Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when CrossFrame Suite routes explicit Chinese analysis of teams, projects, organizations, responsibility chains, feedback write-back, repair, or retrospectives.
.claude/skills/sickn33-crossframe-org/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 87% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 79% | 0% |
crossframe-suite routes an explicit CrossFrame task about teams, projects, organizations, responsibility chains, authority chains, feedback write-back, retrospectives, or repair.This AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.
crossframe-suite routing; do not apply it as a generic default reasoning layer.> 本 skill 不独立触发。 所有 CrossFrame 任务统一从 crossframe-suite 入口调度。用户无需直接调用本 skill；suite 根据路由规则在需要时自动加载。
如果组织修复判断之后要写文章、沉淀案例、做辩论或评审输出，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 只负责团队、项目和组织修复专项。
CrossFrame Org 是 crossframe 的平行组织修复 skill，不替代 canonical crossframe，也不复制 CrossFrame 全文。它把 CrossFrame 的事实闸、尺度闸、责任闸、机制候选和概念保真，转成团队、项目、组织场景里的可执行修复备忘录。
中文是权威语义。英文只用于 skill id、文件名或必要的外部接口；不要把“承接、回流、责任链、授权链、修复副产品、停止错误加速”翻译后再反向理解。
../crossframe/SKILL.md。../crossframe/references/read-routing-map.md，确定本次需要加载的 canonical protocol、worksheet、concept card 和模板。../crossframe/references/continuity-bundles.md，并按需使用 ../crossframe/worksheets/source-continuity-check.md；未完成联读时只能降档。../crossframe/templates/read-state-capsule.md 规定的 v5-read-state-capsule，并在高责任、公共、AI/过程性产物、生命周期、无法退出主体或文章输出场景执行 ../crossframe/worksheets/source-anchor-integrity-check.md。如果胶囊缺失，回到 ../crossframe/SKILL.md 补齐；本 skill 不重新发明源路由。references/org-routing-map.md，选择本 skill 的专项协议、引用材料和模板。protocols/org-diagnostic-protocol.mdprotocols/feedback-writeback-protocol.mdprotocols/retrospective-redesign-protocol.mdprotocols/low-risk-pilot-protocol.mdreferences/responsibility-authorization-chain.mdreferences/middle-manager-depletion.mdreferences/org-failure-signals.mdreferences/anti-chicken-soup-guardrails.md../crossframe/references/read-routing-map.md 读取对应概念卡，并用 ../crossframe/worksheets/concept-fidelity-check.md 做概念保真检查。每次输出前，至少在内部写清：
组织推理提纲，再输出用户需要的备忘录或方案。crossframe-essay，除非用户明确要求写文章。使用 templates/output-selector.md 判断模板。常见默认：
text# 组织推理提纲 # 组织诊断备忘录 # 反馈写回方案 # 低风险试点计划
如果用户只要求复盘改造，使用 templates/retrospective-redesign-recommendation.md。如果用户只要求一个行动实验，使用 templates/low-risk-pilot-plan.md 并附 templates/stop-condition-card.md。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 22,116 | 18,926 | -14% | 1 | 1 | 0% | 3,257 | 4,584 | +41% | 0 | 0 | — |
case-02 | pass→pass | 20,115 | 20,806 | +3% | 1 | 1 | 0% | 3,241 | 5,286 | +63% | 0 | 0 | — |
case-03 | fail→pass | 21,912 | 22,347 | +2% | 1 | 1 | 0% | 3,378 | 5,228 | +55% | 0 | 0 | — |
case-04 | pass→pass | 15,708 | 18,684 | +19% | 1 | 1 | 0% | 2,574 | 4,601 | +79% | 0 | 0 | — |
case-05 | fail→fail | 36,435 | 39,037 | +7% | 1 | 1 | 0% | 4,935 | 7,217 | +46% | 0 | 0 | — |
case-06 | pass→pass | 18,613 | 20,646 | +11% | 1 | 1 | 0% | 2,932 | 5,007 | +71% | 0 | 0 | — |
case-07 | fail→pass | 19,857 | 20,379 | +3% | 1 | 1 | 0% | 2,968 | 5,007 | +69% | 0 | 0 | — |
case-08 | fail→pass | 14,189 | 17,305 | +22% | 1 | 1 | 0% | 2,210 | 4,136 | +87% | 0 | 0 | — |
case-09 | fail→pass | 19,276 | 20,907 | +8% | 1 | 1 | 0% | 3,227 | 5,200 | +61% | 0 | 0 | — |
case-10 | pass→pass | 16,164 | 20,536 | +27% | 1 | 1 | 0% | 2,665 | 4,739 | +78% | 0 | 0 | — |
case-11 | pass→pass | 14,799 | 16,659 | +13% | 1 | 1 | 0% | 2,309 | 4,090 | +77% | 0 | 0 | — |
case-12 | pass→pass | 18,406 | 21,474 | +17% | 1 | 1 | 0% | 3,011 | 5,210 | +73% | 0 | 0 | — |
case-13 | fail→pass | 17,120 | 17,995 | +5% | 1 | 1 | 0% | 2,579 | 4,617 | +79% | 0 | 0 | — |
case-14 | pass→pass | 18,017 | 20,974 | +16% | 1 | 1 | 0% | 2,890 | 4,823 | +67% | 0 | 0 | — |
case-15 | pass→pass | 17,211 | 22,876 | +33% | 1 | 1 | 0% | 2,392 | 5,653 | +136% | 0 | 0 | — |
case-16 | pass→pass | 17,774 | 20,195 | +14% | 1 | 1 | 0% | 2,688 | 4,496 | +67% | 0 | 0 | — |
case-17 | pass→pass | 18,511 | 21,676 | +17% | 1 | 1 | 0% | 2,816 | 4,709 | +67% | 0 | 0 | — |
case-18 | fail→pass | 17,428 | 22,219 | +27% | 1 | 1 | 0% | 2,533 | 4,389 | +73% | 0 | 0 | — |
case-19 | pass→pass | 18,838 | 19,627 | +4% | 1 | 1 | 0% | 2,690 | 4,502 | +67% | 0 | 0 | — |
case-20 | pass→pass | 18,309 | 28,460 | +55% | 1 | 1 | 0% | 2,709 | 5,841 | +116% | 0 | 0 | — |
case-21 | pass→pass | 23,360 | 19,245 | -18% | 1 | 1 | 0% | 3,723 | 4,493 | +21% | 0 | 0 | — |
case-22 | pass→pass | 20,491 | 22,303 | +9% | 1 | 1 | 0% | 2,862 | 4,915 | +72% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.