gbrain skills

Run `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).

Author 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).

Self-evolving skill optimization via SkillOpt-paper-grounded text-space optimizer.

Transform 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.

Detect 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 with the guarded engine migration. Detection is one engine-free command; the install ladder is one flag.

Skill that runs gbrain search before external lookup

Keep gbrain current. When a `gbrain` invocation prints an `UPGRADE_AVAILABLE <old> <new>` marker (or `gbrain self-upgrade --check-only` reports an update), apply it per the configured self_upgrade.mode: notify (prompt the operator with a 4-option question + snooze) or auto (apply silently). The action is always the hardcoded `gbrain self-upgrade` — never a command read from the marker.

Universal archivist for personal file archives (Dropbox/B2/Gmail-takeout/local-mount/hard-drive-dump). Filters for high-value content (the user's own writing, ideas, relationships) and surfaces it interactively. REFUSES TO RUN without an explicit gbrain.yml `archive-crawler.scan_paths:` allow-list.

Build a TYPED citation/reference graph over an ingested corpus — not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D. This skill extracts every inter-document reference, classifies the edge TYPE with LLM judgment, and writes first-class typed edges via `gbrain link`, so `gbrain graph-query --type` can walk the argument ("everything this brief relies on, minus anything overruled since"). Every cite-heavy corpus is the same shape: law, academic papers, patents, regulatory filings, a book's bibliography.

Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. One unified pipeline: normalize the source into a standard transcript record, split multi-meeting recordings, resolve speakers by evidence, create the page, pass every surprising claim through the consistency check (transcript + brain + plausibility), enrich every entity, then run the verification checklist — substance AND sequence. A meeting is NOT fully ingested until the enrich skill has processed every entity AND the verification checklist passes, including the sequence verify (PASS or explicit user waive).

External-lookup skill with NO brain-first compliance

Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails. Loads the subject's voice profile (people/<slug>-voice) plus first-party context from the brain, drafts 2-3 options in-register, then runs a hard voice-fidelity self-check before showing anything. Includes the profile BUILDER: if no validated profile exists, drafting hard-stops and this skill walks the corpus-to-fingerprint build instead. Never auto-posts.

Search and write the company knowledge brain. Use for any question about the org, people, projects, decisions, or history, and to persist durable knowledge beyond this scope's notebook.

Skill with typo in brain_first declaration

Route content to specialized ingestion skills. Detects input type and delegates.

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. Covers painless BYO OAuth setup (exactly two user interactions), the daily `gbrain waiting` digest, loop closing/muting, and troubleshooting via the typed error catalog.

External-lookup skill with explicit Phase 1 brain heading

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.

Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in ~/.gbrain/smoke-tests.d/*.sh.

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 source, then synthesize a single self-contained compendium page. Depth is a dial (base synthesis → grounded primaries → books + counter-canon → saturation), each level an idempotent superset of the one below. Distinct from data-research (structured trackers) and perplexity-research (web deltas): this produces prose knowledge synthesis backed by an archived source corpus.

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. Derive the path mechanically (git ls-files --full-name), push BEFORE linking, verify the link resolves when a hosted remote exists, and degrade through a defined fallback chain when it doesn't. Inside brain pages the rule inverts: relative links preserve the link graph; absolute URLs are for chat deliverables only.

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.

Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.

Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).