Install
openclaw skills install @javihaus/groundlensCheck an answer against the user's own documents before sending it. Catches wrong figures, recomputes the arithmetic, and flags claims about the wrong company or person. Runs locally in milliseconds, no API key, no second model.
openclaw skills install @javihaus/groundlensUse this skill when you answer from documents the user gave you or that you retrieved (reports, contracts, invoices, statements, regulations, notes) and your answer contains figures, dates, percentages, amounts or names.
GroundLens compares your draft with those documents and returns one of three decisions:
It runs on the user's machine. No account, no API key, no network, no model.
Skip it for small talk, opinions, or answers with no figures and no documents.
Write the draft answer, the question and each source to files, then:
groundlens verify \
--question question.txt \
--answer answer.txt \
--source report=annual_report.txt \
--source notes=meeting_notes.txt
report=, notes=); the result cites it.--scope entity="Acme Ltd" when the question is about one entity.--locale es (or de, fr, ...) when the documents write numbers in
that language's format, e.g. 41,2 millones.--json to get the full record with every claim and its source.Exit code: 0 PASS, 1 FAIL, 3 REVIEW, 2 error.
Example output:
FAIL policy=groundlens_default_v1 record=rec_ab201f0cf308_b0ced69fd71a
c2 groundlens.numeric contradicted 0.00 nearest in report: '€41.2 million'
c5 groundlens.numeric unsupported 0.00 nearest in report: '2025'
Never present a FAIL or REVIEW answer as verified.
GroundLens checks figures, arithmetic, who the answer is about, and whether it answers the question. It does not judge the meaning of free text: a wrong statement with no number in it will usually pass. Treat PASS as "no figure problem found", not as "the answer is true".
uvx --from "groundlens[mcp]" groundlens-mcp