GeorgeDoors888/GB-Power-Market-JJ - 第 10 页

permission-footprint-reviewer

梳理某个 Skill、脚本或工作流需要的权限，并提出最小权限替代方案。；use for permissions, least-privilege, security workflows；do not use for 绕过系统安全控制, 生成提权方法.

personal-deadline-radar

扫描个人待办、会议和消息摘要，找即将到期事项与时间冲突。；use for deadlines, calendar, tasks workflows；do not use for 自动改日历, 伪造截止时间.

policy-application-checker

Read policies, application requirements, and forms, then turn them into a completeness checklist, risk list, and submission plan.

原文语言：英语

policy-delta-watcher

比较新旧制度或政策差异，指出业务影响、流程影响和需更新的操作手册。；use for policy, diff, governance workflows；do not use for 给法律定性结论, 忽略边缘影响人群.

policy-to-checklist

把征稿启事、通知、比赛规则、制度文件、招标要求等转成可执行检查清单与时间线。

portfolio-case-study-forge

Turn rough project notes into polished portfolio case studies with metrics, visuals checklist, and interviewer talking points.

原文语言：英语

priority-conflict-resolver

面对多个目标、有限资源与冲突时，输出排序、牺牲说明、边界与不做清单。；use for priority, tradeoff, planning workflows；do not use for 替代人事绩效决策, 伪造资源承诺.

project-brief-writer

把零散需求、聊天和会议内容整理成项目任务书、边界、验收标准和风险清单。；use for project-brief, requirements, scope workflows；do not use for 生成法律合同, 替代正式需求审批.

prompt-ab-lab

Design, log, compare, and score prompt experiments so users can systematically improve outputs instead of guessing.

原文语言：英语

prompt-leak-auditor

审查 prompt、Skill 文案和说明中是否泄漏密钥、路径、内部规则或高风险指令。；use for prompt, security, audit workflows；do not use for 把扫描到的密钥原文再次扩散, 输出可利用攻击步骤.

proposal-comparator

对比多个方案文档，输出差异、隐含成本、风险与推荐结论。；use for proposal, comparison, decision workflows；do not use for 忽略用户给的约束, 伪造数据支持结论.

qa-scenario-synthesizer

把需求拆成功能、异常、跨端、脏输入和恢复场景测试集。；use for qa, test-scenarios, edge-cases workflows；do not use for 宣称已经完成测试, 忽略关键用户路径.

quote-invoice-workbench

Turn messy service pricing notes into professional quotes, SOW line items, and invoice drafts with assumptions clearly surfaced.

原文语言：英语

real-estate-showing-brief

为房产带看前整理买家画像、关注点、路线与现场提问清单。；use for real-estate, showing, brief workflows；do not use for 编造房源信息, 替代正式法律披露.

receipt-expense-sorter

整理收据和报销资料，按周期、类别、凭证完整度做分组与缺失提醒。；use for receipts, expenses, finance-ops workflows；do not use for 替代正式财务报销系统, 生成虚假发票信息.

receipt-expense-workbench

Normalize receipts, reimbursement slips, and invoices into a clean expense ledger with category mapping and anomaly flags.

原文语言：英语

recruiting-interview-kit

根据 JD 生成面试题、评分维度、红旗项与面试记录模板。；use for recruiting, interview, hiring workflows；do not use for 生成歧视性问题, 替代最终录用决策.

regression-story-builder

基于历史问题生成回归测试故事集、风险等级和优先级。；use for regression, testing, qa workflows；do not use for 宣称已经执行测试, 跳过高风险路径.

release-note-localizer

将发布说明转换为中文、英文、客户版和技术版，同时保持术语一致。；use for localization, release-notes, translation workflows；do not use for 机翻敏感合同条款, 替代专业法律翻译.

renewal-risk-monitor

识别续约风险信号，区分可挽回风险与高概率流失信号。；use for renewal, risk, customer-success workflows；do not use for 伪造健康度数据, 替代正式续约决策.

