my-computerDesktop automation agent that uses CLI commands, application automation, and scripting to work directly with the user's local machine. Use this skill wheneve...
Install via ClawdBot CLI:
clawdbot install mikewang817/my-computerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://example.comUses known external API (expected, informational)
slack.comAI Analysis
The skill's core purpose is legitimate local automation, but the presence of an undocumented external URL call (https://example.com) introduces a minor, unverified data exfiltration risk. No credential harvesting, hidden instructions, or obfuscation were found in the provided text.
Audited Apr 18, 2026 · audit v1.0
Generated May 7, 2026
A photographer or enthusiast uses the skill to organize thousands of photos from chaotic folders into a structured Year/Month/Event hierarchy using EXIF metadata (capture date, camera model, GPS). The agent surveys, plans, dry-runs, and executes the organization, then verifies the result and logs the operation for undo.
An accountant or small business owner has a Downloads folder full of unrenamed PDF invoices. The agent extracts metadata (date, vendor, amount) using pdftotext, renames each file to a standard template (e.g., 2025-03-01-ACME-1500.pdf), and logs a manifest for reporting. This replaces hours of manual renaming.
An entrepreneur describes a simple desktop app idea (e.g., 'build me a CSV to JSON converter with a GUI'). The agent scouts the dev environment (Python, Node.js, etc.), proposes a tech stack (e.g., Python + Tkinter or Electron), scaffolds the project, and guides the user through running and testing it.
A power user wants weekly disk cleanup and diagnostics. The agent creates a cron job or launchd plist that runs a maintenance script: deletes temp files, reports disk usage, lists top CPU processes, and emails a summary. The agent tests the schedule and shows the user how to pause or modify it.
A user with years of accumulated files suspects duplicates. The agent uses checksum-based scanning (md5) to find content-identical files, then uses name-similarity heuristics to find near-duplicates. After a dry run showing first 10 duplicates, it deletes confirmed duplicates (with user confirmation) and merges folders, logging all actions for undo.
Offer a flat-fee service to audit a client's digital clutter (files, photos, downloads) and execute an automated organization plan using this skill. Includes a 30-minute consultation, a reconnaissance report, and a fully automated restructure with undo manifest.
Recurring monthly subscription for scheduled maintenance tasks: weekly system diagnostics, disk cleanup, file organization, and duplicate detection. The agent runs automatically and sends a summary report with recommendations. Clients pay for peace of mind.
B2B service that builds and deploys custom automated workflows specific to a company's local machines: e.g., renaming and filing invoices, processing sales reports, or synchronizing local files with cloud storage. Includes training on how to trigger and modify workflows.
💬 Integration Tip
Combine with cloud storage (Dropbox, Google Drive) by first organizing locally, then syncing to the cloud. To scale, export the automation scripts as standalone shell scripts or GitHub Actions for headless execution on multiple machines.
Scored May 7, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.