David Ondrej

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publishing changes to existing skills
• Syncing global AGENTS.md instructions
• Publishing while unrelated local edits are present

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refining a request without expanding its scope
• Identifying original materials and expert methods
• Adding independent criteria for checking results

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying decisions before a major product change
• Planning a large refactor
• Deciding rollout order for a risky change

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting an independent review of code changes
• Checking serious issues before a production merge
• Reviewing related code and tests together

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore new ideas for an existing design
• Compare four possible appearances
• Review design options as separate images

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing past decisions before changing a design
• Learning the background of an unfamiliar project
• Loading all ADRs before starting implementation

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn a new topic across multiple sessions
• Practice with quizzes and immediate feedback
• Build printable reference sheets for review

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving video and article ideas
• Recording observations and hypotheses
• Collecting startup and small project ideas

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deciding whether to proceed after prolonged deliberation
• Checking for serious issues before moving forward
• Reducing a discussion to practical next steps

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Rename a thread to reflect its main activity
• Give a session a short, descriptive title
• Update the current conversation title on request

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing personal notes with an expert's ideas
• Finding overlooked questions in a proposal
• Collecting relevant quotes with source locations

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review the context of a long conversation
• Simplify a difficult previous response
• Revisit the original request and current progress

Handle Git and GitHub CLI commands blocked by a sandbox, an environment that restricts access. Retry only authorized commands on the host, then check authentication, repository status, or pull request details there.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking authentication after a sandbox failure
• Handling blocked GitHub repository and pull request commands
• Retrying Git writes blocked by permission errors

Request an independent code review using GPT-6.1-Sol at Max reasoning through Codex and Cloudroom. Review the current environment, including uncommitted changes, and return the completed reviewer’s full response covering serious issues and readiness to merge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Get an independent review before merging
• Review changes that are still uncommitted
• Check serious issues across related code and tests

Guide a setup process one step at a time in plain English. Each response provides the current actions and required values, followed by a short list of remaining stages that updates as the user progresses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Follow a setup process one step at a time
• See required values for the current form
• Keep track of remaining setup stages

Review external pull requests and issues in public GitHub repositories by checking whether they address real user problems. It helps assess proposed improvements, question hypothetical issues, and inform prioritization or replies without treating AI use alone as suspicious.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review an external pull request for a real user need
• Assess whether a reported issue fits actual usage
• Prioritize contributions by their practical value

Draft clear instructions for an agent to keep working toward a measurable goal. It defines the objective, constraints, validation commands, and stopping conditions, and guides setup, monitoring, and troubleshooting for the agent's supported runtime.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a goal prompt with a measurable stopping condition
• Planning repeated test and fix cycles
• Setting up and monitoring an autonomous run

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a cloud workspace for a coding agent
• Configure repositories and secrets
• Reuse prepared environments through templates

Turn a research question into a focused DeepAPI request and save the findings as a Markdown report with source links. For longer reports, research subquestions separately and combine their answers and sources into one file.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Research a question that informs a decision
• Save findings with citation URLs
• Combine separate subquestions into a longer report

Show the file and folder structure of the subject being discussed as a simple tree in a code block. When the structure is large, include only the main entries so the overview stays easy to read.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check the overall file structure being discussed
• Focus on the main folders in a large structure
• Share a file tree in a code block

Distribute shared skills across Codex, Claude Code, Pi, Hermes, and Cursor on a Mac. Use copies and symbolic links, which reference the original folder, to manage placement and updates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Distribute a new shared skill to five agents
• Propagate updates to an existing shared skill
• Check skill locations and symbolic links

Launch a new bb agent thread with the intended project, model, permissions, and task brief. It sets up a separate working copy when needed, checks the assigned permissions, and reports the resulting thread configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launching a standalone bb agent
• Assigning a subtask in a separate working copy
• Starting a read-only investigation worker

Inspect and manage BB threads, environments, projects, and plugins through its command line interface. The skill guides agents to identify the correct targets, apply changes, and verify the resulting state.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check BB projects and environment status
• Manage skills and plugins
• Create or operate threads

Configure a shared guard that blocks destructive shell commands before local AI agents execute them. Adjust blocking rules, connect agent integrations, and test why commands are blocked or allowed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adjust rules for blocking destructive commands
• Connect the guard to another agent or machine
• Investigate blocked or unexpectedly allowed commands