@davidondrej
founder of Cloudroom
61 skills1 repository 4.2K
Publish saved skill and global AGENTS.md changes to a private repository, then check the automated public mirror. The workflow isolates intended edits, preserves unrelated work, and verifies the actual published content.
Rewrite a prompt to address the same task more deeply. The skill identifies what an expert would examine, which original materials and methods they would use, and what independent evidence would confirm the result.
Work through sixteen open questions in four rounds to clarify major product decisions, risky changes, or large refactors. The agent adapts later questions to earlier answers, then turns your decisions into a step-by-step implementation plan.
Request an independent code review using Meta Muse Wonder at max reasoning through Pi and OpenRouter. Receive the reviewer's complete, unchanged report on serious issues, proposed fixes, validation gaps, and readiness to merge into production.
Explore four new design options for a subject, with each option presented as a separate rendered image. Use the images to compare possible appearances and consider improvements to an existing design.
Review a conversation with a concise three-to-five-sentence summary in plain English, including the original request. Then get the previous response rewritten in shorter, simpler language with readable Markdown formatting.
Compare your notes with an expert's essays, talks, or interviews on a chosen topic. Receive exact quotes, source file locations, and an analysis that identifies connections and at least one gap in your thinking.
Read every architecture decision record in a project's docs/adr/ folder from beginning to end, giving the agent context about earlier design choices before it starts further work.
Get a short, practical decision when deliberation stalls. This manually invoked skill highlights critical or serious issues, otherwise says work can proceed, and gives next steps in concise, plain English.
Create short HTML lessons and interactive practice tailored to a learning goal and prior progress. Keep learning records, trusted resources, and quick reference documents in the workspace to support study across multiple sessions.
Capture ideas for videos, articles, businesses, and small projects in separate files, with entry numbers and source details. The skill commits and pushes the additions to a Git repository for later review.
Rename the current thread or session in Cloudroom with a short title describing its main activity. When explicitly requested, the skill chooses two to five lowercase words, updates the title through room-cli, and returns the new name.
Delegate a self-contained coding task to Codex CLI from another agent using ChatGPT subscription authentication. Run independent implementation, request a second opinion, or verify changes, with separate working copies for parallel tasks.
Create and manage Boat cloud sandboxes, remote machines for development work, through API, CLI, or SSH. Configure repositories and secrets, prepare reusable templates, manage machine state, and verify coding agents inside the selected environment.
Create a copy-ready prompt teammates can give their AI agents to apply a fix, upgrade, or setup change. It includes tested commands, verification steps, stopping conditions, and what to report, with enough context to work independently.
Manage local development servers and APIs with macOS LaunchAgents, which run background processes. Keep servers running after the shell closes, restart them after crashes, inspect logs, and handle occupied ports when starting a service.
Assess online purchases and subscriptions by comparing prices, checking seller trust, and considering delivery. It summarizes suitable places to buy and relevant business tax checks, while leaving orders, accounts, and payment details to the user.
Automate web tasks in an already-running Chrome session, including clicks, forms, and content extraction from signed-in pages. Use screenshots to guide actions and verify visible results, with remote browsers available for isolated work.
Use Cua Driver to operate desktop apps and browsers for testing, form filling, calendar entries, screenshots, and requested demo recordings. Inspect the target window before acting and check its state afterward to verify results.
Review important choices the agent made during the current work and identify those it remains unsure about. It considers overlooked alternatives and returns a concise list in plain English when explicitly requested by name.
Review code independently with five AI models, combine their reports, and filter out duplicate or unsupported findings. Present concrete bugs and risks for approval, then fix only the issues the user accepts.
Coordinate project or repository renames and moves across Git, tools, services, and machines. Preserve local work and history, update affected paths and references, and verify that the relevant workflows function at the new location.
Check assumptions before changes to APIs, pricing, quotas, or defaults. This skill combines research, measurements from real services, documented results, and product-owner approval to assess customer impact beyond passing tests, with follow-up verification after deployment.
Turn recurring work into a defined Grok Bot role and a setup prompt ready to paste into the app. Clarify tools, workflow, schedule, approval requirements, and a first task to test the role.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)