Skill collection
garrytan/gbrain agent skills
- skills
- 47
- GitHub stars
- 31k
GitHub description: “Garry's Opinionated OpenClaw/Hermes Agent Brain”
- Stars
- 30,666 (4,597 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Apr 2026
Install all skills
npx skills add garrytan/gbrainAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in garrytan/gbrain, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Traces a factual error the user points out back to its source (a brain page, a memory file, SOUL.md or USER.md, or a hallucination) and fixes that source instead of just noting the correction. | garrytan/ | 31k | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 2 | Searches and writes a company-wide knowledge brain through the gbrain CLI, so durable decisions and facts about people, projects and history stay findable beyond one session. | garrytan/ | 31k | — | ~875 | Automated safety check: Pass | MIT | today |
| 3 | Ingest links, articles, tweets, and ideas into the brain. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 4 | Sends what your notes already know about a topic to Perplexity, so the cited web search reports only what is new, such as entity updates or deal changes. | garrytan/ | 31k | — | ~2k | Automated safety check: Notes | MIT | today |
| 5 | Migrate a brain from gbrain-base (or any pack) to gbrain-base-v2's 14-canonical-type taxonomy via gbrain onboard --check + the unify-types Minion handler. | garrytan/ | 31k | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 6 | Run gbrain skillpack-check to produce an agent-readable JSON health report for the gbrain install. | garrytan/ | 31k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 7 | Lift a proven skill from a host repo (e.g. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~2.8k | Automated safety check: Pass | MIT | today |
| 8 | Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. | garrytan/ | 31k | — | ~6.3k | Automated safety check: Notes | MIT | today |
| 9 | Pre-write quality gate for content entering the brain. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~3.9k | Automated safety check: Pass | MIT | today |
| 10 | When you report a brain page to the user — created, edited, committed, or relayed from a subagent — a working link is part of the deliverable, in the SAME message. | garrytan/ | 31k | — | ~3.1k | Automated safety check: Pass | MIT | today |
| 11 | Filing gate for ALL brain writes. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 12 | 12.Blog Ingest Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. | garrytan/ | 31k | — | ~3.8k | Automated safety check: Warn | MIT | today |
| 13 | End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. | garrytan/ | 31k | — | ~4.7k | Automated safety check: Pass | MIT | today |
| 14 | Connect a ChatGPT or Claude account and sync its conversation history into the brain automatically. | garrytan/ | 31k | — | ~2.8k | Automated safety check: Pass | MIT | today |
| 15 | Build a TYPED citation/reference graph over an ingested corpus — not just embeddings. | garrytan/ | 31k | — | ~3k | Automated safety check: Pass | MIT | today |
| 16 | Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESSPOLICY.md, HEARTBEAT.md) or… | garrytan/ | 31k | — | ~3.2k | Automated safety check: Pass | MIT | today |
| 17 | Confirmation gate before any bulk delete, cleanup, or destructive operation that could result in data loss — shell-level (rm -rf, git rm, bulk sed) or brain-level (bulk forget, delete sweeps… | garrytan/ | 31k | — | ~2.8k | Automated safety check: Pass | MIT | today |
| 18 | 18.DB Repair Auto-fix gbrain's Postgres access so the brain stays available. | garrytan/ | 31k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 19 | Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails. | garrytan/ | 31k | — | ~3.7k | Automated safety check: Pass | MIT | today |
| 20 | 20.Eiirp Everything In Its Right Place. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~5.6k | Automated safety check: Pass | MIT | today |
| 21 | 21.Fact Check Systematic claim-by-claim verification for any content before it ships. | garrytan/ | 31k | — | ~5.2k | Automated safety check: Pass | MIT | today |
| 22 | Validate and auto-repair YAML frontmatter on brain pages. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~3.8k | Automated safety check: Pass | MIT | today |
