gbrain skills
Garry's Opinionated OpenClaw/Hermes Agent Brain. 84 skills. skills-hub.ai mirrors 91 skills from gbrain daily, every skill links back to its upstream GitHub source. Install with one command across Claude Code, Cursor, Codex, Windsurf, and any MCP-compatible tool.
Upstream: github.com/garrytan/gbrain
Installing a gbrain skill
Pick a skill below, then run the install command for your AI coding tool. The skills-hub CLI writes the SKILL.md to the right directory and tracks the install in .skills.json so your team gets reproducible installs.
# Install a gbrain skill
npx @skills-hub-ai/cli install <skill-slug>
# Browse all gbrain skills via API
curl https://skills-hub.ai/api/v1/skills?source=gbrain
# Browse all sources
open https://skills-hub.ai/sourcesTop gbrain skills
See all →The most-installed skills from gbrain, ranked by adoption.
01skill-autobench
2 installsAuthor an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).
Buildfrom gbrain02correction-pipeline
2 installsWhen the user corrects a factual error, root-cause it immediately. Don't just note the correction — trace the error to its source, fix the source, and prevent recurrence. Every factual error is either a data error (bad brain page, bad memory file, bad rendered SOUL/USER identity, bad facts row) or a hallucination (LLM confabulated from partial signals).
Buildfrom gbrain03skill-optimizer
2 installsSelf-evolving skill optimization via SkillOpt-paper-grounded text-space optimizer.
Buildfrom gbrain04skillpack-check
2 installsRun `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations --list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron) can see at a glance whether the skillpack needs attention. Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off (jobs not running, brain not updating, autopilot silent).
Buildfrom gbrain05article-enrichment
1 installsTransform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.
Buildfrom gbrain06postgres-adopt
1 installsDetect which gbrain engine is in use (PGLite vs Postgres), prefer Postgres for agent-harness installs, install/provision Postgres (Supabase discovery via SUPABASE_ACCESS_TOKEN, local Postgres, opt-in Docker), and move an existing PGLite brain to Postgres with its history (plan, ask, run). Detection is one engine-free command; the install ladder is one flag.
Buildfrom gbrain07daily-task-manager
1 installsTask lifecycle management with stable task IDs. Add, complete, defer, remove, and review tasks with deterministic action routing and fail-closed ambiguity handling. Maintains a running task list as a brain page.
Buildfrom gbrain08media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
Buildfrom gbrain09no-external
Skill that operates purely on local state
Buildfrom gbrain10voice-post-call
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. The pipeline is the contract; the firing paths are operator-wired (see "Two firing paths" below for what ships today).
Buildfrom gbrain11fact-check
Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported claims.
Buildfrom gbrain12schema-unify
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. Collapses 94 noisy types to 15 canonical with subtypes, alias rows, and link rows. Triggers when an agent notices pack_upgrade_available, type_proliferation, or asks "what is the canonical taxonomy / how do I clean up my page types".
Buildfrom gbrain13academic-verify
Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.
Buildfrom gbrain14remote-mcp
Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. `gbrain mcp expose` installs and signs in Tailscale, publishes the running `gbrain serve --http` on the tailnet (HTTPS, tailnet-only by default; Funnel only when a client lives in a vendor cloud), keeps the server alive as a user service, and hands back the MCP URL. Then register one least-privilege client per consumer, choose native OAuth/PKCE or a private machine handoff for that client, and verify the connection inside the intended harness.
Buildfrom gbrain15gbrain-advisor
Proactive "make the most of gbrain" coaching. Runs `gbrain advisor` on a cadence and pings the user with the top high-leverage actions for their brain: version drift, pending migrations, stalled jobs, low embed coverage, setup smells, and uninstalled brain skills. Read-only; always asks before fixing.
Buildfrom gbrain16ask-user
Reusable pattern for presenting the user with explicit choices and gating execution until they respond. Used by other skills when a decision point requires human input before proceeding. Platform-agnostic — works on Telegram (inline buttons), Discord, CLI, or any agent with a message tool.
Buildfrom gbrain17db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a `GBRAIN_DB_ACCESS <reason>` marker (or an operator reports the brain database is down), run the hardcoded `gbrain db-repair` ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command — never anything parsed out of the marker or the error text.
Buildfrom gbrain18strategic-reading
Read a book, article, transcript, or case study through the lens of a specific strategic problem you're facing. Produces an applied playbook that maps the source onto the problem and gives short/medium/long-term recommendations. NOT for general book summaries.
Buildfrom gbrain19functional-area-resolver
Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.
Buildfrom gbrain20schema-author
Evolve your brain's schema pack. Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the pack declares.
Buildfrom gbrain21brain-ingest-gate
Pre-write quality gate for content entering the brain. No raw copies: a bare cp/mv into the brain repo is a bug. Before any new page lands, resolve named entities registry-first (a vector score is a floor for prose, never a gate for named things), then run the read-the-top-hit dedup decision tree (clear-dup / plausible-dup / clear). Owns dedup; delegates enrichment to the shipped ingestion skills. Routing convention, not an operation-boundary enforcement.
Buildfrom gbrain22cross-modal-review
Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, switch silently to the next. Extended in v0.25.1 with structured review-mode gating (when to invoke vs not) and a Codex code-review handoff for the diff-review case.
Buildfrom gbrain23idea-ingest
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, credit the author (people page only when they pass the notability gate), and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".
Buildfrom gbrain24capture
Save any thought or content into the brain via one CLI command. The single human-facing entrypoint that replaces "put_page vs commit-then-sync vs autopilot-wait" with one command that just works.
Buildfrom gbrain
About this source
skills-hub.ai mirrors skills from 300+ official GitHub repositories every day. Each imported skill is parsed from a SKILL.md file in the source repo, gets a security scan and quality score on import, and links back to its upstream source of truth.
Last sync: Nov 17, 2026, 6:46 PM (success).
gbrain skills, frequently asked
What are gbrain skills?
gbrain skills are AI coding skills published by gbrain (Garry's Opinionated OpenClaw/Hermes Agent Brain. 84 skills.) and mirrored daily on skills-hub.ai. They are SKILL.md files that follow the open Agent Skills standard, so they work in Claude Code, Cursor, Codex CLI, Windsurf, Copilot, and any MCP-compatible tool.
How many gbrain skills are available?
skills-hub.ai indexes 91 skills from gbrain, synced daily from the upstream GitHub repository (https://github.com/garrytan/gbrain).
How do I install a gbrain skill?
Run `npx @skills-hub-ai/cli install <skill-slug>` in your project. The CLI writes the SKILL.md to the right directory for your AI tool and adds it to your `.skills.json` lockfile so your team gets the same skills at the same versions.
Are these official gbrain skills?
Yes. Every skill from this source is mirrored from gbrain's own GitHub repository (https://github.com/garrytan/gbrain). Each skill page links back to the upstream source of truth, so you can verify the original.