reply-coach

从剪贴板读取聊天内容，生成尊重边界、自然不油腻的高情商回复建议，适用于微信、QQ等聊天场景。

repo-onboarding-guide

扫描仓库目录与说明文件，生成新成员上手路径、推荐阅读顺序与踩坑提醒。；use for repo, onboarding, developer-experience workflows；do not use for 泄漏私有源码内容到外部, 执行构建命令.

research-claim-checker

检查一篇研究或分析里的结论是否被证据支撑，指出证据链断点。；use for research, claims, evidence workflows；do not use for 伪造出处, 替代同行评议.

research-matrix-builder

Build literature matrices from papers, notes, and abstracts to compare methods, data, findings, and research gaps.

原文语言：英语

resume-job-match-lab

Tailor resumes and project bullets to a target role, quantify gaps, and prepare an interview-ready evidence map.

原文语言：英语

review-miner

从评论、评价和反馈中提炼卖点、痛点、反对意见与应删除的话术。；use for reviews, voice-of-customer, marketing workflows；do not use for 造假好评, 泄露用户身份.

run-command-safety-check

在执行 shell 方案前检查危险模式，如 pipe-to-shell、覆盖式删除、危险重定向或混淆执行。；use for shell, security, command-review workflows；do not use for 提供攻击性命令, 帮用户绕过限制.

sbom-explainer

把依赖清单或 SBOM 翻译成非技术可读的风险说明，按影响面排序。；use for sbom, dependencies, risk workflows；do not use for 伪造 CVE 状态, 替代专业漏洞扫描.

screenshot-to-task

把截图里的待办或灵感整理成任务、备注和优先级。；use for screenshots, tasks, capture workflows；do not use for 伪造截图内容, 替代 OCR 系统.

screenshot-ux-auditor

Turn app screenshots into structured UX, copywriting, and conversion audits with issue severity and recommended fixes.

原文语言：英语

secret-exposure-gate

在发布前检查目录中是否含秘钥、token、私有 URL、证书片段或凭证文件。；use for secrets, security, preflight workflows；do not use for 显示完整密钥值, 修改用户文件.

skill-example-synthesizer

为 Skill 生成高质量正例、反例和边界例，提升路由与可理解性。；use for skills, examples, routing workflows；do not use for 只给笼统例子, 忽视误触发场景.

skill-frontmatter-doctor

修复 frontmatter、metadata、requires、install 和目录结构问题，贴合当前 OpenClaw 规范。；use for skills, frontmatter, validation workflows；do not use for 编造不存在的字段, 忽略单行 JSON 约束.

skill-gap-finder

扫描现有 Skill 套装，找重复、缺口、职责冲突和最该补的空位。；use for skills, bundle, analysis workflows；do not use for 臆造目录内容, 直接删除 skill.

skill-install-checker

安装前验证二进制、环境变量、配置、OS 与 sandbox 条件，解释为什么此机不适合装。；use for skills, install, preflight workflows；do not use for 假装依赖已经满足, 直接修改系统环境.

skill-market-fit-ranker

对一批 Skill 选题按高频、低门槛、传播性、ROI 和风险做排序。；use for skills, market-fit, prioritization workflows；do not use for 只按个人偏好排序, 忽略发布风险.

skill-pack-composer

把多个 Skill 组合成套装，检查 slug、依赖、资源和定位冲突。；use for skills, bundle, packaging workflows；do not use for 混入重复职责的 skill, 忽略依赖冲突.

skill-readme-rebuilder

从 SKILL.md、脚本与资源反推 README、FAQ 与示例，保持说明一致。；use for skills, readme, docs workflows；do not use for 伪造脚本能力, 跳过真实依赖声明.

skill-routing-benchmark

测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。；use for skills, routing, benchmark workflows；do not use for 只给模糊建议, 忽略高度相近的 skill.

skill-smoke-test-author

自动为 Skill 生成 smoke test 模板，覆盖依赖缺失、空输入和标准路径。；use for skills, testing, smoke-test workflows；do not use for 写无法执行的测试, 忽略失败路径.