| 23 | Proactive "make the most of gbrain" coaching. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 24 | Keep gbrain current. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 25 | 25.Google Loops Set up and operate the Gmail/Calendar/Contacts connector and the open-loop engine: who is waiting on the user, what they promised, and the context needed to respond. | garrytan/ | 31k | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 26 | Before fixing a slow/stale/timeout alert, measure the step yourself. | garrytan/ | 31k | — | ~2.5k | Automated safety check: Pass | MIT | today |
| 27 | Detect which gbrain engine is in use (PGLite vs Postgres), prefer Postgres for agent-harness installs, install/provision Postgres (Supabase discovery via SUPABASEACCESSTOKEN, local Postgres, opt-in… | garrytan/ | 31k | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 28 | 28.Reports Save and load timestamped reports. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 29 | Gate on identity questions to the user. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 30 | 30.Setup Add keyless GBrain memory to an existing agent, or connect a hosted brain while preserving identity and configuration | garrytan/ | 31k | — | ~3.6k | Automated safety check: Pass | MIT | today |
| 31 | Author an eval for an existing skill from its REAL usage history, not its spec. | garrytan/ | 31k | — | ~3.2k | Automated safety check: Pass | MIT | today |
| 32 | 32.Smoke Test Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). | garrytan/ | 31k | — | ~1.8k | Automated safety check: Notes | MIT | today |
| 33 | 33.Soul Audit Re-run or deepen the agent's identity interview. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 34 | Tiered LLM extraction pattern for large corpus processing (email archives, document dumps, transcript libraries). | garrytan/ | 31k | — | ~4.4k | Automated safety check: Pass | MIT | today |
| 35 | Post-call handling for a voice session — turn the transcript into a brain page, post the summary to the operator's messaging surface, archive the audio. | garrytan/ | 31k | — | ~1.7k | Automated safety check: Notes | MIT | today |
| 36 | 36.Book Mirror Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. | garrytan/ | 31k | — | ~6.6k | Automated safety check: Pass | MIT | today |
| 37 | Extract a sanitized shared team/company brain from a personal brain. | garrytan/ | 31k | — | ~9k | Automated safety check: Pass | MIT | today |
| 38 | Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. | garrytan/ | 31k | — | ~5.5k | Automated safety check: Pass | MIT | today |
| 39 | Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the… | garrytan/ | 31k | — | ~5.6k | Automated safety check: Pass | MIT | today |
| 40 | Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. | garrytan/ | 31k | — | ~7.7k | Automated safety check: Pass | MIT | today |
| 41 | 41.Remote MCP Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. | garrytan/ | 31k | — | ~7.4k | Automated safety check: Notes | MIT | today |
| 42 | 42.Skillify The meta skill. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~7.5k | Automated safety check: Pass | MIT | today |
| 43 | 43.MCP Access Open the GBrain owner dashboard, manage MCP clients and permissions, or connect a native OAuth harness. | garrytan/ | 31k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 44 | When/what to retrieve — open the brain page for a salient entity before answering from memory. | garrytan/ | 31k | — | ~735 | Automated safety check: Pass | MIT | today |
| 45 | Opt-in ambient signal capture. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~2k | Automated safety check: Pass | MIT | today |
| 46 | Task lifecycle management with stable task IDs. An agent skill from garrytan/gbrain. | garrytan/ | 31k | — | ~2.2k | Automated safety check: Warn | MIT | today |
| 47 | Deep-research a topic end to end and produce a permanent, reusable knowledge asset: archive every primary source verbatim (gated by the user's privacy/retention posture), write one 1:1 summary per… | garrytan/ | 31k | — | ~5.9k | Automated safety check: Warn | MIT | today |
Questions, answered from the data.
What is the best skill in garrytan/gbrain?
Correction Root-Cause Pipeline from garrytan/gbrain ranks first of the 47 skills in garrytan/gbrain listed here, with the highest score: its repository has 31k GitHub stars, its SKILL.md loads about 3.4k tokens and it passes the automated safety check with no findings. Next come Company Knowledge Brain and Idea Ingest.
Are the skills in garrytan/gbrain official?
None yet. All 47 skills in garrytan/gbrain listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from garrytan/gbrain?
Run npx skills add garrytan/gbrain in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.