Guide for ingesting the latest OpenAI TypeSpec specification into the openai-dotnet SDK. Use this when asked to update or ingest OpenAI API specs, copy base TypeSpec files from upstream, fix client TSP compile errors, or run code generation for new API areas.
AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai. No API keys or dependencies required — all content is fetched from a central feed.
Comprehensive guide for kagent development covering CRD modifications, E2E testing, PR workflows, local deployment, and debugging. Use this skill when working on the kagent codebase itself - adding features, fixing bugs, reviewing PRs, running tests, or troubleshooting failures. Trigger for any kagent development tasks including understanding the codebase structure, modifying CRDs, writing tests, deploying locally, or analyzing CI failures.
Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".
Generates HTTP request examples for Spring Boot Web interfaces according to task specification and saves them as .http files in module-generate.md directories
Generates comprehensive README.md files for Spring Boot modules based on task specification requirements
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill for TorchRec, or needs help with SKILL.md files.
Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.
Project knowledge base and workflow router. knowledge/ caches previously explored file locations, module boundaries, and call chains for direct reuse; decisions/maxims are established architectural decisions and coding standards -- follow, don't re-debate; pipelines are reusable workflows; short-term/ holds new conclusions temporarily, promoted or deleted upon expiry. Use self-improve to capture new insights after completing tasks. Provides five tools: init, upgrade, migrate, doctor, self-improve.
Search your coding memory. Use when user asks about past work, previous sessions, how something was implemented, what they worked on before, or wants to recall information from earlier sessions.
业务知识获取与 Skill 文档编写工作流。当用户需要熟悉新业务模块、从 iWiki 获取文档、结合代码分析生成架构文档、或将业务知识沉淀为 Skill 时使用。
Guide for deprecating R functions/arguments. Use when a user asks to deprecate a function or parameter, including adding lifecycle warnings, updating documentation, adding NEWS entries, and updating tests.
Builds volume and chapter outlines from the total outline, inherits creative constraints, and prepares writing-ready chapter plans. Use when the user asks for outlining or runs /webnovel-plan.
触发：当你准备下判断、做决策或提出建议，但事实、上下文或一手信息还不充分时优先调用；常见信号包括 unknowns、信息缺口、证据不足、领域陌生、需要先摸清现状。 English: Trigger before making claims or decisions when context is incomplete, evidence is weak, or the domain is unfamiliar. Use this skill to investigate first, gather firsthand facts, and let reality shape the conclusion.
Use this skill when running .NET CLI commands — building, testing, restoring packages, formatting code, or running projects. Covers dotnet build, test, restore, format, run, and NuGet package management. Apply when troubleshooting build errors, running the backend, or executing any dotnet command-line operation.
Use this skill when querying, counting, patching, or paginating data through Foundatio.Repositories Elasticsearch abstractions. Covers filter expressions, aggregation queries, partial and script patches, and search-after pagination. Apply when working with any repository method — never use raw IElasticClient directly.
Use when code changes may have made documentation outdated, when reviewing docs for consistency, or when the user asks to sync or audit documentation.
Guides design and review of computer-graphics rendering tests for the cg crate. Covers the distinction between reftests (independent oracle), golden/snapshot regression tests (previously accepted output), and observation-based probe tests (pixel/color assertions without vision). Use when adding, reviewing, or debugging visual comparison tests, pixel diffs, golden image generators, SVG reftest suites, or designing fixtures that can be verified programmatically by probing pixel values. Relevant paths: crates/grida-canvas/tests/, crates/grida-canvas/goldens/, crates/grida-canvas/examples/golden_*, crates/grida-dev/src/reftest/, fixtures/test-svg/, docs/wg/feat-svg/testing.md.
Author and manage user-facing documentation for the Grida Canvas editor. Covers writing style, tone, product screenshots, demo state preparation, and content structure for pages under docs/editor/. Use when creating or editing canvas editor documentation, capturing screenshots of canvas features, or planning visual demos. Trigger phrases: "write user docs", "document this feature", "screenshot for docs", "canvas user guide", "update help page".
