Integrations & APIs

vivy-yi Skill

ESG 报告主流程 — 整合环境/社会/治理数据收集、ESG 评级管理、重大事件应对与报告编制。 适用情形：年度 ESG 报告披露或评级机构（MSCI/Sustainalytics）评估时执行， 整合 esg-data-integration、esg-materiality-assessment、esg-rating-tracking 和 esg-reporting， 输出符合监管要求的 ESG 报告。 核心：数据完整性 → 重要性评估 → 评级管理 → 合规披露。

vishuwa2004 Bundle

Split conversation history into API-round buckets so compaction retries cut only the chunks tied to the failed round.

vishuwa2004 Bundle

Pause terminal animations when the user requests reduced motion, then resume cleanly without tearing the rest of the UI.

openlabor Skill

Generate unit and integration tests

nvidia-omniverse Skill

Loading USD scenes into the renderer from files, URLs, or inline USDA strings. Use when user asks to load a USD scene, compose USD content, add cameras or RenderProducts to an existing USD layer, add referenced content, or create runtime geometry.

nvidia-omniverse Skill

Error checking patterns for both C and Python. Use when user asks about error handling, checking errors, debugging ovrtx failures, or troubleshooting.

nvidia-omniverse Skill

Upgrade skill to migrate an existing ovrtx codebase from 0.2.0 to 0.3.0. Use when the user asks to "upgrade from 0.2 to 0.3", migrate ovrtx API usage, update 0.2 projects to 0.3, or fix code after moving from ovrtx 0.2.x to 0.3.x.

nvidia-omniverse Bundle

Port an existing nanoUSD renderer to a new GPU backend or API (e.g. Vulkan to Metal, DX12, or WebGPU) or stand up a second backend behind the shared renderer contract. Use when Codex adds a backend, translates shaders and RHI calls across graphics APIs, decides what to share versus reimplement versus stub, keeps backends at ABI and feature parity, or hits cross-API transform, struct-alignment, command-encoder, or resource-residency pitfalls.

nvidia-omniverse Bundle

Debug rendering, viewer, shader, material, camera, lighting, and GPU integration bugs with reproducible visual evidence. Use when scenes render blank, only appear after camera motion, show incorrect shading, diverge across backends, crash in GUI mode, or need pixel/screenshot verification.

nvidia-omniverse Bundle

Map unfamiliar or multi-repository codebases before refactoring, integration, or feature work. Use when Codex needs to analyze submodules, ownership boundaries, APIs, duplicate implementations, build/test surfaces, risk areas, and a practical refactor sequence before changing code.

nvidia-omniverse Bundle

Author and accept a reproducible OVPhysX rigid-body drop or contact test from Blender, including collision proxies, authoritative pose readback, settling, and visible contact evidence. Use when a user needs to prove that a SimReady prop falls, collides, and comes to rest through the installed OVRTX/OVPhysX runtime rather than a Blender-only animation.

malekokour Bundle

Reviews the clinical pharmacology content of a draft EU Summary of Product Characteristics — sections 4.2, 4.5, 5.2 and the quantitative statements in 4.4 — against the SmPC guideline's required content, the QRD template's section structure, and the source data each statement claims to rest on. Use this skill when someone asks to review, QC, check the structure of, or trace the numbers in draft SmPC clinical pharmacology content — for example "does 5.2 cover all the populations it needs to" or "trace every interaction magnitude in 4.5 back to its study". Do not use for drafting or rewording SmPC text, for US Prescribing Information, for Japanese package inserts, for a company core data sheet, for reviewing a Module 2.7.2 submission summary, or for any request to decide what the label should say.

malekokour Bundle

Reviews Section 12 of a draft US Prescribing Information, and the quantitative basis of the statements in Sections 2, 7 and 8, against 21 CFR 201.57(c)(13), the December 2016 clinical pharmacology labelling guidance, and the source data each statement claims to rest on. Use this skill when someone asks to review, QC, check conformance of, or trace the numbers in draft labelling clinical pharmacology content — for example "does Section 12.3 carry everything the content list requires" or "trace every number in Section 8 back to its source". Do not use for drafting or rewording label text, for reviewing a Module 2.7.2 submission summary, for advising on or responding to an agency labelling comment, or for any request to decide what the label should say.

malekokour Bundle

Assembles and organises the evidence behind a registration or dose-optimisation dose justification — exposure-response integration, intrinsic and extrinsic factor coverage, formulation-bridging logic, dose-modification rules — arranged against the questions clinical pharmacology reviewers ask, with every claim carrying a locator and every gap named. Use this skill when someone asks to assemble, index, organise or gap-check the evidence supporting a proposed dose or regimen — for example "pull together what supports the 200 mg dose", "map our dose-modification rules to their evidence", or "which intrinsic factors are uncovered before we file". Do not use for first-in-human starting-dose review, for assessing a development plan for study gaps, or for any request to select, recommend, adjust or justify a dose — that decision belongs to a qualified human and this skill never makes it.

