1fc8b6c2d8
* test: isolate embedding configuration between unit fixtures Reset model-probe gateway state and pin chunk-sanitization fixtures to the shared legacy embedding dimensions. Preserve the original persistence and hash assertions. * feat: add existing-agent memory and unified hosted access (v0.49.0.0) Add isolated in-agent setup and repair, private PGLite backup and relocated restore, shared hosted grants and live delegation enforcement, secure credential handoff and recovery, and capability discovery and verification. Make local and hosted onboarding prominent in dedicated Grok Bot and Muse guides. Preserve explicit native-harness acceptance gates, update generated references and release metadata, and keep withdrawn facts out of active memory after synchronization. Co-Authored-By: OpenAI Codex <noreply@openai.com> * docs: sync harness documentation for v0.49.0.0 * fix: update security dependencies and confine restored configuration Refresh patched dependency versions, traverse only owned configuration properties during restore, and trust the CI checkout before calculating the Semgrep baseline. Add a regression that preserves inherited path objects. --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
386 lines
19 KiB
JSON
386 lines
19 KiB
JSON
{
|
|
"name": "gbrain",
|
|
"version": "0.32.3.0",
|
|
"conformance_version": "1.0.0",
|
|
"description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
|
|
"skills": [
|
|
{
|
|
"name": "ingest",
|
|
"path": "ingest/SKILL.md",
|
|
"description": "Route content to specialized ingestion skills. Detects input type and delegates."
|
|
},
|
|
{
|
|
"name": "chat-connectors",
|
|
"path": "chat-connectors/SKILL.md",
|
|
"description": "Connect a ChatGPT or Claude account and sync its conversation history into the brain incrementally, on a schedule. Live account lane (export files + retrieval live in conversation-archive)."
|
|
},
|
|
{
|
|
"name": "query",
|
|
"path": "query/SKILL.md",
|
|
"description": "Answer questions using 3-layer search, synthesis, and citation propagation"
|
|
},
|
|
{
|
|
"name": "maintain",
|
|
"path": "maintain/SKILL.md",
|
|
"description": "Brain health checks: back-link enforcement, citation audit, filing validation, stale info, orphans, benchmarks"
|
|
},
|
|
{
|
|
"name": "enrich",
|
|
"path": "enrich/SKILL.md",
|
|
"description": "Enrich pages with tiered enrichment protocol, person/company page templates, and validation rules"
|
|
},
|
|
{
|
|
"name": "briefing",
|
|
"path": "briefing/SKILL.md",
|
|
"description": "Compile daily briefing with meeting context, active deals, and citation tracking"
|
|
},
|
|
{
|
|
"name": "migrate",
|
|
"path": "migrate/SKILL.md",
|
|
"description": "Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam"
|
|
},
|
|
{
|
|
"name": "setup",
|
|
"path": "setup/SKILL.md",
|
|
"description": "Add keyless GBrain memory to an existing agent, or connect a hosted brain while preserving identity and configuration"
|
|
},
|
|
{
|
|
"name": "publish",
|
|
"path": "publish/SKILL.md",
|
|
"description": "Share brain pages as beautiful password-protected HTML (code + skill pair, zero LLM calls)"
|
|
},
|
|
{
|
|
"name": "frontmatter-guard",
|
|
"path": "frontmatter-guard/SKILL.md",
|
|
"description": "Validate and auto-repair YAML frontmatter on brain pages; gates against malformed YAML, missing closing ---, nested quotes, slug mismatches, null bytes"
|
|
},
|
|
{
|
|
"name": "signal-detector",
|
|
"path": "signal-detector/SKILL.md",
|
|
"description": "Opt-in ambient signal capture. After explicit enablement, detects original thinking and entity mentions in substantive messages."
|
|
},
|
|
{
|
|
"name": "google-loops",
|
|
"path": "google-loops/SKILL.md",
|
|
"description": "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 to respond."
|
|
},
|
|
{
|
|
"name": "brain-ops",
|
|
"path": "brain-ops/SKILL.md",
|
|
"description": "Brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment. The core read/write cycle."
