David Ondrej

Document approved decisions as concise ADRs, or architecture decision records. It preserves the user's meaning and conditions, removes conversational filler, follows the project's numbering, and presents the saved record for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Record a decision approved in conversation
• Preserve the conditions and scope of a decision
• Add a numbered ADR to existing records

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

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

Control workspaces, split panes, browser views, and notifications in the cmux macOS terminal app. The skill guides the agent to identify the intended target, read terminal output, send requested input, and check the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a workspace for a project
• Adding a terminal pane beside the current task
• Reading terminal output and sending requested commands

Coordinate AI agents running in Herdr workspaces inside Ghostty. Inspect terminal output and agent status, send instructions, wait for completion, share missing context, and combine results into one summary while avoiding duplicate work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check agent status and output in a Herdr workspace
• Send instructions to a specific agent
• Wait for task completion and read the results

Keep a Mac awake for a chosen duration or while a specified process runs. The skill uses built-in macOS tools to manage one session, verify that sleep prevention is active, and control whether the display stays on.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keep a Mac awake during a lengthy task
• Prevent sleep while a specified process runs
• Allow the display to dim while keeping the Mac awake

Design, debug, and tune OpenRouter API integrations. It checks model capabilities, reasoning settings, output limits, and fallback routes, then validates results against quality, cost, privacy, and performance requirements, including failed attempts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design an OpenRouter API integration
• Investigate empty, truncated, or malformed responses
• Configure fallback models and provider restrictions

Collect public evidence about a person, company, or topic with DeepAPI and save it as a structured JSON dossier. Source links, uncertainty checks, and coverage notes show what was found and what remains missing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching a sales prospect
• Collecting evidence about a software vendor
• Organizing documentation and discussions on a technical topic

Check registration records for several domains using public RDAP APIs, which provide domain registration data. Get distinct statuses for registered names, missing records, restrictions, and uncertain results without API keys, login, or a browser.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking registration records for several domain candidates
• Comparing a name across different domain endings
• Reviewing restrictions and reasons for uncertain results

Research a person's public profiles, posts, and development activity to produce a brief credibility assessment. Highlight up to three meaningful facts, distinguish personal claims from verified evidence, and note missing or private profiles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check someone's public track record
• Compare profile claims with documented achievements
• Review development activity and recent posts

Create, review, and troubleshoot agent skills: reusable instructions stored in SKILL.md and supporting files. This skill guides description writing, file organization, activation testing, execution checks, and diagnosis when a skill fails to load or follow its intended process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new SKILL.md and supporting file structure
• Diagnosing why a skill is not invoked
• Improving instructions when execution fails

Turn a feature or refactoring idea into a concise implementation prompt for another agent. It asks focused questions one at a time, records decisions, and includes development steps, validation, and working rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify requirements for a new feature
• Decide edge cases and failure behavior
• Define the scope of a refactor

Identify one to three important decisions before starting a build. Based on the user's idea, this skill presents concise options and an initial recommendation for each, then waits for answers before work proceeds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying important decisions before implementation
• Deciding whether a solution needs to be reusable
• Choosing between a short script and a separate module

Write four distinct prompts for images, thumbnails, banners, logos, or illustrations. Each describes the subject, setting, colors, mood, and visual style, giving users copyable text to try different creative directions in an image model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing different visual directions for a thumbnail
• Preparing image prompts for a banner
• Exploring four logo concepts

Isolate parallel coding tasks with Git worktrees, separate working folders with their own branches. The skill guides environment setup, dependency installation, change review, merging, and cleanup so each task has a dedicated workspace.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare separate working folders for parallel coding tasks
• Set up dependencies and environment files in a new worktree
• Review and merge completed changes

Archive the current Cloudroom thread and its child threads, then stop its runtime, the environment running the agent. It acts only on an explicit request and provides a short closing summary before archiving.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Archiving a finished Cloudroom conversation
• Stopping the runtime for the current thread
• Closing a thread together with its child threads

Retrieve meeting transcripts from Fireflies.ai and save the original text to a file, with or without speaker names. Find meetings by recent listings and dates, then check that the transcript matches the requested conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save a meeting transcript with speaker names
• Export transcript text without speaker labels
• Find an untitled meeting by date and participants

Reset a stuck Cursor ACP thread in a chat app while preserving its history. Clean up orphaned processes, check CLI health, and reload configuration when the next message starts a fresh agent.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recover a Cursor thread that has stopped responding
• Reload rules, skills, and MCP configuration
• Clean up orphaned processes and check CLI health

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

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

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

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

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

Research a topic through five web searches, five GitHub data collections, and five X/Twitter data collections using DeepAPI. Bring coverage, relevant repositories, and social discussion together in a concise, readable Markdown report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Research a topic across web pages, GitHub, and X/Twitter
• Compare web coverage with relevant repositories
• Include social discussion in topic research