Garry Tan

Turn voice calls into GBrain records containing transcripts, summaries, audio links, and references to people or companies. The workflow also sends summaries to a configured messaging service; automatic processing when calls end requires additional implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keep a transcript and summary of a voice call
• Review call decisions alongside the original audio
• Link call records to people and company pages

Check a gbrain installation after a restart or when services seem broken. It tests key components, repairs some local problems, checks OpenClaw when installed, and records results, with support for custom test scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check services after a machine or container restart
• Investigate problems with a gbrain installation
• Check OpenClaw services when installed

Turn incoming SMS, meeting events, and social mentions into cited pages in GBrain, a knowledge store. The workflow extracts people and other entities, updates timelines, sanitizes content, and preserves failed payloads for retry.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save SMS events to a sender’s timeline
• Route completed meetings to meeting ingestion
• Record social mentions with source links

After explicit opt-in, captures original ideas in the user's exact words and identifies people and companies mentioned in conversations. Stores them in linked knowledge pages with sources, dated facts, and a brief capture log.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving ideas expressed during conversations
• Adding context to people and company pages
• Connecting ideas with related people and concepts

Validates skill files and registration consistency, then checks project tests and system health. Compares failures with recent changes to distinguish regressions, outdated tests, intermittent failures, and infrastructure issues, producing a report that tracks results over time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validating definitions and registration for new skills
• Running daily tests and system health checks
• Classifying failures after code changes

Improve an existing skill’s instructions using benchmark tasks that measure its output. Generate starter tasks, preview costs, and keep version history, with validation checks deciding whether proposed edits can replace the current instructions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improve a skill against benchmark tasks
• Create starter evaluation tasks for a new skill
• Retune a skill after changing models

Save voice notes as organized knowledge pages while preserving the speaker's exact wording, including hesitations. Store the original audio, file the note by subject, add separate analysis, and link mentions to relevant person and company pages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capturing ideas in their original spoken wording
• Filing voice notes by subject
• Recording spoken observations about people or companies

Learn how to author a third-party gbrain skillpack through a reference example. It explains required files, ten validation criteria, tests, and evaluation coverage, helping authors understand what to check before packaging and publishing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning the structure of a gbrain skillpack
• Checking requirements before publication
• Understanding test and evaluation files

Make your local gbrain accessible to other devices and cloud agents through MCP, a connection interface for AI tools. Set up Tailscale access, assign limited permissions to each client, configure authentication, and verify connections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Accessing gbrain from another laptop or phone
• Connecting cloud agents to your local gbrain
• Giving each client limited access permissions

Check stored knowledge before answering substantive questions about a person, company, project, or other named subject. The skill retrieves the relevant page when needed and follows related links only when relationship details matter to the response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking saved notes before discussing a person
• Verifying company or project details before a decision
• Resolving an unfamiliar name in a conversation

Create evaluation drafts for existing skills using actual conversations and user corrections. Produce criteria and repeatable test cases, distinguish evidence from specification assumptions, and prepare an anonymized draft for human review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn user corrections into repeatable test cases
• Compare promised behavior with actual usage
• Draft an evaluation from conversation history

Check whether gbrain uses PGLite or Postgres, set up a Postgres-backed installation, or migrate existing PGLite data with its history. The workflow presents a migration plan for approval, verifies transferred tables, and supports interrupted migration recovery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking which database engine gbrain uses
• Setting up Postgres for a new gbrain installation
• Moving PGLite data and history to Postgres

Read a book, article, transcript, or case study against a specific strategic problem. The skill turns relevant passages into practical actions, countermeasures, and warning signs, with source evidence and recommendations for the short, medium, and long term.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Applying lessons from a book to a current business problem
• Learning tactics and countermeasures from historical cases
• Turning an article or transcript into an action plan

Create skills that follow GBrain’s required structure, including workflow steps, expected output, and failure handling. Check for overlapping triggers, update the skill registry and routing guide, and verify the result with conformance tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a skill for an uncovered user request
• Check for overlap with existing skill triggers
• Update skill registration and routing

Looks up a person's identity, role, and relationship before asking the user for clarification. Searches stored knowledge and connected records, then the web, updates incomplete pages, and asks a specific question with a hypothesis when evidence remains inconclusive.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identifying contacts from existing records
• Filling role and relationship fields after imports
• Adding context to names in meeting preparation

Use Mars as a voice partner for reflecting on meaning, identity, and recurring patterns, or demonstrating a personal AI to others. It adapts between reflective conversation and demonstrations that search stored knowledge and summarize shared links.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reflecting on thoughts and recurring patterns
• Demonstrating a personal AI to others
• Starting a voice conversation with recent topic context

Choose where new GBrain pages belong by their main subject rather than file format or source. Follow a filing decision tree, check existing pages, and receive a suggested path with a clear reason for the placement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a directory for a new knowledge page
• Checking subject-based placement for PDFs or email content
• Finding existing coverage before adding a page

Review an agent’s role, communication style, user profile, and boundaries through an interview. It records the user’s exact answers in a shared store, then regenerates the relevant identity files after the user reviews and confirms those answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revisiting the agent’s role and purpose
• Adjusting tone and communication style
• Updating user details and access boundaries

Save reports with timestamps and categories, then retrieve the latest version using familiar keywords. Before delivery, check that links point directly to the relevant content and flag actionable items that lack a link.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving and retrieving the latest morning briefing
• Finding meeting digests by keyword
• Checking research report links before delivery

Connect to an English-speaking voice assistant for quick checks of calendars, tasks, recent conversations, and stored knowledge. Venus gives short, answer-first spoken responses and can start calls with context from a selected topic.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking today's calendar by voice
• Reviewing tasks in a short call
• Looking up stored knowledge aloud

Answer questions from saved gbrain knowledge using keyword, meaning-based, and relationship searches. The skill combines relevant evidence with page citations and highlights missing information, conflicting sources, or potentially outdated results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find saved notes on a topic
• Look up connections between people and companies
• Trace events and changes through timelines

Research a topic from multiple angles, preserve sources according to your privacy preferences, and summarize each one. Combine the evidence into a self-contained reference page, including limitations and counterarguments, with options to deepen the research later.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a reference guide on a new topic
• Keeping sources alongside individual summaries
• Comparing evidence, counterarguments, and limitations

Prepare a personal knowledge base for team sharing by removing compensation, performance assessments, personal details, and other sensitive content. The skill checks pages and searchable records, verifies the cleaned material, and addresses sensitive Git history with explicit confirmation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a shared team knowledge base from personal notes
• Auditing an existing shared knowledge base
• Checking sensitive content before onboarding team members

Reduce the size of AGENTS.md or RESOLVER.md by grouping skills into functional areas. Each area keeps a list of its sub-skills, helping the agent find the appropriate skill through a two-level routing structure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shortening a large AGENTS.md
• Grouping skill routes by functional area
• Checking routing accuracy after compression