市面上有一千个会背语录的乔布斯。 我们把"他怎么想到那句话"这件事，做成了可复现的工程。 你问它"这生意该不该做"，它不给你十页报告，先甩你一句： "这事的根不在市场，在你把相机当硬件卖。" 我们要复刻的，就是这一句怎么来的。 乔布斯式决策分析工作流（社区演示版）。当用户需要分析赛道/创业机会、做产品定义、战略取舍、砍需求做减法、竞品定位、用户洞察、技术窗口判断，或用「乔布斯视角/连点成线」拆解问题时启用。三层推理框架（理解意图+拷问+答案+Voice 蒸馏）产出带证据链、确定性标记与域类型路由的结构化决策；B 端/I 层危险域标⚠️翻车不模仿其判断，AI/云/社媒等未及域标「框架推演·非本人立场」。非触发（闲聊、纯信息检索、纯代码实现）不加载。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/Jobs-SystemSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/Jobs-SystemSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/Jobs-SystemSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @sabre232/jobs-system-communityclawhub inspect @sabre232/jobs-system-community --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:0a205b21808e8d62cd060e7e8bbf5beb7bf31a6b81af94fb09a6f6ef5bd967c1jobs-voice.mdREADME.mdreferences/_selftest_record.jsonreferences/cognitive_bridge.pyreferences/lattice_resolver.pyreferences/product_shell.pyreferences/quality_matrix.pyskill-card.mdSKILL.md安装说明.mdJobs-System v1.0.0 — Initial public release - Introduces the Jobs-System decision analysis workflow using a three-layer reasoning framework (Intent, Interrogation, Answer) with persistent Voice distillation, specifically tailored for high-stakes product, strategy, and opportunity analysis. - Enforces strict evidence, certainty, and domain routing protocols: all judgments must include sourced references, determinacy markers, and clear routing by domain (A/B/C, I-layer risk flagging). - Features a non-dialogue digital apprenticeship model: outputs reflect distilled thinking and critical evaluation, not expert substitution or roleplay. - Provides structured commands for common scenarios (product definition, cut, research, keynote, timing) and tightly scoped output voice rules for authenticity and clarity. - Built-in strong fail-safes: I-layer risk lockouts, evidence sufficiency checks, for…