“verification”的搜索结果

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

中文简介正在准备中。当前显示原文说明。

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

中文简介正在准备中。当前显示原文说明。

Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.

中文简介正在准备中。当前显示原文说明。

Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".

中文简介正在准备中。当前显示原文说明。

Citation format and verification protocol for legal documents that draw on Bates-stamped source records. Defines the bracket citation format, multi-source citation rules, quotation handling, the verification pass that runs before output, and the [UNVERIFIED] flag protocol. Use this skill any time another skill produces a legal work product that cites Bates-stamped pages, including medical chronologies, deposition summaries, demand letters, case briefs, and discovery responses. Also use any time the user asks how to format a citation or verify that a claim is supported by the source.

中文简介正在准备中。当前显示原文说明。

Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'. NOT for pricing lookups, budget planning, or cost optimization strategies.

中文简介正在准备中。当前显示原文说明。

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

中文简介正在准备中。当前显示原文说明。

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

中文简介正在准备中。当前显示原文说明。

Verification before delivery: production-level command outputs, build, browser evidence. Use when implementing, reviewing or testing verification before delivery for React, Vite, Next.js or Perfect_AI projects.

中文简介正在准备中。当前显示原文说明。

Run verification commands and confirm output before claiming success

中文简介正在准备中。当前显示原文说明。

Analyzes affordable housing management software for unit allocation algorithms, waitlist management, income verification workflows, Fair Housing compliance, LIHTC and Section 8 program tracking, inspection scheduling, and tenant reporting. USE THIS SKILL WHEN: - You are reviewing housing management software or tenant management systems - Someone asks about Section 8, LIHTC, or public housing program compliance - You need to audit unit allocation algorithms for fairness or bias - A project involves waitlist management, income verification, or rent calculations - You are evaluating HUD compliance (50058, EIV, PIC submissions) - Someone mentions Fair Housing, reasonable accommodation, or protected class handling - You need to review HQS/NSPIRE inspection tracking or abatement workflows - A codebase handles tenant eligibility, subsidy calculations, or housing vouchers TRIGGER PHRASES: "affordable housing", "Section 8", "LIHTC", "public housing", "waitlist management", "income verification", "Fair Housing", "HUD compliance", "rent calculation", "housing voucher", "tenant management", "HQS inspection", "unit allocation", "housing authority"

中文简介正在准备中。当前显示原文说明。

Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'. NOT for pricing lookups, budget planning, or cost optimization strategies.

中文简介正在准备中。当前显示原文说明。

为功能验证或PR录屏添加字幕、局部放大和播放速度调整，制作带有操作说明的MP4，同时保留原始视频作为证据。

• 为PR录屏添加操作说明字幕
• 放大界面中的操作位置
• 缩短功能验证视频中的等待片段

设计或修改REA调查工具时，梳理职责范围、输入输出及CLI或MCP调用约定，并提出涵盖调查依据含义、现有工具比较和验证方法的设计方案。

• 设计新的REA调查工具
• 调整CLI或MCP的输入输出
• 明确provider职责与Evidence含义

在报告任务完成或修复成功前运行测试、构建等检查，核对完整输出，并在提交修改或创建拉取请求前，以当前实际结果为依据说明状态。

• 报告完成前核对结果
• 验证问题是否修复
• 提交或创建拉取请求前验证

在仓库中执行命令，检查状态，调查CI或构建失败，并验证必要的修复。依据执行结果报告本地修改、验证、提交和推送的状态。

• 检查仓库和分支状态
• 调查CI或构建失败的原因
• 进行小范围修复并验证

将大型功能的RFC设计提案拆分为带依赖关系和验收测试的工作单元，组织多个智能体完成调查、实现、测试与审查，再依次合并变更并验证整个系统。

• 将大型设计提案拆成可验证的任务
• 为多个智能体分配带依赖关系的工作
• 审查并依次合并变更分支

用于在Quarkus服务修改后或部署前，依次检查构建、代码分析、测试与漏洞，并验证原生可执行文件、容器及环境配置，梳理部署前的检查事项。

• 提交Quarkus拉取请求前检查
• 验证重构或依赖更新
• 检查原生可执行文件兼容性

在合并或部署Laravel项目前，依次检查环境、代码、测试覆盖率、依赖漏洞、数据库变更、缓存、队列及定时任务；前置检查失败时停止后续操作。

• 创建Laravel拉取请求前检查
• 重大重构或依赖更新后验证
• 部署至预发布或生产环境前检查

设计或检查AI智能体的反复作业，明确机器可判定的完成条件、不可更改的边界、独立验证和重试上限，防止空转、失控或错误完成。

• 定义反复作业的完成条件
• 检查空转和验证漏洞
• 划分规划、实现与验证职责

在Django发布或提交变更提案前，依次检查环境、代码质量、数据库变更、测试、漏洞及配置，汇总各阶段是否通过和需要修复的问题。

• 提交Django变更提案前检查
• 检查数据库迁移
• 核对测试覆盖率目标

在实际邮箱中整理收件、根据往来记录起草回复，并发送邮件、核实已发送记录。明确发件账户与收件人，检查承诺和期限，并报告草稿、待批准、已发送或待核实等状态。

• 整理收件箱和待归档邮件
• 根据往来记录起草回复
• 发送邮件并核实发送记录

协助审查Cisco IOS和IOS-XE配置，检查流量允许与拒绝规则及接口设置，选择只读故障排查命令，并整理网络变更前后的验证与配置保存步骤。

• 变更前审查路由器和交换机配置
• 使用只读命令排查故障
• 检查ACL掩码和应用方向

为AI智能体创建专用邮箱，收发邮件并处理回复和附件。还可查看邮件中的一次性验证码，并设置收到新邮件后继续执行任务的流程。

• 创建AI智能体专用邮箱地址
• 发送邮件并处理回复与附件
• 查看邮件中的验证码