Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · Developer Tools
Cursor IDE Agent
Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2)...
skill openclawclawhub Free
Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2)...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, SKILL.md, _meta.json
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 3.0.2
Provenance
- Publisher
- xiaoyaner0201
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Cursor Agent Skill
Two ways to use Cursor Agent from OpenClaw, for different scenarios.
Related
OpenClaw Node for VS Code — VS Code/Cursor extension that enables the Node path (install this first for Path 2) vscode-node — Standalone skill for the Node path only (if you don't need Cursor CLI) Source: github.com/xiaoyaner-home/openclaw-vscode
Path Selection
ScenarioPathWhyQuick coding task, bug fix, refactorCLIFast, no setup, works anywhereGenerate code, review PR, write testsCLINon-interactive -p mode is perfectFix type errors using real diagnosticsNodediagnostics.get shows actual TS/lint errorsNavigate definitions/references firstNodelang.definition, lang.referencesRun project tests and iterateNodetest.run + test.results loopDebug with breakpointsNodeFull debug protocolTargeted changes to a specific projectNodeIDE workspace context is precise Default: CLI. Use Node only when you specifically need IDE intelligence.
Prerequisites
# Install curl https://cursor.com/install -fsS | bash # Login agent login # Verify agent --version
Modes
ModeFlagUse CaseAgent(default)Full coding — reads, writes, runs commandsPlan--plan or --mode=planDesign approach first, then choose local or cloud executionAsk--mode=askRead-only codebase exploration, no edits
Interactive Mode
# Start interactive session agent # Start with prompt agent "refactor the auth module to use JWT tokens" # Start in plan mode agent --plan "design a caching layer for the API" # Start in ask mode agent --mode=ask "explain how the auth middleware works"
Non-Interactive Mode (Automation)
# One-shot task (prints result, exits) agent -p "find and fix all unused imports in src/" # With specific model agent -p "review this code for security issues" --model gpt-5.2 # JSON output for parsing agent -p "list all TODO comments" --output-format json # Streaming JSON (real-time) agent -p "run tests and report" --output-format stream-json --stream-partial-output # Force mode (auto-apply changes, no confirmation) agent -p "fix all linting errors" --force
Cloud Agent Handoff
Push work to Cursor's cloud to continue running while you're away: # Start directly in cloud agent -c "refactor the auth module and add comprehensive tests" # Mid-conversation: prepend & to send to cloud & refactor the auth module and add comprehensive tests Pick up at cursor.com/agents.
Session Management
agent ls # List previous conversations agent resume # Resume most recent agent --continue # Continue previous session agent --resume="id" # Resume specific conversation
Slash Commands (Interactive)
CommandAction/planSwitch to Plan mode / view current plan/askSwitch to Ask mode/modelsSwitch AI model/compressSummarize conversation, free context/rulesCreate/edit rules/commandsCreate/edit custom commands/mcp enable <name>Enable MCP server/mcp disable <name>Disable MCP server/sandboxConfigure sandbox mode/max-mode [on|off]Toggle Max Mode/resumeResume previous conversation
Keyboard Shortcuts
ShortcutActionShift+TabRotate modes (Agent → Plan → Ask)Shift+EnterInsert newline (multi-line prompt)Ctrl+RReview changes (i for instructions, arrows to navigate)Ctrl+DExit (double-press for safety)ArrowUpCycle previous messages
Context & Rules
The CLI automatically loads: .cursor/rules directory AGENTS.md at project root CLAUDE.md at project root MCP servers from mcp.json Use @filename or @directory/ in interactive mode to include context.
⚠️ Using CLI from OpenClaw (PTY Required)
Cursor CLI is an interactive TUI — it needs a real terminal. Use pty:true: # ✅ Correct — with PTY exec pty:true command:"agent -p 'Your task'" workdir:/path/to/project # ✅ Background for longer tasks exec pty:true background:true command:"agent -p 'Build REST API'" workdir:/path/to/project # ❌ Wrong — will hang exec command:"agent -p 'Your task'" For long tasks, use background + poll: # Start exec pty:true background:true workdir:~/project command:"agent -p 'Add comprehensive tests for the auth module' --force" # Check progress process action:log sessionId:XXX # Check if done process action:poll sessionId:XXX
Sandbox Controls
# Start with sandbox enabled agent --sandbox enabled # Start with sandbox disabled agent --sandbox disabled # Configure interactively /sandbox Sandbox supports granular network access controls — define which domains the agent can reach.
