feat: 完成项目助手与监控演示并修复聊天及云部署配置

backend/skills/risk_evidence/SKILL.md

@@ -1,5 +1,11 @@
 ---
 name: risk-evidence-review
+id: risk.evidence_review
+kind: skill
+version: 1.1.0
+schema_version: 1
+status: published
+owner: xingbang-platform
 description: Review authorized peer data cards and human rules, then produce evidence-linked pre-submission suggestions for a customer manager.
 ---
 
@@ -8,8 +14,11 @@ description: Review authorized peer data cards and human rules, then produce evi
 Use only the tools supplied by the current risk task. This skill never authorizes
 terminal execution, file browsing, database access, rule changes or approval decisions.
 
-1. Call `list_data_cards` and read every listed snapshot with `read_data_card`.
-2. Call `read_checks_and_rules` for deterministic calculations, data gaps and human rules.
+1. In the project assistant, call `read_project_snapshot`. In the legacy risk
+   workbench, call `list_data_cards` and read each card using `read_data_card`.
+   Use only the tool set supplied by the active task, never request absent tools.
+2. Read deterministic calculations, data gaps and human rules using `read_checks`
+   in the project assistant or `read_checks_and_rules` in the legacy workbench.
 3. Compare only the same project, financial period and reporting scope. Retain separate
    periods when examining trends. Never silently sum or deduplicate conflicting rows.
 4. Do not calculate material financial ratios yourself. Use the computed outputs;
@@ -23,3 +32,5 @@ terminal execution, file browsing, database access, rule changes or approval dec
 
 Output in Chinese: attention item, facts and evidence, applicable human rule,
 uncertainty, and suggested verification or supplementary material.
+When the active task requires structured JSON, use its exact result schema.
+Task-specific natural language priorities cannot remove mandatory program checks.