AI Ml AI Skills

Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user…

Build an iOS app and run it on the Simulator, then read build errors, logs and screenshots. Use when asked to build, run, launch, test or debug an iOS/iPadOS app, or when xcodebuild fails.

Analyst-grade long report writing style with 15 quality constraints.

Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

Arbitrary file download vulnerability detection and exploitation using path traversal techniques, bypass methods, and sensitive file discovery. Use this skill when user needs to test for file download…

Honey for plain Claude — the terse-prose core with no agent-harness features. Paste into a claude.ai Project's custom instructions, a Style, or an API system prompt. Strips filler, hedging, and…

Find duplicates, dead links and untagged items in a saved library and propose what to do about each.

Coordinates work entrusted to several Codex, Claude, Cursor or mixed windows, with tasks, acknowledgements, proofs, a non-author reviewer and a persistent registry. Includes squadra dash to view the…

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one…

Generate an image from a text prompt using the default OpenAI-like LLM config (gpt-image-1-mini or compatible image generation API). The image is uploaded to the gofile.io public file sharing service…

Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like…

Use when executing implementation plans, handling multiple independent tasks, or doing structured task-by-task development with review gates in Antigravity.

Diagnose ClickHouse cluster health and provide concrete remediation.

After the founder brief and the market research, turn them into an honest diagnosis and a prioritized, stage-aware GTM roadmap saved as docs/gtm-cofounder/gtm-roadmap.md. This is the hub the user…

Use when seeing decides faster than reading — UI directions or mockups to choose between, a page to tune or click through, a design doc, review, proposal, or architecture walkthrough for them or their…

教学过程中自动捕获和记录学习者的概念疑难点（"为什么/是什么/怎么推/什么意思"类型的问题），保存到进度文件的"概念疑难点记录"区，形成考前回顾清单。

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

Owns repositories, data sources and mapping for Compose and Compose Multiplatform apps: DTO to domain to UiModel boundaries, Ktor clients and bearer auth, WebSocket and SSE, Room, DataStore, Paging 3,…

Use when the user wants to start work in a new git worktree — "new worktree", "spin up a worktree/branch for this", "work on X in another worktree", "branch this off". Allocates a reusable slot (<repo…

Maintenance of the contributor issue pipeline for JSONbored/awesome-claude (HeyClaude) — closing issues that are already done but not marked so, and keeping a small, high-value contributor-available…

使用 agentao-kanban 看板进行任务管理（拆任务 / 状态流转 / 后台服务 / 看产物）。 本技能负责：① 初始化 .kanban/ 项目 ② 把需求拆成原子卡片入板 ③ 推动状态流转 INBOX → READY → DOING → REVIEW → DONE ④ 启停 daemon 与 Web UI ⑤ 察看卡片状态与产物。 触发关键词（中/英）：看板 / kanban /…

把一道立体几何题解成一个自包含的交互教学网页：左侧 MathJax 分步解析， 右侧 Three.js 可交互 3D 模型（分步高亮 + 镜头切换）。支持三种入口——给定文字题目、 随机出题、上传题目图片识别后解题。覆盖正方体/长方体、棱锥/棱柱、圆柱/圆锥上的线面角、 二面角、异面直线夹角、点到平面距离、体积等题型，统一用"建系+向量法"，并由 sympy 精确 计算驱动（答案、3D…

Rewrite the immediately preceding assistant response with clearer and more direct prose when the user invokes this skill.

Documents how the codebase works today for a task's research questions and saves it as a research file (.ork/tasks/TASK/NN-research-SLUG.md) with file:line citations, so the plan builds on a…

Use when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history and native emulo:mine is not available. This is the cross-agent skills.sh…

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus)…

当用户学习或接触一个新概念/新技术/新算法/新领域时使用（尤其感到陌生或有点难时）。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西（换了名字）、结构同构的旧知识、能解释新知识的已有知识，并点出新概念体现的跨领域元知识模式。让「学新东西」变成「发现你已经会了一半」。触发场景：学 X、接触 X、这个好难、X 是什么、帮我理解 X。

ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not found'.

Conduct deep web research using the openbrowser-ai agent: decompose a query, investigate sub-questions across multiple sources, and produce a cited markdown report plus structured JSON under…

Use when performing authorized Android APK, XAPK, or APKS security testing that needs static analysis, split install handling, rooted emulator setup, mitmproxy interception, Frida hook generation, or…

Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface,…

Plan and execute organizational or technical changes. Trigger with "we're changing", "rolling out", "migration plan", "how do we communicate this change", "change management plan", or when the user is…

Earnings-quality forensics — Beneish M-Score, Altman Z, Sloan accruals ratio, cash-vs-earnings divergence, SBC-adjusted FCF, revenue-recognition and capitalisation checks, auditor and related-party…

从某个固定点（提交、分支、标签或合并基点）以来的改动出发，沿两条轴做评审：规范（代码是否遵循本仓库已记录的编码规范？）与规格符合（代码是否与最初那个议题／规格说明所要求的一致？）。两条评审各交给一个并行子代理去跑，然后并排报告结果。适用于用户想评审一条分支、一个 PR、进行中的改动，或者说「评审自 X 以来」的场合。

Autonomous batch mode for Vault Health findings. Works through orphans, missing backlinks, and tags in batches without asking on every fix.

Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism, the files, symbols or kernels it touches (or a local diff), the upstream…

检查并解释 portable Pragma bundle 的内容、依赖和环境绑定。

Design and document a ai adoption plan with structured process, quality checks, and system integration

Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across…

Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段", "增加字段", "新增字段", "修改字段",…

用于【AI科幻】题材下的章节正文创作。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口名，补充起点追读、数据追溯程序、真实编号、数字压迫感与文件写回要求，并要求生成的 ` ## 作者有话说` 保持读者向小剧场口感。

Automatically allocate and manage development server ports, avoiding port conflicts between multiple Claude Code instances

Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT…

Accessibility testing toolkit using Selenium WebDriver 4+ with Java 21+ and axe-core engine. Use when asked to validate WCAG 2.2 AA compliance, scan pages or components for a11y violations, test…

Router skill for LLMQuant credit workflows. Use when the user needs issuer credit review, spread regime analysis, high-yield stress monitoring, default risk, debt maturity, or covenant context.

Create REST/GraphQL API endpoint with validation, error handling, and tests. Auto-invoke when user says "add endpoint", "create API", "new route", or "add route".

AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. 과학적 언어학 연구(KatFishNet 논문, 94.88% AUC 정확도)에 기반합니다. 쉼표 과다, 띄어쓰기 경직성, 품사 다양성, AI 어휘 과용, 번역투(에 대해/통해/되어진다), 대명사 과다, 복수형 과다, 구조적 단조로움 등 40가지 패턴을…

Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.

OpenYida 跨端发布风险守卫。当改动涉及浏览器/URL 拉起（openyida login、bridge 页面唤起、resolveBrowserLauncher、openBrowser、spawn 打开浏览器），或用户明确要求检查 Windows/Linux 发布风险时使用。用于静态扫描并拦截「cmd /c start 截断 URL」「open -n 假装开新窗口」等跨端问题；普通版本…

Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent. Includes a background client for task progress, follow-up prompts, conversation recovery,…

Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code.…