Create a directory in a sandbox. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Remove a file from a sandbox. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Remove a directory from a sandbox. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Run a one-shot command in a sandbox (creates, executes, destroys). Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Create a snapshot from a sandbox. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete a snapshot. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get snapshot details. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Add or update a tag on a snapshot. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Upload a compressed archive to a sandbox and extract it. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Download a file using security copy. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Upload a file using security copy. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get details about a specific session. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get logs for a specific session. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
SSH into a cloud project or sandbox. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete a storage resource or file. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Download a file from storage bucket. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Show details about a specific storage bucket. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
List storage resources or files in a bucket. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Upload a file to storage bucket. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete a stream by ID (soft delete). Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get detailed information about a specific stream. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get details about a specific thread. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete one or more vectors by key. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete a vector namespace and all its vectors. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get a specific vector entry by key. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Get statistics for vector storage. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Add or update vectors in the vector storage. Requires authentication. Use for Agentuity cloud platform operations
Score 80/100
Delete a project. Requires authentication. Use for project management operations
Score 80/100
Show project detail. Requires authentication. Use for project management operations
Score 80/100
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications.
Score 80/100
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package.
Score 80/100
Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates.
Score 80/100
Execute project-specific verification rules. Validates business logic, architecture patterns, and naming conventions that linters cannot catch.
Score 80/100
Python 执行增强（uv heredoc 规范）。TRIGGER when: Bash 工具中需要执行 Python 代码（多行脚本、依赖安装、uv run 调用）。SKIP: 纯 shell 命令、不涉及 Python 的 Bash 操作。
Score 80/100
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality…
Score 80/100
Generate conventional commit messages without scope from staged changes. Use when: preparing commits with #git_diff_staged to create concise commit messages following conventional…
Score 80/100
Generate descriptive commit messages by analyzing git diffs, very fast and context pollution safe. Use on any request to commit staged changes.
Score 80/100
Commit changes with well-crafted messages, grouping related files into separate commits
Score 80/100
Generate and run comprehensive test suites — unit tests, integration tests with real services (testcontainers/docker-compose), and Playwright E2E tests.
Score 80/100
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…
Score 80/100
Find all @deprecated APIs in the workspace, count their callers, and extract migration guidance. Produces a prioritized report sorted by call count so you know which deprecations…
Score 80/100
Test coverage heatmap from lcov or JSON coverage data. Finds coverage reports, parses line coverage per file, and renders a color-coded file-tree heatmap as HTML.
Score 80/100
Find unused exports, dead functions, and unreachable code across the workspace using LSP analysis. Cross-verifies detectUnusedCode with findReferences to eliminate false…
Score 80/100
Full debug workflow using IDE bridge tools. Runs tests to find failures, sets conditional breakpoints, evaluates expressions in the debugger, identifies root causes, applies…
Score 80/100
Dependency graph for a file or symbol. Calls getCallHierarchy and findReferences, builds a directed graph, and renders an interactive HTML force-directed graph.
Score 80/100
Diagnostic dashboard across the workspace. Calls getDiagnostics, groups results by severity and file, and renders a sortable color-coded HTML table. Opens in the system browser.
Score 80/100
Deep codebase exploration using IDE bridge LSP tools. Maps architecture, traces call chains, discovers entry points, and builds a mental model of unfamiliar code.
Score 80/100
Continuous IDE monitoring using bridge tools. Checks diagnostics, test results, or terminal output. Designed for use with /loop for recurring checks.
Score 80/100
Multi-language code quality sweep using IDE bridge tools. Runs diagnostics across all languages, auto-fixes lint errors, organizes imports, formats code, runs tests, and…
Score 80/100
Safe refactoring with snapshot rollback. Creates a checkpoint, performs the refactoring using LSP rename and code actions, runs tests, and rolls back automatically if anything…
Score 80/100
Deep PR review using IDE bridge LSP and GitHub tools. Analyzes diffs with code intelligence — follows definitions, checks references, inspects types, runs diagnostics, and posts…
Score 80/100
Diagnose and fix TypeScript/language type errors using LSP diagnostics, hover, and code actions. For each type error, fetches the expected vs actual types, surfaces quickfix…
Score 80/100
One-time workspace setup. Generates local context files (.claude/context/, git-ignored) that all workflows depend on — repo metadata, coding conventions, local repo paths,…
Score 80/100
Use when you need to lint the codebase and auto-fix issues - detects linter, runs it, and fixes what it can.
Score 80/100
Decompose an approved requirements summary into an implementation plan with atomic tasks, Mermaid diagrams, and a task tracker.
Score 80/100
Analyzes any codebase and generates a complete, tailored skill pack — coding skills, review agents, Q&A agents, and a shared guidelines document, all grounded in the actual…
Score 80/100
Wave-based comprehensive project documentation generator with dynamic task decomposition. Analyzes project structure and generates appropriate documentation tasks, computes…
Score 80/100
Generate professional freelancer proposals, scopes of work, and project quotes from a brief description.
Score 80/100
Generate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas.
Score 80/100