Software Development AI Skills

按评分点组织论文结构并给出模型路线，产出论文大纲、评分点对齐表与候选模型对照实验方案。当需要在多个候选模型间取舍、需要把评分要求映射成章节结构、或模型路线尚未确定时使用。赛题原文解析由 problem-doc-model-selector 负责。

Use when you want Gemini CLI as a second opinion for coding tasks such as prototyping, debugging, or diff review, while keeping Codex as the primary implementer.

Queries, manages, and troubleshoots Apache Airflow using the `af` CLI. Use when working with anything related to Airflow - a DAG, a DAG run, a task log, an import or parse error, a broken DAG, or any…

Efficiently read and analyze pi agent session JSONL files. Use when asked to "read a session", "review a session", "analyze a session", "what happened in this session", "load session", "parse…

Use this skill as the default XCrawl entry point for direct XCrawl requests, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema.

Migrate ASP.NET Web Forms applications to Blazor Server using the webforms-to-blazor CLI tool and BlazorWebFormsComponents (BWFC). Orchestrates L1 automated transforms via CLI, then guides L2…

This skill should be used when writing documentation for codebases, including README files, architecture documentation, code comments, and API documentation. Use this skill when users request help…

This skill provides comprehensive guidance for documenting SAP APIs following the SAP API Style Guide standards. It should be used when creating or reviewing API documentation for REST, OData, Java,…

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this",…

Break an approved PRD into small, dependency-ordered, vertically-sliced implementation issues written as local files in the Foreman feature directory. Each issue ships a runnable acceptance check and…

Review and fix temporal references in code comments.

Use to craft concise executive updates, agendas, and follow-up logs for QBR/EBR sessions.

生成符合 Kling 3.0（可灵 3.0，快手）规则的视频提示词。三种写法自适应：4 部分基础公式（短视频）/ 5 层进阶公式（剧情+音频）/ 图生视频专用（只描述运动）。Kling 是 2026 年中文理解最强、原生音画同步、最长 2 分钟、支持角色定向发声、Motion Brush 的电影级模型。用于"用 Kling 生成视频"、"可灵 AI…

Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for…

Address PR review feedback systematically — fetch inline comments, review bodies, handle outside-diff-range comments, resolve threads with proper attribution

Design a module's interface using parallel sub-agents producing radically different designs ("design it twice"). Compare on depth, simplicity, and efficiency. Embedded grill on the synthesized choice.…

Enforce existence, reuse, mirror, and symmetry principles to keep new code minimal and consistent with surrounding code. Use when writing new code in an existing codebase, adding new features,…

Use when playing, mixing or debugging sound in Unreal Engine — one-shot SFX, looping ambience, music, dialogue or procedural audio. Also use when the user mentions 'UAudioComponent',…

Operate Tencent Cloud control-plane resources (monitoring/alarms, CLB, CAM roles, COS, MySQL, SCF) via cloud APIs when no dedicated MCP tool covers the task. Use when a task needs control-plane…

Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.

Use when attacking or auditing a CI/CD pipeline or software supply chain — pwn requests, poisoned pipeline execution, compromised/mutable-tag actions, dependency confusion, registry worms, runner…

配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent，支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用；普通 API 问题与配置后的日常编码任务不触发。

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow,…

End-to-end pipeline for releasing an iOS / watchOS app to TestFlight and the App Store. Use when the user wants to publish, ship, or release an iOS/watchOS app, get a build onto TestFlight, archive…

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology…

Drive an omh-ralph run: dispatch, evidence, commit hygiene.

Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.

