53 markdown skill files, explained as one story: what happens to a message from the moment it arrives to the moment the brain dreams about it at 3 AM.
A skill is just a markdown file with instructions. The agent reads the file, then does what it says. No code to run — the file is the program. Ten steps below, one diagram each. Every skill name below links to its file on GitHub, so you can read the real thing in place.
Every message first hits RESOLVER.md — a phone book of trigger phrases. Match a phrase, read that skill file, follow it. If two match, read both: skills are built to chain.
Two skills run on every message, no trigger phrase needed. Together they make the core loop: notice → look up → answer → save → link → sync.
One front door (ingest) that looks at what you shared and hands it to the right specialist. Everything lands as a markdown page.
gbrain capture "…".A brain where everything lands in inbox/ forever is just a pile. Three gate skills keep the shape; one sweeps up after big work sessions.
lab-result) when your data outgrows the defaults.Asking is three searches at once, fused, then written up — with citations and an honest "here's what I don't know."
gbrain search stops at "fuse"; gbrain think goes all the way). The gap note in green is the differentiator.A person page with one line is a stub. Enrichment asks the web only for what the brain doesn't already know, writes it back with citations, then audits the citations.
[Source: …], fixes formats.While you sleep, gbrain dream runs eight phases. The two in the middle are the memory-consolidation part: yesterday's conversations become permanent, linked pages.
cron-scheduler places all of these; quiet hours keep the agent from pinging you at 3 AM.The meta layer. A trick you did once becomes a file; the file gets tested, optimized against a benchmark, and shipped upstream so every gbrain user's agent learns it.
That's all 53. The README says "43 curated skills" — the pack has grown since that sentence was written.
| Skill | In one sentence | |
|---|---|---|
| Always on | ||
| signal-detector | Catches names, ideas, todos in every message, silently. | writes |
| brain-ops | House rules for every brain read/write: brain first, cite, back-link. | writes |
| Intake | ||
| capture | Save any thought with one command. | writes |
| ingest | Front door; routes to the right specialist. | writes |
| idea-ingest | Links, tweets, articles, ideas. | writes |
| media-ingest | Video, audio, PDF, books, screenshots, repos. | writes |
| meeting-ingestion | Transcripts → pages + attendee enrichment. | writes |
| voice-note-ingest | Voice notes, exact words kept. | writes |
| webhook-transforms | Outside events (SMS, Zapier) → brain signals. | writes |
| archive-crawler | Mines old archives for your own high-value writing. | writes |
| data-research | Extracts structured data (tables of facts) from sources. | writes |
| Filing & shape | ||
| repo-architecture | The rulebook for where files go. | reads |
| brain-taxonomist | The gate that applies the rulebook before every write. | reads |
| frontmatter-guard | Fixes broken YAML headers. | writes |
| eiirp | Post-work sweep: everything in its right place. | writes |
| schema-author | Adds new page types when your data needs them. | writes |
| schema-unify | Collapses type sprawl to the 15 canonical types. | writes |
| Answers out | ||
| query | 3-layer search + synthesized, cited answer. | reads |
| idea-lineage | Traces one idea's evolution over time. | reads |
| strategic-reading | Reads a source through the lens of your current problem. | writes |
| book-mirror | Book analysis mapped to your actual life. | writes |
| concept-synthesis | Thousands of concept stubs → tiered idea map. | writes |
| publish | Share a page as protected HTML. | reads |
| brain-pdf | Page → clean PDF. | reads |
| Enrichment | ||
| enrich | Fills out person/company pages, tiered. | writes |
| perplexity-research | Web research that only returns what's new vs the brain. | writes |
| academic-verify | Traces claims to paper → data → replication. | writes |
| article-enrichment | Wall-of-text dumps → structured, quotable pages. | writes |
| citation-fixer | Every fact gets a source, formatted right. | writes |
| Health & night shift | ||
| maintain | 13-dimension audit + the dream cycle runbook. | writes |
| smoke-test | Post-restart checks with auto-fix. | writes |
| skillpack-check | Health report for the skills themselves. | reads |
| cron-scheduler | Staggered schedules, quiet hours. | writes |
| minion-orchestrator | Crash-proof background jobs and subagents. | writes |
| cross-modal-review | Second opinion from a different model. | reads |
| gbrain-upgrade | Keeps gbrain itself up to date. | writes |
| Daily ops | ||
| daily-task-prep | Morning calendar lookahead + meeting context. | reads |
| briefing | The daily digest. | reads |
| daily-task-manager | Add, complete, defer, review tasks. | writes |
| reports | Timestamped, findable reports. | writes |
| ask-user | Stop and offer the human clear choices. | reads |
| gbrain-advisor | Weekly "get more out of your brain" coaching. | reads |
| Meta (skills about skills) | ||
| skillify | Raw capability → proper skill. | writes |
| skill-creator | Conformant SKILL.md scaffolds. | writes |
| skill-optimizer | Benchmark-gated skill text optimization. | writes |
| testing | Skill validation + regression watch. | reads |
| skillpack-harvest | Promote a proven skill upstream. | writes |
| functional-area-resolver | Shrinks a bloated routing file. | writes |
| Day zero | ||
| setup | First boot: DB, agent wiring, first import. | writes |
| install | The agent-driven install protocol. | writes |
| cold-start | What to import first into an empty brain. | writes |
| migrate | In from Obsidian / Notion / Logseq / Roam / CSV. | writes |
| soul-audit | Interview that writes the agent's SOUL.md identity. | writes |
Source: skills/ in garrytan/gbrain, read 2026-08-07. Write/read flags from each skill's mutating: frontmatter (judgment call where unmarked).