已通过物理实现AUD-AAE504A2C2

拥塞与 ECO 规划

基于 placement/routing 拥塞、timing、fanout 和 ECO 约束生成低风险优化计划，区分 RTL、约束、floorplan 与后端策略动作。

查看 Skill 详情

Benchmark

87.1%

通过率

检查项

low

风险等级

自动检查

SKILL.md format and section validation

通过

skills/congestion-eco-planner/SKILL.md

Required frontmatter and sections are present.

Hardcoded secret scan

通过

skills/congestion-eco-planner

No private key, cloud key, token, or long generic secret matched.

High-risk behavior scan

通过

skills/congestion-eco-planner

No recursive deletion, cloud metadata access, encoded shell, or unreviewed transfer matched.

Declared dependency inventory

通过

skills/congestion-eco-planner

No runtime dependency manifest is included in this Skill package.

Sandbox dry-run readiness

通过

skills/congestion-eco-planner

Package is documentation/reference only, so runtime sandbox is marked as dry-run ready.

Benchmark evidence completeness

通过

skills/congestion-eco-planner/SKILL.md

Score 84, level B+, pass rate 87.1%.

Human review gate

通过

skills/congestion-eco-planner/SKILL.md

Status is reviewed.

Benchmark 套件

Format and metadata fixtures5/6

content/audit/evidence/congestion-eco-planner/bm-fmt.json

IC workflow scenario cases14/16

content/audit/evidence/congestion-eco-planner/bm-scenario.json

Safety and guardrail cases5/6

content/audit/evidence/congestion-eco-planner/bm-safety.json

Regression and replay cases3/4

content/audit/evidence/congestion-eco-planner/bm-regression.json

包盘点

Package hash: sha256:eco10084
Files: 1
Executables: 0
Decision: publishable