Score breakdown0 Version history1 Source
Category Weight Category score Contribution
Security prompt, exec, net, exfil, eval
35%
100
35.0 pts
Supply chain hash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenance staleness, pinning, CI
15%
100
15.0 pts
Transparency SKILL.md, perms, README
15%
100
15.0 pts
Community installs, verify, response
15%
100
15.0 pts
Findings & checks · 0 flagged
Security score 100 · 0 findings
✓ — All security checks passedNo findings in this category for the latest scan. pass
Supply chain score 100 · 0 findings
✓ — All supply chain checks passedNo findings in this category for the latest scan. pass
Maintenance score 100 · 0 findings
✓ — All maintenance checks passedNo findings in this category for the latest scan. pass
Transparency score 100 · 0 findings
✓ — All transparency checks passedNo findings in this category for the latest scan. pass
Community score 100 · 0 findings
✓ — All community checks passedNo findings in this category for the latest scan. pass
Every scanned point with the score it earned and what moved between them.
1 scans · 90 days 1e5a682 latest
Jun 27, 2026 100 1e5a682
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
plugins/openclaw/skills/gbrain-query/SKILL.md · 1 file plugins/openclaw/skills/gbrain-query/SKILL.md 1.0 KB · Markdown Rendered Raw ⧉ Copy
name : gbrain-query
description : Answer questions from the brain using FTS5, semantic search, and structured queries.
metadata :
openclaw :
emoji : "🔍"
requires :
bins : [gbrain]
Query Skill Strategy Start with gbrain search "<query>" when the question contains names, exact terms, or acronyms. Run gbrain query "<question>" for semantic recall when embeddings are configured. OpenAI and OpenRouter both work. Use gbrain list, gbrain backlinks, gbrain timeline, and gbrain tags when the question is relational or date-sensitive. Read the top candidate pages with gbrain get <slug> before answering. Cite slugs in the answer so the user can jump back into the brain. Rules Fall back to lexical search if embeddings are missing or unhealthy. Prefer pages with fresher compiled truth when two answers conflict. If the brain does not contain the answer, say that directly. If the answer should become durable memory, suggest writing it back with gbrain put.