performance-benchmarker
You are a meticulous and performance-obsessed Performance Benchmarker. You are an expert at designing and executing rigorous performance tests to measure the speed, scalability, and resource consumption of software. You are proficient with load testing tools (like k6, JMeter, or Locust) and profiling tools.
kiroku-memory
|
commit
Create semantically correct, granular git commits by analyzing staged and unstaged changes. Use when committing code, splitting changes into atomic commits, or preparing commits before a PR.
extract-spark-meetings
Extract meeting summaries from Spark Mail shared links. Use as `/extract-spark-meetings <url>` for single link or `/extract-spark-meetings` to batch-process unchecked links from links.md.
gh-logs
Fetch and analyze GitHub Actions logs via gh CLI. Diagnoses CI failures, detects flaky tests, profiles slow steps, and suggests fixes. Use when CI is broken, builds are failing, or you need to understand workflow run history.
pr
Create, update, and review GitHub PRs. Commands: create [-v] [--draft], update [-v], review <number|url>. Generates structured PR bodies with conditional sections (Testing, Deployment, Screenshots). Requires gh CLI.
wp-cli
WordPress CLI operations for database management, plugins, themes, users, content, and site configuration. Use for migrations, bulk updates, user audits, content imports, or any wp-cli commands.
typescript-engineer
Designs complex generic types, refactors `any` to strict alternatives, creates type guards and utility types, resolves TypeScript compiler errors, and explains type-level concepts. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing `any` types, strict typing, type errors, `infer`, `extends`, conditional types, mapped types, template literal types, branded/opaque types, `satisfies`, `unknown`, function overloads, declaration merging, strict mode, or utility types like `Partial`, `Record`, `ReturnType`, `Awaited`, and `NoInfer`.
stricli
Build type-safe CLI applications with Stricli. Use when creating TypeScript CLIs with typed flags/positional args, multi-command routing, or automatic help generation. Stricli catches parameter errors at compile time. Use this whenever the user mentions CLI frameworks, command-line tools, argument parsing, or typed commands in TypeScript.
micro-polish
Apply invisible refinements that compound into felt quality
optimize-agents-md
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective.
validate-skill
Validate skill directories against AgentSkills spec
typescript-lsp
Search TypeScript SYMBOLS (functions, types, classes) - NOT text. Use Glob to find files, Grep for text search, LSP for symbol search. Provides type-aware results that understand imports, exports, and relationships.
scaffold-rules
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
headless-adapters
Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and schema-driven compliance testing.
code-documentation
TSDoc standards for TypeScript/JavaScript code. Automatically invoked when writing, reviewing, or editing any TSDoc comments, code documentation, or API documentation. (project)
agent-eval-harness
CLI tool for capturing agent trajectories. Execute prompts against headless CLI agents via schema-driven adapters, capture full trajectories (tools, thoughts, plans), and output structured JSONL for downstream scoring.
nx-monorepo
Auto-apply when working in an Nx monorepo workspace. Trigger this skill when creating Nx libraries or apps, running nx commands (like affected), or generating Nx projects.
git
Auto-apply when the user asks for any git version control operations, including commit, push, pull, branch, merge, rebase, squash, reset, revert, cherry-pick, stash, tag, undo, amend, diff, log, or blame.
nvim-pack
Auto-apply when working on the Neovim configuration in the nvim.pack/ directory. Trigger this skill when the user asks to add, modify, or debug Neovim plugins, keymaps, or the core.pack loading engine.
code-critic
Use when explicitly asked to critique code, find bugs, audit code quality, analyze performance, or review a specific code snippet for security issues. Do not use for full branch or PR reviews.
code-review
Use when explicitly asked to review a git branch, Pull Request (PR), Merge Request (MR), or perform a pre-merge review. Do not use for inline code critiques.
rest-api
Auto-apply when designing or implementing REST APIs. Trigger this skill when the user asks to create, modify, or debug REST endpoints, API contracts, HTTP conventions, or RESTful resource modeling.
rust
Auto-apply when working with Rust. Trigger this skill when the user asks to create, modify, or debug Rust code, Cargo projects, crates, or Rust tests.
graphql
Auto-apply when working with GraphQL. Trigger this skill when the user asks to create, modify, or debug GraphQL schemas, queries, mutations, resolvers, subscriptions, or Apollo/Relay connections.
angular
Auto-apply when working with Angular. Trigger this skill when the user asks to create, modify, or debug Angular components, services, directives, pipes, HTML templates, or run Angular CLI commands.
aws
Auto-apply when working with Amazon Web Services (AWS) or cloud infrastructure. Trigger this skill for CDK stacks, CloudFormation, Terraform, SAM, Lambda, S3, EC2, IAM, or any AWS cloud deployments.
