@garrytan
Writes software, dreams.
148 skills3 repositories 168.8K
When a user corrects a factual error, trace it through stored knowledge, memory, identity settings, and fact records. Fix the underlying source, check related records where needed, and report the cause, changes, and safeguards against recurrence.
Investigate slow jobs, stale data, and timeout alerts by timing the specific operation and comparing monitoring thresholds. Produce an evidence-based verdict that distinguishes insufficient time, stalled work, and false alerts before proposing changes.
Prepare for the day with meeting context, unresolved conversations from yesterday, and prioritized tasks. The skill combines calendar entries with GBrain records about attendees to produce a briefing that explains what to know before each meeting.
Collect public posts across a blog, newsletter, or feed archive and save clean Markdown pages for each article. The workflow avoids duplicates, supports resumed runs, repairs empty results, and hands articles to a separate enrichment skill.
Compare saved knowledge with current web sources using Perplexity. This skill produces a cited research page that separates new developments, supporting evidence, and contradictions, with suggested updates to stored information about people, companies, or deals.
Trace how one idea developed across stored notes and records. Identify its earliest documented mention, clearest expression, changes of stance, contradictions, abandoned branches, and current form, with dated evidence and explicit gaps where sources are missing.
Turn videos, audio, PDFs, books, screenshots, and GitHub repositories into knowledge pages with summaries and highlights. Preserve original files, extract people and companies, and connect the material to their pages and timelines for later reference.
Connect a ChatGPT or Claude account to import conversation history into knowledge pages. Sync new and changed conversations incrementally, revisit recent history to catch updates, and optionally enable scheduled syncing.
Connect Gmail, Calendar, and Contacts to track people awaiting replies and promises still outstanding. Get a prioritized digest with supporting quotes, email links, deadlines when available, and background context to help prepare a response.
Turn exported AI chats and agent session logs into dated, searchable pages in gbrain. Check for missing conversations, extract facts, and trace when a topic first appeared or how an idea developed, with quotes and dated references.
Check names, aliases, and existing pages before saving content to a gbrain knowledge store. The skill reads likely matches to identify duplicates, links to existing information, and routes new material to the appropriate ingestion skills.
Create and update person or company pages in gbrain using existing knowledge and external sources. Organize cited facts, dated events, and relationships, while adjusting research depth to importance and flagging contradictions without overwriting user assessments.
Build a workflow for importing large collections of audio, email, documents, or chats into knowledge pages. Test varied samples first, track progress in a persistent JSON file, and verify outputs before marking work complete.
Restructure raw article text stored in gbrain into summaries, exact quotes, key insights, and links to related pages. Preserve the original text and connect the article's significance to projects and interests already recorded in gbrain.
Audit citations across stored knowledge pages, fix formatting problems, and flag claims without sources. For X posts missing links, use the host's API integration to find matching posts and add verified URLs, with counts of fixes and unresolved gaps.
Check YAML frontmatter, the metadata at the top of knowledge pages, for formatting and identity errors. Explain why gbrain holds files during sync, preview proposed changes, and repair supported problems after approval.
Draft posts, replies, launch copy, or emails in a specific person's writing style using a validated profile and stored source material. Produce two or three checked options, or build and validate the profile first when needed.
Create a detailed chapter-by-chapter reading companion from an EPUB or PDF, connecting the book’s ideas to experiences and words saved in your personal knowledge store. The result highlights parallels without prescribing actions.
Have a different AI model review code, analysis, or documents against the original skill's stated requirements. Receive evidence-based findings and a comparison of agreement and disagreement, then decide which recommendations to accept.
Look up people, companies, and topics in an existing knowledge base before answering. Save authorized information with source references, update related pages and timelines, and maintain links that connect each record to its context.
Check research claims cited in books, articles, or conversations by tracing the original paper, methods, underlying data, and independent replication. Save a sourced assessment explaining whether the claim holds up and what remains uncertain.
Audit a gbrain knowledge base for outdated pages, broken or missing links, inconsistent tags, and missing citations. Get issue counts and specific repair actions, with additional checks for search quality and maintenance status.
Deliver knowledge-page updates with links derived from Git paths and checked after pushing. Use defined alternatives for local repositories, rewrite paths relayed by other agents, and keep links between pages relative to preserve their connections.
Turn a GBrain page into a PDF for sharing or archiving. Remove frontmatter metadata, handle emoji, and add running headers and page numbers, while keeping the original brain page as the authoritative source.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)