Run a pre-deployment security compliance checklist based on KISA guidelines. Supports CII compliance (70 items), AI security checklists, Robot Security (103 items), Space Security (12 domains, 53…

Isolate parallel work in a git worktree of the current repository (worktree tool: status / new / merge / remove). Use when another live session is dirty in the same directory (list_agents), when two…

Use this skill when creating, converting, or manipulating colors in PixiJS v8. Covers Color class input formats (hex, CSS names, RGB/HSL objects, arrays, Uint8Array), conversion methods (toHex,…

Search oip-visual-v2 for traceable prompt-image pairs and open local result galleries. Use when finding, inspecting, comparing, browsing, or copying real image-generation references or exact source…

After a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks "what did we actually do," wants to review a large change, or invokes a…

各種SNS・広告プラットフォーム向けのバナー/クリエイティブを生成するスキル。 X, Facebook, Instagram, PRTimes, YouTube, LINE, Web広告に対応。 「バナーを作って」「広告画像を生成」「SNS用の画像」「クリエイティブ制作」等のリクエストで発動。

Build, run and test macOS apps and Swift packages from the command line with XcodeBuildMCP, xcodebuild and swift. Use when asked to build, launch, test or debug a macOS target, a Swift package, or a…

consumerが知る目的・操作・契約と内部技術・手順を分け、技術漏出、caller分岐、責務境界と変更局所性を設計・監査するときに使う。if削減、interface量産、全体architectureの選定には使わない。

Audit Value Delivery compliance after PR push

Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge,…

Beginner-friendly reverse-engineering workflow for Android Crypto Hooking. Use it to collect evidence, choose static or dynamic analysis, correlate runtime behavior, and produce a reproducible result.

Draft and stress-test a VISION.md for a repository, then iterate with the author on an interactive review board until approved. Use on /vision or when asked to create or refine a project vision.

Use when ECS Service Connect の DNS alias が IPv6 アドレスを返し、 IPv4-only の Fargate task から `network is unreachable` / `EAI_AGAIN` 等で接続できない問題に遭遇したとき。 OTel Collector → Tempo の OTLP gRPC、 Fargate → Service…

超圧縮PRレビューコメント。1行1指摘: 位置・問題・修正。前置き削除、シグナル優先。 日本語対応。「PRレビューして」「コードレビュー」「/review」「/genshijin-review」で起動。 プルリクエストレビュー時に自動起動候補。

把灵感、观察或长文写成 Ray 能直接开机录的中文口播稿（Ray 口吻、观点说满，存疑处列进「待确认」）；也审读口播稿，或对照录制稿学习 Ray 的真实表达。用于“做成口播”“改成口播”“审一下口播稿”“对比我录的”。讲清一件事、以讲解为主的科普视频稿不在这里（装了 ray-kepu 时转它）。不发布。

回炉：完整成稿与改稿。把用户的素材或参考观点写成可以直接念的完整逐字稿，也修改已有稿件和 AI 初稿；从“我要表达什么”出发借观点，不照搬别人的脉络。用户要完整口播稿、要改稿、要把别人的爆款改成自己的时使用。

观自在 · MindMirror——基于真实语料的自我认知工具箱。 基于用户的真实语料（Obsidian 笔记与日记、AI 记忆、对话历史）运行三种模式：①照见模式——带证据引用、 带置信度地回答 22 个自我认知问题，生成坦诚不奉承的自我画像；②数字分身模式——从语料起草十个维度的 「数字分身画像」（价值观/思维/情绪/关系/表达/审美/习惯等），用户只需校准；③人生规划模式——推演三种…

Generate, edit, and iterate raster images from text prompts or reference images with GPT Image, Nano Banana, or Seedream. Use for visual asset creation, concept art, product/mockup imagery, style…

Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read…

Use when writing a social post on a topic or a reply to someone's post — X/Twitter, LinkedIn, Bluesky, Threads — and the obvious take is not good enough. Triggers include "reply to this post", "write…

Visualize your highlights and their connections in an interactive 2D graph

Build a positioning and narrative where the developer is the hero and a real trend is the villain. Use when the messaging describes the product instead of the problem, sounds like every competitor, or…

Use when evolving aggregate invariants, value objects or domain events in an existing DDD-style Spring Boot 3 application, or when DDD is explicitly requested. Preserve existing API identifiers and…