Explore in MochiBot. Install in chat.Hosted workspaces and MochiBot lightweight setups include the Skills assistant. Choose a Skill and ask for installation in chat. Other OpenClaw setups can follow the first-install guide.
How to use Skills →
MOCHILAB / AI SKILL
In-Text Citation and Bibliography Crosscheck
Bounded parsers for explicit author-year keys (including year suffix) and numeric citation ranges; preserve extracted spans/line numbers.
Tell your assistant what you want to check and provide the actual relevant materials. It prepares the structured records and asks for facts that affect the result.
Crosscheck this paper’s in-text citations against its bibliography and show unmatched entries with locations.
Find ambiguous author-year keys and unused bibliography entries; preserve my original document.
You receive a readable report, detailed records and a preserved input snapshot. Bounded parsers for explicit author-year keys (including year suffix) and numeric citation ranges; preserve extracted spans/line numbers. Build many-to-many citation/reference mapping and detect ambiguous keys rather than guessing. Treat styles/fields outside supported syntax as unparsed coverage.
No claim that a reference exists or supports a statement. No Zotero/Word citation-field repair or guaranteed full PDF OCR. Never silently alter original prose or delete an uncited reference.
Runs locally with Python 3.10+ standard library; no paid data key or MochiLab backend account is required. Optional extraction and explanation use your current agent model under its existing service terms. No automatic messages, applications, account changes or notifications.