AI Skills Directory

Write API contract, 写接口契约。Use when: PRD 完成后、HLD 之前需要定义 OpenAPI/AsyncAPI/GraphQL/gRPC/WebSocket/SSE/Webhook/SDK/文件格式规范。 也用于既有相关文档的有限增量更新。

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent…

Use when a CI release/build pipeline runs a smoke test that boots the project's bundled binary against an external dependency stack (PostgreSQL, MySQL, Redis, MongoDB, S3, etc.) and the test fails…

酒店预订/选酒店/住哪里。用于用户要你“订酒店/选酒店/酒店推荐/比较官网和OTA价格/确认取消政策与早餐/靠近某地标住哪更方便”等场景。 默认官网优先、再用 OTA 比价；不自动下单；引用外部事实必须尽量给来源链接与来源当地时间；绝不编造。

Load whenever building or debugging an Iced UI.

Android app manager with VPN integration that freezes/unfreezes app groups based on VPN connection state using Shizuku's pm disable-user

Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).

Review implementation plans from the .tasks/ directory for flaws before committing — either a single phase (phase mode) or across all phases of a task for consistency (cross-phase analyze mode).…

Coordinates multi-session, delegated, or long-running work with persistent state, recovery checks, and explicit status transitions. Use when a task spans multiple turns, multiple agents, background…

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the…

Choosing the right concurrency abstraction in .NET - from async/await for I/O to Channels for producer/consumer to Akka.NET for stateful entity management. Covers both high-level abstractions and…

Laravel 13 queue and job patterns — driver choice, job design (idempotency, ShouldQueue, model serialisation), retry and failure handling, worker scaling, Bus batching and chaining, Horizon when…

Navigation implementation patterns for turn-by-turn directions, route optimization, real-time traffic, multi-stop routing, and voice guidance across web, iOS, and Android platforms

Undo a change already written to a ServiceNow instance — recover the prior payload from sys_update_version, write it back without corrupting it, and know which damage update set back-out, Deleted…

Zoom Meeting SDK for macOS native apps. Use when embedding Zoom meetings in macOS with default/custom UI, PKCE + SDK auth, host start/join flows, and desktop meeting feature controllers.

Test-driven development for Drupal with PHPUnit and Drupal Test Traits (DTT). Use when writing or fixing tests, reproducing a bug before fixing it, choosing a bootstrap level (Unit vs Kernel vs…

Copilot agent that assists with CI/CD pipeline creation, infrastructure automation, Docker/Kubernetes deployment, and DevOps best practices Trigger terms: CI/CD, DevOps, pipeline, Docker, Kubernetes,…

Research customer context across docs, tickets, CRM, email, and web sources with cited confidence.

Comprehensive Odoo ERP upgrade assistant for migrating modules between Odoo versions (14-19). Handles XML views, Python API changes, JavaScript/OWL components, theme SCSS variables, manifest updates,…

Knowledge engineer — architecture docs, ADRs, diagrams, changelogs, onboarding, and reports. Use when asked to "write an ADR", "map the architecture", "document this decision", "onboarding docs", or…

Create or update a Lens chart documentation page following Elastic docs conventions. Use when writing a new chart type page (pie, bar, metric, gauge, heat map, etc.) or updating an existing one in…

Load when Codex 即将要求用户在 2-3 个互斥方案中做真实决定、准备询问阻塞性澄清问题或需要确认高影响取舍；将选择转换为宿主原生可点击 UI，并在工具不可用时诚实文本回退。不要用于低风险实现细节、只有一个合理答案的问题、普通信息采集或不需要用户决策的完成汇报。

Guides the agent through upgrading a Capacitor app from v7 to v8. Use when the project is on Capacitor 7 and needs the v8 migration path. Do not use for other major versions, plugin-only upgrades, or…

Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agents.md", "review my agents.md", "claude.md", or questions about agent…

Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports…

Anti-forensics is the offensive counterpart to digital forensics.

Stellar spectral analysis from first light to chemical abundance. Covers continuum emission and absorption, the OBAFGKM classification sequence, luminosity classes, line identification, Doppler…

Expert guidance for testing web applications using Playwright and other testing frameworks. Use when testing UIs, automating browser interactions, or validating web app behavior.

Business logic, race conditions, and AI security analysis

State machines, ISRs, RTOS, hardware abstraction, and timing analysis — domain expertise for electrical and embedded systems engineers

清理冗余 CSS 并在现有 Tailwind 项目中重构样式。支持明确输入与结果回读。Use to refactor CSS and Tailwind styles.

Use when updating, versioning, deprecating, or maintaining existing Standard Operating Procedures. Covers keeping SOPs accurate, relevant, and synchronized with implementation changes.

Learning & Decision Expert

Deliver an explicitly requested multi-subtask plan as sequential reviewed and verified commits with one aggregate publication path. Use only when the user requests or accepts this workflow; subtasks…

Manage content, chats, subscribers, and earnings on the Fanvue creator platform via OAuth 2.0 API.

Help with CDS (Core Data Services) view entity development including data modeling, annotations, associations, compositions, access controls, aggregate expressions, built-in functions, and input…

Next.js App Router best practices covering file conventions, RSC boundaries, async APIs, data patterns, hydration errors, metadata, route handlers, image/font optimization, and bundling. Use when…

Use when writing or reviewing MSSQL/T-SQL, creating stored procedures, designing table schemas, writing views, building migrations, defining custom types, or architecting a SQL Server application…

Create structured game info/rules content for slot games. Invoke when drafting game info sections, symbol payouts, bonus purchase rules, or required disclaimers.

Write and run tests for Frappe apps including unit tests, integration tests, and UI tests. Use when adding test coverage, debugging test failures, or setting up CI for Frappe projects.

Configure and use the Backoffice Reson8 speech-to-text capability. Use when setting up Reson8, transcribing audio files, or debugging Reson8 runtime availability.

Use when you have a spec or requirements for a multi-step task, before touching code

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

Patrones idiomáticos de Go, buenas prácticas y convenciones para construir aplicaciones Go robustas, eficientes y mantenibles.

Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or…

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting…

Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

Quarterly / monthly financial report — masthead with KPIs, revenue and burn charts, P&L summary table, top-line highlights, and an outlook paragraph. Use when the brief mentions "financial report",…

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits,…

Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or…