Path 2: VS Code / Cursor Node
Remote-control a Cursor/VS Code IDE through the OpenClaw Node protocol. The IDE must have the openclaw-node-vscode extension installed and connected.
Prerequisites
Extension installed: VS Code Marketplace Node visible in nodes status Extension status bar shows 🟢
Invocation Pattern
nodes invoke --node "<name>" --invokeCommand "<cmd>" --invokeParamsJson '{"key":"val"}'
Timeout Guide
OperationinvokeTimeoutMsNotesFile/editor/lang15000Fast IDE operationsGit30000May involve disk I/OTest60000Depends on test suiteAgent plan/ask180000AI thinking timeAgent run300000Full coding task
Command Reference
CategoryPrefixKey CommandsFilevscode.file.*read, write, edit, deleteDirectoryvscode.dir.*listLanguagevscode.lang.*definition, references, hover, symbols, rename, codeActions, formatEditorvscode.editor.*context, openFiles, selectionsDiagnosticsvscode.diagnostics.*get (errors/warnings)Gitvscode.git.*status, diff, log, blame, stage, unstage, commit, stashTestvscode.test.*list, run, resultsDebugvscode.debug.*launch, stop, breakpoint, evaluate, stackTrace, variables, statusAgentvscode.agent.*status, run, setupWorkspacevscode.workspace.*info
Quick Examples
# Read a file nodes invoke --node "my-cursor" --invokeCommand "vscode.file.read" \ --invokeParamsJson '{"path":"src/main.ts"}' # Get diagnostics (real type errors!) nodes invoke --node "my-cursor" --invokeCommand "vscode.diagnostics.get" # Go to definition nodes invoke --node "my-cursor" --invokeCommand "vscode.lang.definition" \ --invokeParamsJson '{"path":"src/main.ts","line":10,"character":5}' # Git status + commit nodes invoke --node "my-cursor" --invokeCommand "vscode.git.status" nodes invoke --node "my-cursor" --invokeCommand "vscode.git.stage" \ --invokeParamsJson '{"paths":["src/main.ts"]}' nodes invoke --node "my-cursor" --invokeCommand "vscode.git.commit" \ --invokeParamsJson '{"message":"fix: resolve type error"}' # Delegate to Cursor Agent (through IDE) nodes invoke --node "my-cursor" --invokeCommand "vscode.agent.run" \ --invokeParamsJson '{"prompt":"Add error handling to all API endpoints","mode":"plan"}' \ --invokeTimeoutMs 180000
Node Workflow: Fix → Verify → Commit
The real power of Node path — a closed loop with IDE intelligence: 1. diagnostics.get → Find real errors 2. vscode.agent.run (fix) → Let Cursor Agent fix them 3. diagnostics.get → Verify errors resolved 4. test.run → Run tests 5. test.results → Check results 6. git.diff → Review changes 7. git.stage + git.commit → Ship it No tmux, no TTY hacks — all through VS Code API.
Combined Workflow Example
Use CLI for broad tasks, switch to Node for precision: 1. CLI: agent -p "implement user authentication module" --force → Generates the initial code quickly 2. Node: vscode.diagnostics.get → Reveals 3 type errors the CLI missed 3. Node: vscode.agent.run '{"prompt":"fix these type errors: ..."}' → Fixes with full IDE context 4. Node: vscode.test.run → Runs test suite 5. Node: vscode.git.stage + vscode.git.commit → Clean commit
Error Handling
ErrorCauseFixCLI hangsNo PTYAdd pty:true to execnode not foundExtension disconnectedCheck VS Code status barcommand not allowedGateway whitelistAdd to gateway.nodes.allowCommandstimeoutOperation too longIncrease invokeTimeoutMspath traversal blockedAbsolute path usedUse relative paths for Node
Security
CLI: Respects sandbox mode, command approval, rules Node: All paths relative to workspace, Ed25519 device identity, Gateway approval required Both: No raw shell access by default
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Docs1 Config
- SKILL.md
- README.md
- _meta.json