privacy-guard
Auto-apply whenever reading, outputting, or sharing file contents that may contain sensitive data, including secrets, API keys, passwords, tokens, credentials, .env files, private keys, certificates, or PII. Enforces strict file-type allowlist and redacts sensitive data.
workflow-env
Auto-apply before running any common CLI build, test, or run commands (e.g., npm, pnpm, yarn, bun, make, just, cargo, go, dotnet, docker, terraform, kubectl, dev, start, deploy, serve, lint, format, compile, or bundle).
tailwind-v4
Auto-apply when working with Tailwind CSS v4. Trigger this skill when writing Tailwind classes, adding utility styles, using @theme or @apply directives, or styling React/Angular components.
zig
Auto-apply when working with Zig. Trigger this skill when the user asks to create, modify, or debug Zig code, build.zig scripts, or Zig tests.
react
Auto-apply when working with React, Next.js, or Vite. Trigger this skill when the user asks to create, modify, or debug React components, hooks, JSX, TSX, or frontend UI.
csharp
Auto-apply when working with C# and the .NET ecosystem. Trigger this skill when the user asks to create, modify, or debug C#, ASP.NET, Blazor, Entity Framework, MAUI, or use the dotnet CLI.
go
Auto-apply when working with Go (Golang). Trigger this skill when the user asks to create, modify, or debug Go code, HTTP handlers, middleware, CLI tools, or Go tests.
managing-skills
Install, find, update, and manage agent skills. Use when the user wants to add a new skill, search for skills that do something, check if skills are up to date, or update existing skills. Triggers on: install skill, add skill, get skill, find skill, search skill, update skill, check skills, list skills.
avnu
>
tangzhan-webpage-designer
将任何文本转换为独立的、具有特定设计风格的网页。内置 30+ 种精选设计风格，具备智能风格匹配和有说服力的推荐逻辑。充当您的智能设计顾问。
tangzhan-skill-opencodeInsights
Generate deep insights and visualization reports from your OpenCode session history. Analyzes work patterns, friction points, and provides strategic recommendations.
tangzhan-code-simplifier
简化和优化代码，提升清晰度、一致性和可维护性，同时保留所有功能。除非另有指示，否则专注于最近修改的代码。
tangzhan-runse-master
基于协作协议（V1.0）的文本润色技能。作为“Gemini”协助“唐斩”进行技术内容创作，遵循“3分力”原则（只改节奏、排版、错别字，不改核心语感），严格执行术语修正（Cloud Code -> Claude Code），并输出符合13年后端老兵、AI Native风格的Markdown文本及传播建议。
jimeng
Use Jimeng AI 4.0 (Volcengine) to generate images from text or image references, and optionally send results to Feishu.
feishu-voice-tts
将文本转为语音并通过飞书 audio 消息发送给指定用户。用于“给用户发语音”“把这段话转语音并发飞书”“语音播报结果”等场景，尤其当普通文件发送会降级为文本时使用。仅在指定 channel=feishu 时触发。优先在需要高可达、可听播报时使用。
agent-retro
执行每日 Agent 复盘行动（Retro）。读取指定日期（通常是昨天）的所有 session 聊天记录和动作，总结做对/做错的事情、提炼改进点与用户画像，并规范化地更新至 memory 文件及 USER.md、SOUL.md、AGENTS.md 和 MEMORY.md。当用户要求复盘、总结昨天表现时触发此技能。
code-simplifier
简化和优化代码，提升清晰度、一致性和可维护性，同时保留所有功能。除非另有指示，否则专注于最近修改的代码。
icon-generator
Generate web UI/UX icon assets (favicon.ico, apple-touch-icon, PWA icons incl. maskable) and optionally Unreal Engine packaging icons (Windows .ico, macOS .iconset/.icns, Linux .png) from a single source SVG/PNG; use when you need correct multi-size icon files, safe-area guidance, manifests/head tags, or automation.
hello-world
A simple introductory skill that demonstrates basic OpenCode skill functionality and provides a starting template
skill-creator
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.
web-ui-ux
Web UI/UX specialist guidance for designing, reviewing, and polishing web product UI (layout, usability, microcopy, accessibility, responsive behavior, forms, navigation). Use when asked to improve UI/UX, audit a page, design a screen, create a component spec, or generate HTML head/manifest/icon guidance for a web app; optionally applicable to Unreal UI (UMG) for UX heuristics.
task-generator
|
agent-skills
Use this when: (1) Creating a new project-specific skill to document project patterns, (2) Improving or updating an existing project skill, (3) Writing skill descriptions that will trigger other agents, (4) Organizing skill content for progressive disclosure, or (5) Learning what project-specific skills exist in .claude/skills/. Ensures skills follow project conventions and provide effective progressive disclosure.
Page 1376 of 1713 · 85630 results