|
|
},
|
|
{
|
|
"name": "capture",
|
|
"path": "capture/SKILL.md",
|
|
"description": "Single human-facing entrypoint for ingestion. Routes through put_page (local) or MCP (thin-client); replaces put-page-vs-commit-vs-autopilot confusion with one verb."
|
|
},
|
|
{
|
|
"name": "idea-ingest",
|
|
"path": "idea-ingest/SKILL.md",
|
|
"description": "Ingest links, articles, tweets, and ideas into the brain with analysis and entity cross-linking."
|
|
},
|
|
{
|
|
"name": "media-ingest",
|
|
"path": "media-ingest/SKILL.md",
|
|
"description": "Ingest video, audio, PDF, book, screenshot, and repo content with entity extraction."
|
|
},
|
|
{
|
|
"name": "meeting-ingestion",
|
|
"path": "meeting-ingestion/SKILL.md",
|
|
"description": "Ingest meeting transcripts with attendee enrichment, entity propagation, and timeline merge."
|
|
},
|
|
{
|
|
"name": "citation-fixer",
|
|
"path": "citation-fixer/SKILL.md",
|
|
"description": "Audit and fix citation formatting across brain pages."
|
|
},
|
|
{
|
|
"name": "repo-architecture",
|
|
"path": "repo-architecture/SKILL.md",
|
|
"description": "Where new brain files go. Filing rules and directory conventions."
|
|
},
|
|
{
|
|
"name": "skill-creator",
|
|
"path": "skill-creator/SKILL.md",
|
|
"description": "Create new skills following the conformance standard with MECE validation."
|
|
},
|
|
{
|
|
"name": "daily-task-manager",
|
|
"path": "daily-task-manager/SKILL.md",
|
|
"description": "Task lifecycle: add, complete, defer, remove, review with priority levels."
|
|
},
|
|
{
|
|
"name": "daily-task-prep",
|
|
"path": "daily-task-prep/SKILL.md",
|
|
"description": "Morning preparation with calendar context, open threads, and task review."
|
|
},
|
|
{
|
|
"name": "cross-modal-review",
|
|
"path": "cross-modal-review/SKILL.md",
|
|
"description": "Quality gate via second model with refusal routing chain."
|
|
},
|
|
{
|
|
"name": "cron-scheduler",
|
|
"path": "cron-scheduler/SKILL.md",
|
|
"description": "Schedule management with staggering, quiet hours, and wake-up override."
|
|
},
|
|
{
|
|
"name": "reports",
|
|
"path": "reports/SKILL.md",
|
|
"description": "Save and load timestamped reports with keyword routing for fast lookup."
|
|
},
|
|
{
|
|
"name": "testing",
|
|
"path": "testing/SKILL.md",
|
|
"description": "Skill validation framework: frontmatter, sections, manifest coverage, MECE checks."
|
|
},
|
|
{
|
|
"name": "soul-audit",
|
|
"path": "soul-audit/SKILL.md",
|
|
"description": "Re-run/deepen the identity interview via the shared bootstrap answer bank (interview --set/--show/--confirm), then re-render SOUL.md/USER.md/ACCESS_POLICY.md/HEARTBEAT.md with render --only."
|
|
},
|
|
{
|
|
"name": "webhook-transforms",
|
|
"path": "webhook-transforms/SKILL.md",
|
|
"description": "Convert external events into brain-ingestible signals with entity extraction."
|
|
},
|
|
{
|
|
"name": "data-research",
|
|
"path": "data-research/SKILL.md",
|
|
"description": "Structured data research: search, extract, archive, deduplicate, track. Parameterized YAML recipes for investor updates, donations, company metrics."
|
|
},
|
|
{
|
|
"name": "minion-orchestrator",
|
|
"path": "minion-orchestrator/SKILL.md",
|
|
"description": "Unified Minions skill for deterministic shell jobs and LLM subagent orchestration. Submit, monitor, steer, pause/resume, replay. Replaces the older gbrain-jobs routing intent and sessions_spawn for durable observable background work."
|
|
},
|
|
{
|
|
"name": "schema-author",
|
|
"path": "schema-author/SKILL.md",
|
|
"description": "Evolve the active schema pack. Add page types, propose new types from a corpus scan, backfill page.type via sync. Wraps the 14 gbrain schema CLI verbs + 9 MCP ops shipped in v0.40.7.0."
|
|
},
|
|
{
|
|
"name": "skillify",
|
|
"path": "skillify/SKILL.md",
|
|
"description": "Meta skill. Turn any raw feature into a properly-skilled, tested, resolvable, evaled unit. Paired with gbrain check-resolvable gives user-controllable auto-skill-creation."
|
|
},
|
|
{
|
|
"name": "skillpack-check",
|
|
"path": "skillpack-check/SKILL.md",
|
|
"description": "Agent-readable gbrain health report. Wraps doctor + apply-migrations --list into one JSON blob with exit codes. Cron-friendly for morning-briefing pipelines."
|
|
},
|
|
{
|
|
"name": "skillpack-harvest",
|
|
"path": "skillpack-harvest/SKILL.md",
|
|
"description": "Editorial workflow for lifting a proven skill from a host repo back into gbrain. Pairs with `gbrain skillpack harvest` CLI. Drives the genericization checklist that scrubs fork-specific names + real entities before files land in gbrain core."
|
|
},
|
|
{
|
|
"name": "smoke-test",
|
|
"path": "smoke-test/SKILL.md",
|
|
"description": "Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments"
|
|
},
|
|
{
|
|
"name": "gbrain-upgrade",
|
|
"path": "gbrain-upgrade/SKILL.md",
|
|
"description": "Keep gbrain current: act on the UPGRADE_AVAILABLE marker per self_upgrade.mode (notify prompt or silent auto)"
|
|
},
|
|
{
|
|
"name": "book-mirror",
|
|
"path": "book-mirror/SKILL.md",
|
|
"description": "Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables: left = chapter summary, right = how it applies to you based on brain context. Output: brain page + PDF."
|
|
},
|
|
{
|
|
"name": "article-enrichment",
|
|
"path": "article-enrichment/SKILL.md",
|
|
"description": "Transform raw article text dumps in the brain into structured pages with executive summaries, verbatim quotes, key insights, why-it-matters, and cross-references."
|
|
},
|
|
{
|
|
"name": "strategic-reading",
|
|
"path": "strategic-reading/SKILL.md",
|
|
"description": "Read a book/article/case study through the lens of a specific strategic problem; produce an applied playbook (do/avoid/watch for) with short/medium/long-term recommendations."
|
|
},
|
|
{
|
|
"name": "concept-synthesis",
|
|
"path": "concept-synthesis/SKILL.md",
|
|
"description": "Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time."
|
|
},
|
|
{
|
|
"name": "idea-lineage",
|
|
"path": "idea-lineage/SKILL.md",
|
|
"description": "Trace one idea's evolution through the brain: first mention, best articulation, reversals, contradictions, abandoned branches, related concepts, and current live version."
|
|
},
|
|
{
|
|
"name": "perplexity-research",
|
|
"path": "perplexity-research/SKILL.md",
|
|
"description": "Brain-augmented web research via Perplexity plus Opus; surfaces what is NEW vs already-known about a topic by cross-referencing against the brain first."
|
|
},
|
|
{
|
|
"name": "archive-crawler",
|
|
"path": "archive-crawler/SKILL.md",
|
|
"description": "Universal archivist for personal file archives (Dropbox/B2/email exports). Filters for high-value content within an explicit gbrain.yml allow-list scan_paths gate."
|
|
},
|
|
{
|
|
"name": "academic-verify",
|
|
"path": "academic-verify/SKILL.md",
|
|
"description": "Verify academic citations and research claims against current literature; routes through perplexity-research for the actual web search and formats results as a citation-checked brain page."
|
|
},
|
|
{
|
|
"name": "brain-pdf",
|
|
"path": "brain-pdf/SKILL.md",
|
|
"description": "Generate a publication-quality PDF from any brain page via the gstack make-pdf binary; strips frontmatter, sanitizes emoji, applies running headers."
|
|
},
|
|
{
|
|
"name": "voice-note-ingest",
|
|
"path": "voice-note-ingest/SKILL.md",
|
|
"description": "Ingest voice notes with exact-phrasing preservation (never paraphrased); routes content based on a decision tree across originals/concepts/people/companies/ideas/personal/voice-notes."
|
|
},
|
|
{
|
|
"name": "cold-start",
|
|
"path": "cold-start/SKILL.md",
|
|
"description": "Day-one brain bootstrapping: sequence the highest-leverage data sources (contacts, calendar, email, conversations, social, archives) to go from empty brain to useful brain. Uses ClawVisor for safe credential handling \u2014 agents never hold raw API keys."
|
|
},
|
|
{
|
|
"name": "ask-user",
|
|
"path": "ask-user/SKILL.md",
|
|
"description": "Reusable choice-gate pattern for presenting users with 2-4 options and stopping execution until they respond. Platform-agnostic (Telegram buttons, Discord, CLI, OpenClaw clarify tool)."
|
|
},
|
|
{
|
|
"name": "functional-area-resolver",
|
|
"path": "functional-area-resolver/SKILL.md",
|
|
"description": "Compress an agent's routing file (RESOLVER.md or AGENTS.md) by replacing skill-per-row tables with functional-area dispatcher entries. Two-layer dispatch keeps every sub-skill reachable at ~50% of the file size."
|
|
},
|
|
{
|
|
"name": "gbrain-advisor",
|
|
"path": "gbrain-advisor/SKILL.md",
|
|
"description": "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. Read-only; always asks before fixing."
|
|
},
|
|
{
|
|
"name": "brain-taxonomist",
|
|
"path": "brain-taxonomist/SKILL.md",
|
|
"description": "Filing gate consulted before every brain page write. Reads the active schema pack via `gbrain schema show --json`; emits a recommended filing path with reasoning."
|
|
},
|
|
{
|
|
"name": "eiirp",
|
|
"path": "eiirp/SKILL.md",
|
|
"description": "Everything In Its Right Place \u2014 post-work organizer. 7-phase audit: inventory, taxonomy, schema check (via cathedral CLI), file, skill graph audit, verify, report."
|
|
},
|
|
{
|
|
"name": "schema-unify",
|
|
"path": "schema-unify/SKILL.md",
|
|
"description": "Migrate a brain off a noisy 24+-type pack onto gbrain-base-v2 (15 canonical types). 7-phase workflow: brain \u2192 assess \u2192 propose \u2192 apply \u2192 sync \u2192 verify \u2192 commit. Wraps the v0.41.22 unify-types PROTECTED Minion handler."
|
|
},
|
|
{
|
|
"name": "skill-optimizer",
|
|
"path": "skill-optimizer/SKILL.md",
|
|
"description": "Self-evolving skill optimization via gbrain skillopt \u2014 SkillOpt-paper-grounded text-space optimizer with validation gating (median-of-3 + epsilon=0.05), bundled-skill safety, bootstrap review sentinel, per-skill DB lock, and atomic versioned writes."
|
|
},
|
|
{
|
|
"name": "measure-before-you-fix",
|
|
"path": "measure-before-you-fix/SKILL.md",
|
|
"description": "Before fixing a slow/stale/timeout alert, measure the step yourself. Kill the theory with a stopwatch, not a code change. Measure-first ops triage for temporal alerts (stale, timeout, freshness, wedged, N hours behind)\u2026"
|
|
},
|
|
{
|
|
"name": "data-loss-gate",
|
|
"path": "data-loss-gate/SKILL.md",
|
|
"description": "Confirmation gate before any bulk delete, cleanup, or destructive operation that could result in data loss \u2014 shell-level (rm -rf, git rm, bulk sed) or brain-level (bulk forget, delete sweeps, purge-deleted, source\u2026"
|
|
},
|
|
{
|
|
"name": "fact-check",
|
|
"path": "fact-check/SKILL.md",
|
|
"description": "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\u2026"
|
|
},
|
|
{
|
|
"name": "resolve-before-asking",
|
|
"path": "resolve-before-asking/SKILL.md",
|
|
"description": "Gate on identity questions to the user. Before any \"who is X?\" (or role / relationship question) reaches the user, exhaust the brain's lookup chain: think \u2192 search + page read \u2192 mounted sources \u2192 timeline/graph \u2192 web."
|
|
},
|
|
{
|
|
"name": "brain-ingest-gate",
|
|
"path": "brain-ingest-gate/SKILL.md",
|
|
"description": "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\u2026"
|
|
},
|
|
{
|
|
"name": "correction-pipeline",
|
|
"path": "correction-pipeline/SKILL.md",
|
|
"description": "When the user corrects a factual error, root-cause it immediately. Don't just note the correction \u2014 trace the error to its source, fix the source, and prevent recurrence."
|
|
},
|
|
{
|
|
"name": "company-brainify",
|
|
"path": "company-brainify/SKILL.md",
|
|
"description": "Extract a sanitized shared team/company brain from a personal brain. Strips internal ratings, compensation, performance assessments, retention and political dynamics from pages, takes, and facts across the full scan\u2026"
|
|
},
|
|
{
|
|
"name": "citation-graph-ingest",
|
|
"path": "citation-graph-ingest/SKILL.md",
|
|
"description": "Build a TYPED citation/reference graph over an ingested corpus \u2014 not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D."
|
|
},
|
|
{
|
|
"name": "two-tier-extraction",
|
|
"path": "two-tier-extraction/SKILL.md",
|
|
"description": "Tiered LLM extraction pattern for large corpus processing (email archives, document dumps, transcript libraries). A utility-tier model triages and classifies at speed; the reasoning tier does the default deep read; the\u2026"
|
|
},
|
|
{
|
|
"name": "brain-link-discipline",
|
|
"path": "brain-link-discipline/SKILL.md",
|
|
"description": "When you report a brain page to the user \u2014 created, edited, committed, or relayed from a subagent \u2014 a working link is part of the deliverable, in the SAME message."
|
|
},
|
|
{
|
|
"name": "draft-in-voice",
|
|
"path": "draft-in-voice/SKILL.md",
|
|
"description": "Ghostwrite content in a specific person's voice from a VALIDATED voice profile \u2014 tweets, replies, short posts, launch copy, recruiting blurbs, emails."
|
|
},
|
|
{
|
|
"name": "bulk-ingestion",
|
|
"path": "bulk-ingestion/SKILL.md",
|
|
"description": "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."
|
|
},
|
|
{
|
|
"name": "research-compendium",
|
|
"path": "research-compendium/SKILL.md",
|
|
"description": "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\u2026"
|
|
},
|
|
{
|
|
"name": "context-audit",
|
|
"path": "context-audit/SKILL.md",
|
|
"description": "Token-hygiene audit of the always-loaded context stack \u2014 CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md) or their harness\u2026"
|
|
},
|
|
{
|
|
"name": "blog-ingest",
|
|
"path": "blog-ingest/SKILL.md",
|
|
"description": "Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a common article shape, canonical-URL\u2026"
|
|
},
|
|
{
|
|
"name": "conversation-archive",
|
|
"path": "conversation-archive/SKILL.md",
|
|
"description": "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 native conversation\u2026"
|
|
},
|
|
{
|
|
"name": "skill-autobench",
|
|
"path": "skill-autobench/SKILL.md",
|
|
"description": "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 \u2014 a user correction after an\u2026"
|
|
},
|
|
{
|
|
"name": "db-repair",
|
|
"path": "db-repair/SKILL.md",
|
|
"description": "Auto-fix gbrain Postgres access: GBRAIN_DB_ACCESS marker -> diagnose -> tiered gbrain db-repair ladder -> verify"
|
|
},
|
|
{
|
|
"name": "postgres-adopt",
|
|
"path": "postgres-adopt/SKILL.md",
|
|
"description": "Detect the active engine (PGLite vs Postgres), prefer/install Postgres for harness installs, wrap the guarded engine migration"
|
|
}
|
|
],
|
|
"dependencies": {
|
|
"runtime": "bun",
|
|
"package": "gbrain"
|
|
},
|
|
"setup": {
|
|
"skill": "setup",
|
|
"description": "Auto-provision Supabase or PGLite and configure GBrain (< 2 min)"
|
|
},
|
|
"recipes_dir": "recipes/",
|
|
"resolver": "RESOLVER.md",
|
|
"conventions_dir": "conventions/",
|
|
"templates_dir": "../templates/"
|
|
}
|