| Skill | Added | Review |
|---|---|---|
idea-lineage plugin-variants/gbrain-coding/skills/idea-lineage/SKILL.md Trace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
ingest skills/ingest/SKILL.md Route content to specialized ingestion skills. Detects input type and delegates. | 48 48 Impact — No eval scenarios have been run Securityby Critical Do not install without reviewing Version: e78f1c3 | |
ingest plugin-variants/gbrain-coding/skills/ingest/SKILL.md Route content to specialized ingestion skills. Detects input type and delegates. | 48 48 Impact — No eval scenarios have been run Securityby Critical Do not install without reviewing Version: e78f1c3 | |
maintain skills/maintain/SKILL.md Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality. | 54 54 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
maintain plugin-variants/gbrain-coding/skills/maintain/SKILL.md Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality. | — — — Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
mcp-access plugin-variants/gbrain-coding/skills/mcp-access/SKILL.md Open the GBrain owner dashboard, manage MCP clients and permissions, or connect a native OAuth harness. Distinguishes owner administration from ordinary MCP access. | 62 62 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
measure-before-you-fix plugin-variants/gbrain-coding/skills/measure-before-you-fix/SKILL.md 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) from gbrain doctor, autopilot, sync, and cron monitors — runs BEFORE any timeout raise, threshold change, or pipeline rewrite. | 73 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
media-ingest skills/media-ingest/SKILL.md 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. | 65 65 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
meeting-ingestion skills/meeting-ingestion/SKILL.md 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). | 63 63 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
migrate skills/migrate/SKILL.md Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam | 50 50 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
minion-orchestrator skills/minion-orchestrator/SKILL.md Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface. Also carries the durable-execution doctrine for any operation expected to exceed ~2 minutes: capability ladder, deadman checks that verify the result was reported, and content-addressed stage checkpoints for expensive pipelines. | 70 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
perplexity-research skills/perplexity-research/SKILL.md 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). | 61 61 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: e78f1c3 | |
postgres-adopt plugin-variants/gbrain-coding/skills/postgres-adopt/SKILL.md 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. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
publish skills/publish/SKILL.md Share brain pages as beautiful password-protected HTML with zero LLM calls | 53 53 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: e78f1c3 | |
query skills/query/SKILL.md Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
query plugin-variants/gbrain-coding/skills/query/SKILL.md Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
reference-pack examples/skillpack-reference/skills/reference-pack/SKILL.md Reference skill demonstrating the 10/10 skillpack contract. Adds a "what does this skillpack do" answer to the user's agent. | 52 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
repo-architecture skills/repo-architecture/SKILL.md Where new brain files go. Decision protocol for filing brain pages by primary subject, not by format or source. Reference for all brain-writing skills. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
repo-architecture plugin-variants/gbrain-coding/skills/repo-architecture/SKILL.md Where new brain files go. Decision protocol for filing brain pages by primary subject, not by format or source. Reference for all brain-writing skills. | 58 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 | |
reports skills/reports/SKILL.md Save and load timestamped reports. Keyword routing for fast lookup. Cron jobs save output as reports; the agent or user queries them by keyword. Includes the Actionability Gate: delivery-time link checks (Broken/Dead/Indirect/ Missing) for briefings, meeting digests, and research reports. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e78f1c3 |