3. summary path,
  4. whether selection used real activity or uniform activity,
  5. capacity used vs capacity budget.

Operational References

  1. Load references/default-policy.md when deciding objective priority, timing veto behavior, clock handling, or independence from route submission.
  2. Load references/tool-and-arguments.md when preparing the selector command, optional inputs, or output artifact settings.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.