Agent Skills: macos-computer-use
|
desktopID: PoorRican/dotfiles/macos-computer-use
Install this agent skill to your local
Skill Files
The files that make up macos-computer-use.
More agent skills
- ai-wrapper-productExpert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
- performance-reviewPerformance-focused code review for identifying bottlenecks and optimization opportunities
- trailsTrails — Cross-chain swap, bridge, and DeFi orchestration via Sequence. Use when an agent wants to swap tokens across chains, bridge assets, fund a Bankr wallet from any chain, deposit into yield vaults (Aave, Morpho), get token prices, discover earn pools, or quote cross-chain routes. Integrates with Bankr submit() for on-chain execution. Also use when asked about Trails, Sequence swaps, cross-chain bridging, or DeFi yield deposits.
- ulw-planACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their own words for a work plan before coding. NEVER self-activates: a bare ulw/ultrawork run, an agent-side routing decision, or reading this file is not a request, and the plan-gated reviewers (metis/momus) stay locked without a user request plus a written .omo/plans plan file. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, ulw plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode.
- deepchat-sddUse before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Use plan.md as the only separate tracker when needed, default to implementation-first validation, and ask before optional GitHub issue sync unless the developer explicitly requested sync.
- slop-checkStrip agent-generated noise from a diff — comments that restate the code, private helpers in test files, near-duplicate tests, tests with no assertions, unrequested indexes and validation, defensive guards that duplicate an existing check. Use before opening a PR on agent-written code, or when the user asks to tighten a diff, remove slop, or cut verbose comments.