CLI 工具
命令行工具
playwright-cli
sonofmagic
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
uloop-compile
hatayama
"Compile Unity project. Use when: verifying code compiles after edits, checking for compile errors, or when user asks to compile. Returns error/warning counts."
uloop-execute-dynamic-code
hatayama
"Execute C# code dynamically in Unity Editor via uloop CLI. Use for editor automation: (1) Prefab/material wiring and AddComponent operations, (2) Reference wiring with SerializedObject, (3) Scene/hierarchy edits and batch operations. NOT for file I/O or script authoring."
uloop-get-hierarchy
hatayama
"Get Unity Hierarchy structure. Use when: inspecting scene structure, exploring GameObjects, checking parent-child relationships, or when user asks about hierarchy. Returns the scene's GameObject tree with components."
uloop-execute-menu-item
hatayama
"Execute Unity MenuItem via uloop CLI. Use when you need to: (1) Trigger menu commands programmatically, (2) Automate editor actions (save, build, refresh), (3) Run custom menu items defined in scripts."
uloop-clear-console
hatayama
"Clear Unity console logs. Use when: clearing console before tests, starting fresh debugging session, or when user asks to clear logs. Removes all log entries from Unity Console."
uloop-get-menu-items
hatayama
"Retrieve Unity MenuItems via uloop CLI. Use when you need to: (1) Discover available menu commands in Unity Editor, (2) Find menu paths for automation, (3) Prepare for executing menu items programmatically."
fix-bug
tddworks
Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design. Use this skill when: (1) User reports a bug or unexpected behavior (2) Fixing a defect in existing functionality (3) User asks "fix this bug" or "this doesn't work correctly" (4) Correcting behavior that violates the user's mental model
performance-testing
DaveSkender
Benchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stream benchmarks, regression detection, and optimization patterns. Target 1.5x Series for StreamHub, 1.2x for BufferList.
lean4
cameronfreer
"Use when editing .lean files, seeing type mismatch/sorry/failed to synthesize instance/axiom warnings, lake build errors, or searching mathlib for theorem proofs."
gemini-tmux-orchestration
serejaris
Use when delegating coding tasks to Gemini CLI agent, when you need parallel AI execution, or when tasks benefit from Gemini's 1M+ context window - orchestrates Gemini via tmux since headless mode cannot write files
ikuai-cli
ikuaidev
CLI for managing iKuai routers via local v4.0 API. Use when the user asks to check router status, configure network/DNS/DHCP/VPN/firewall, manage users, view logs, or automate any iKuai router operation.
difit
yoshiko-pg
After completing the requested implementation, use the difit command to ask the user for a code review.
playwright-cli
VoltAgent
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
dashboard-build
mckinsey
A skill that should be invoked whenever a user wants to build a Dashboard or simple app. This skill is Phase 2 of an e2e process that covers the actual build and testing. For Phase 1 (requirements, layout design, visualization selection), use the dashboard-design skill.
skillforge
tripleyak
"Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality."
xcodebuildmcp-cli
getsentry
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
jira-bulk-operations
grandcamel
"Bulk operations for multiple issues at scale. TRIGGERS: 'bulk update', 'bulk close', 'bulk transition', 'bulk assign', 'transition N issues' (N >= 10), 'update all bugs', 'close 50 issues', 'mass transition', 'update multiple issues', quantities like '50 issues', '100 bugs', '20+ tickets'. Use for operations on 10+ issues. NOT FOR: single issue transitions (use jira-lifecycle), searching only without modifications (use jira-search), single issue field updates (use jira-issue)."
.NET CLI
exceptionless
.NET command-line tools for building, testing, and formatting. Common dotnet commands and development workflow. Keywords: dotnet build, dotnet restore, dotnet test, dotnet format, dotnet run, NuGet, package restore, CLI commands, build system
Storybook
exceptionless
Component stories using Storybook with Svelte CSF. Story patterns, defineMeta, argTypes, snippet-based customization, and visual testing. Keywords: storybook, stories.svelte, defineMeta, Story, args, argTypes, autodocs
agent-browser
exceptionless
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Svelte Components
exceptionless
Svelte 5 component patterns for the Exceptionless SPA. Runes, reactivity, props, events, snippets, component organization, and shadcn-svelte integration. Keywords: Svelte 5, $state, $derived, $effect, $props, runes, onclick, snippets, {@render}, reactive, component composition, shadcn-svelte
agentation-self-driving
benjitaylor
Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.
worktree-status
MoonshotAI
Audit all git worktrees in the current project. Use when the user asks about worktree status, which branches are merged, which have uncommitted changes, or which worktrees can be safely cleaned up.