aiunlocked1412 Bundle

AI โปรดิวเซอร์ไลฟ์สตรีม — overlay, scene setup, chat engagement, donation/subscription, sponsor integration สำหรับ Twitch/YouTube Live/TikTok Live/FB Live

zhou210712 Skill

审查AI供应商条款——重点核查训练数据来源合规性、责任分配、 模型变更通知、合规义务向下传导。适用于审查AI SaaS协议、 AI模型授权、AI API服务条款，或采购团队提出"这个AI供应商 合同有问题吗"时使用。

zhou210712 Skill

交割后并购整合追踪器——分阶段工作计划、同意追踪、规模化合同转让、 每周状态报告。从任何可获取的交易工件（股权收购协议、交易摘要、 交割检查表）初始化，并连接到来自并购冷启动的 deal-context.md 和 closing-checklist.yaml。当用户说"整合""交割后""同意未决" "合同转让""整合状态"或"交易还差什么"时使用。

bdambrosio Bundle

Returns API instructions (not data) for retrieving Bluesky metrics via AT Protocol. Read the returned instructions, then use fetch-text + extract to get actual data.

bdambrosio Bundle

Get the API version information from the OSWorld server. Returns API version, server version, and protocol.

aiunlocked1412 Bundle

เขียน README API doc tutorial ADR ที่นักพัฒนาเข้าใจและใช้งานได้จริง

aiunlocked1412 Bundle

Embedded/IoT Engineer — Arduino/ESP32/Raspberry Pi, sensor integration, MQTT/BLE/LoRa, firmware development, battery optimization

nvidia-omniverse Skill

Use this skill when implementing or verifying a generated read-only backend for nanousd's C API.

haomingz Bundle

从 Flask、FastAPI、Express 或 Gin 等 Web 框架的源代码中自动扫描路由定义，生成符合 OpenAPI 3.0 / Swagger 规范的标准化 API 文档文件。当用户需要生成 API 文档、提到 OpenAPI、Swagger、接口文档、路由扫描或从代码自动提取接口信息时触发。

haomingz Bundle

为模块生成多种截然不同的接口设计方案，通过并行探索产出多个接口签名、使用示例和封装说明，并详细对比其简洁性、通用性、深度与易用性。当用户需要设计API、探索接口方案、对比模块形态，或明确提及“设计两次”原则、并行设计、接口形态比较时触发。

haomingz Skill

直接调用 GitLab REST API，用于其他 glab 命令未涵盖的高级查询和操作。适用于直接访问 GitLab API 端点、发起自定义 API 请求或以 JSON 格式获取数据。触发词：API 调用、REST API、GitLab API、JSON 查询、高级查询。

haomingz Bundle

管理 GitLab 个人访问令牌和项目访问令牌。适用于创建令牌、撤销访问权限或管理 API 认证。触发关键词：token、访问令牌、PAT、个人访问令牌、API 令牌。

build-with-dhiraj Skill

Execute HTTP requests and handle JSON in Flutter. Use for REST APIs or parsing structured external data.

build-with-dhiraj Skill

v0 by Vercel expert guidance. Use when discussing AI code generation, generating UI components from prompts, v0 CLI usage, v0 SDK/API integration, or integrating v0 into development workflows with GitHub and Vercel deployment.

build-with-dhiraj Bundle

Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup.

build-with-dhiraj Skill

Vercel Marketplace expert guidance — discovering, installing, and building integrations, auto-provisioned environment variables, unified billing, and the vercel integration CLI. Use when consuming third-party services, building custom integrations, or managing marketplace resources on Vercel.

build-with-dhiraj Skill

Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.

build-with-dhiraj Skill

Sign in with Vercel guidance — OAuth 2.0/OIDC identity provider for user authentication via Vercel accounts. Use when implementing user login with Vercel as the identity provider.

uphiago Skill

Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs prefix-only), pre-flight (OPTIONS) gating bypass, postMessage origin checks. High only when an attacker-controlled origin can perform a CREDENTIALED cross-origin read of sensitive data and you have proven it in a browser. Use when testing API endpoints, SPAs, or any app emitting Access-Control-* headers.

uphiago Skill

Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax sibling-subdomain bypass (Argo CD CVE-2024-22424), GraphQL mutations-via-GET (GitLab $3,370), framework-wide CSRF middleware disabled (Stripe Dashboard $5,000), path-traversal CSRF-token bypass (GitHub Enterprise CVE-2022-23732 $10k), Origin-omission bypass (TikTok $2,500), OAuth-state null-byte (Streamlabs), WebSocket CSRF / CSWSH (Coda), default-SameSite email-change → ATO (YoYo Games $400), social-account-link CSRF (HackerOne), JSON-CSRF via text/plain on email-change (TikTok $500). Use when hunting modern CSRF — heavy emphasis on chain-to-ATO patterns.

uphiago Skill

Hunt LDAP Injection and XPath Injection — authentication bypass, blind char-by-char attribute exfiltration, AD user/group enumeration, XML-store XPath bypass. Covers the LDAP special-character set (* ( ) \ NUL /), search-filter-context vs DN-injection, parenthesis-balancing, AND/OR filter logic, and {SSHA}/{CRYPT} userPassword exfil on non-AD directories. Use when target uses LDAP/AD authentication, corporate SSO with a directory backend, an address-book/people-search API, or XML-based data stores queried with XPath.

uphiago Skill

Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection (HackerOne Salesforce), time-based blind SQLi in GraphQL resolvers, and SQLi on OIDC-proxy backends. Use when hunting SQLi / NoSQLi on any target.