全部能力

Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.

将 PRD 转换为 prd.json 格式以供 ralph-tui 执行。创建包含用户故事、验收标准和依赖项的 JSON 任务文件。触发条件：create…

Enable multiple Claude Code instances to discover each other and exchange messages in real-time via a local broker daemon and MCP server.

Odoo 19 development knowledge base with 18 specialized guides covering Actions (ir.actions.*, cron jobs, server actions), Controllers (HTTP routing, endpoints, auth types), Data files (XML/CSV records, shortcuts, noupdate), API Decorators (@api.depends, @api.constrains, @api.ondelete, @api.onchange, @api.model, @api.private), SQL Constraints (models.Constraint replacing _sql_constraints), Database Indexes (models.Index), Module development (manifest, wizards, reports), Field types (Char, Text, Monetary, relational fields), Manifest configuration (__manifest__.py, dependencies, asset bundles), Mixins (mail.thread, mail.activity.mixin, mail.alias.mixin, utm.mixin), ORM Model methods (search, CRUD, domain filters, recordsets, CamelCase model naming), Migration scripts (pre/post/end hooks, data migration), OWL frontend components (hooks, services, lifecycle), Performance optimization (N+1 prevention, batch ops, _read_group), QWeb Reports (PDF/HTML, paper formats, barcodes, t-out), Security/ACL (record rules, field permissions, privilege-based groups, @api.private), Testing (TransactionCase, HttpCase, mocking, query count assertions), Transactions (savepoints, UniqueViolation, serialization failures), Translations (i18n, PO files, translatable fields), XML Views (list/form/search, kanban card templates, xpath inheritance, QWeb templates). Use when writing, reviewing, or debugging any Odoo 19 Python or XML code, creating or modifying modules, fixing performance issues, or looking up Odoo 19 API patterns and best practices.

Strategies for managing LLM context windows including

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

缺陷→规约协议。当发现缺陷或测试失败时，追溯原因，判断是否需要新增 §V 不变式来防止复发，并将其追加至 §B。这是 SDD 所做的、计划-执行模式所不具备的一项非显而易见的举措。在测试失败、缺陷报告、事后复盘或用户明确要求时触发。

在仓库根目录的 SPEC.md 中创建、修订或反向传播 bug。该项目规范的唯一修改者。当用户要求编写规范、创建新规范、从现有代码提炼规范、添加不变量、修订章节（§G、§C、§I、§V、§T、§B）或通过反向传播记录 bug 时触发。常见表述：“write the spec for...”、“new spec”、“bug: ...”、“amend §V.3”、“distill spec from code”、“spec this idea”。读取并遵循 FORMAT.md 中的原始人编码规则以及 §T 和 §B 的竖线表格形状。

React Native and Expo development guide covering components, styling, animations, navigation, state management, forms, networking, performance optimization, testing, native capabilities, and engineering (project structure, deployment, SDK upgrades, CI/CD). Use when: building React Native or Expo apps, implementing animations or native UI, managing state, fetching data, writing tests, optimizing performance, deploying to App Store/Play Store, setting up CI/CD, upgrading Expo SDK, or configuring Tailwind/NativeWind.

Expert in building Telegram Mini Apps (TWA) - web apps that run

使用 Agent CI 在本地运行 GitHub Actions CI，以便在推送前验证更改。适用于测试、运行检查或验证代码变更。

Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review,…

Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.

Expert in building portfolios that actually land jobs and clients -

Implement an approved feature from PRODUCT.md and TECH.md, keeping specs and code aligned in the same PR as implementation evolves. Use after the product and…

Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI…

Inngest expert for serverless-first background jobs, event-driven

This skill should be used when the user asks "what's the config", "show me the configuration", "what variables are set", "environment config", "service…

Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal,…