AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Bscost Theory Opt

skill-mr-fang-vlsi-edagent-bscost-theory-opt · by Mr-Fang-VLSI

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.

↗ Repository
— No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-mr-fang-vlsi-edagent-bscost-theory-opt

✓ 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.

Are you the author of Bscost Theory Opt? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

BS Cost Theory Opt

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.

Background Knowledge Links

This skill must stay grounded in:

  1. KB workflow and policy context, especially:
  • docs/knowledge_base/80_BSCOST_THREE_SKILL_WORKFLOW_20260304.md
  • docs/knowledge_base/84_REPLACE_COMPARISON_POLICY_20260304.md
  • relevant backside judgment KB notes when applicable.
  1. Paper-derived evidence already summarized into local notes or paper-summary artifacts.
  2. Experiment-experience artifacts from eda-experiment-phenomenology-analyst when related local runs already exposed reusable results, conclusions, or repeated failure patterns.
  3. Scoped retrieval from 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:

  • keep the contradiction explicit,
  • block promotion if the theory basis is no longer defensible,
  • request KB update or overturn follow-up when needed.

Mandatory artifacts

  1. *.dataset.tsv (dataset-level scorecard)
  2. *.per_fold.tsv (fold-level evidence)
  3. *.summary.md with final PASS/FAIL and open risks
  4. include gate mode flag: region_exact vs proxy_mode

Operational References

  1. Load references/background-knowledge-links.md when identifying which KB docs, paper summaries, and theory assumptions are authoritative for the current modeling task.
  2. Load references/theory_formulation.md when locking metric contract, sign convention, and physically meaningful feature blocks.
  3. Load references/optimization_and_gates.md when running repeated validation, HPWL comparison, and promotion gating.
  4. Load references/internet_benchmark_notes.md when extending beyond current datasets and benchmark provenance must be refreshed from primary sources.

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML