AMC-JTC
Community@AMC-JTC
AMC-JTC maintains a 99-skill manifest for gbrain, a personal knowledge-brain system covering ingestion, schema taxonomy, citation graphs, and retrieval.
Agent Skills by AMC-JTC
Showing 67 vetted skills indexed across 1 GitHub repositories.
AMC-JTCvoice-note-ingest
Ingest voice notes into a knowledge base with verbatim transcript preservation and directory routing.
AMC-JTCarticle-enrichment
Rewrites raw article text dumps into structured brain pages with summaries, quotes, and cross-references.
AMC-JTCminion-orchestrator
Orchestrates durable shell jobs and LLM subagents through a Postgres-backed job queue.
AMC-JTCschema-author
Evolves GBrain schema packs by adding page types, link verbs, and backfilling page.type on existing pages.
AMC-JTCdaily-task-prep
Generates a morning prep briefing from calendar, brain context, open threads, and prioritized tasks.
AMC-JTCcapture
Save thoughts and content into a GBrain knowledge base via one CLI command.
AMC-JTCbrain-taxonomist
Determines filing paths for new brain pages by reading the active schema pack.
AMC-JTCcitation-fixer
Audit and fix inline source citations across brain pages, resolving broken tweet references via X API.
AMC-JTCblog-ingest
Ingest entire blogs, newsletters, and RSS feeds into deduplicated brain source pages.
AMC-JTCcompany-brainify
Sanitize a personal knowledge brain into a shareable team brain by stripping sensitive content.
AMC-JTCbrain-link-discipline
Generates verified clickable links for brain pages in delivery messages using git-derived paths.
AMC-JTCcorrection-pipeline
Root-cause user-reported factual errors and fix them at their contamination source.
AMC-JTCcron-scheduler
Schedules cron jobs with staggered slots, quiet hours gating, and idempotency checks.
AMC-JTCeiirp
Organizes post-work outputs into brain pages and audited reusable skills.
AMC-JTCask-user
Present 2-4 labeled options to users and gate agent execution until they respond.
AMC-JTCarchive-crawler
Scans allow-listed personal archives and ingests high-value writing into brain pages.
AMC-JTCbrain-ingest-gate
Validates named-entity resolution and semantic dedup before writing pages into a knowledge base.
AMC-JTCingest
Routes meetings, articles, media, and documents into a structured knowledge graph with citations and back-links.
AMC-JTCrepo-architecture
Determines the correct directory for new brain pages by primary subject.
AMC-JTCskill-optimizer
Optimizes SKILL.md bodies against benchmarks using validation-gated text-space optimization.
AMC-JTCcontext-audit
Audits always-loaded context files for redundancy, contradictions, and token waste.
AMC-JTCdata-loss-gate
Requires explicit user confirmation before bulk delete or destructive operations.
AMC-JTCskillpack-check
Generates a JSON health report for gbrain installs by composing doctor and migration checks.
AMC-JTCcitation-graph-ingest
Extracts and classifies typed citation edges between documents in an ingested gbrain corpus.
Frequently Asked Questions About AMC-JTC
FAQPage SchemaWhat tasks can I accomplish with AMC-JTC's gbrain skills?▼
The skills cover ingesting meetings, voice notes, articles, books, and chat exports into a personal knowledge brain; managing schema packs and page taxonomies; building typed citation graphs; fact-checking claims against live sources; scheduling cron jobs; and sanitizing brains for team sharing.
Who is the target user for these gbrain skills?▼
Operators running a gbrain or OpenClaw personal knowledge-brain installation: founders, investors, and researchers who want durable memory across meetings, email, reading, and conversations, plus engineers maintaining the skillpack, schema packs, and agent routing files.
How do the ingestion skills work in practice?▼
Skills like meeting-ingestion, voice-note-ingest, blog-ingest, and media-ingest normalize source content, resolve entities against existing brain pages, deduplicate via the brain-ingest-gate, then write typed pages under directories like people/, companies/, meetings/, and sources/ with backlinks and timeline entries.
What prerequisites do these skills require?▼
A working gbrain installation with an active schema pack; several skills require specific directories (e.g., conversations/ for skill-autobench), a gbrain.yml allow-list for archive-crawler, ClawVisor for credential handling in cold-start, and Perplexity access for perplexity-research web lookups.
How do the skills enforce data quality and safety?▼
Dedicated gate skills enforce discipline: data-loss-gate requires explicit confirmation before bulk deletes, brain-ingest-gate blocks raw copies without dedup, citation-fixer audits source formatting, fact-check verifies claims against live sources, and frontmatter-guard validates YAML on every brain page.