Menu
Extract bibliography/references from PDF files using GROBID and return a Collection of Notes (one per reference).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | extract-references |
| type | python |
| description | Extract bibliography/references from PDF files using GROBID and return a Collection of Notes (one per reference). |
| schema_hint | {"path":"string (PDF file path or Note ID)","grobid_url":"string"} |
| resolve | {"path":"resource_id"} |
Extract bibliography/references from PDF files using GROBID. Returns a Collection of Notes, where each Note contains structured metadata for one reference (compatible with format-citation).
path: PDF file path (absolute) or Note ID containing PDF URL/metadata (required)grobid_url: Optional GROBID server URL (from world_config)Success (status: "success"):
resource_id: Collection ID containing Notes (one Note per reference)data: Structured reference metadata (title, authors, year, venue, doi, url)metadata: Source PDF, reference index, raw citation text<bibl> elementsformat-citation toolsemantic-scholar), looks up pdf_url from the Note's tool_metadata automatically — no manual metadata extraction neededThis is the right tool for bibliography/reference extraction from papers. It uses GROBID structural parsing (deterministic, fast) rather than LLM extraction (slow, lossy). Prefer this over extract or map(extract) with citation-related instructions.
Common workflow with semantic-scholar:
semantic-scholar → $paper Collectionget_items("$paper")[0] → Note ID (contains pdf_url in tool_metadata)extract-references(path=note_id) → $refs Collection of structured citation Notes{"title": "...", "authors": [...], "year": 2020, "venue": "..."}get_text(note_id) + json.loads() in PythonDo NOT:
$binding string as path — pass the actual Note ID from get_items()pluck(field="text") on result Notes — content is JSON, not plain textextract or map(extract) for reference lists — this tool is faster, structured, and deterministic{"type":"extract-references","path":"/path/to/paper.pdf","out":"$refs"}
{"type":"extract-references","path":"Note_1234","out":"$refs"}
{"type":"format-citation","target":"$refs","format":"bibtex","out":"$bibtex"}
Full semantic-scholar pipeline:
{"type":"semantic-scholar","query":"attention is all you need","limit":1,"out":"$paper"}
items = get_items("$paper")
r = tool("extract-references", path=items[0], out="$refs")
Fetch standardized financial statements (income, balance sheet, cash flow, earnings, company overview) for a ticker from Alpha Vantage. Returns combined annual+quarterly JSON for analysis.
Aim the ChatterBot head to find and center a target in view — the user, a person, an object, an animal. Runs a closed visual loop (capture, judge where the target is, nudge pan/tilt, repeat) until the target is centered, or reports it could not find the target after searching. Use when the user says point at me, look at me, turn to face someone, find the cat, center on the person. For a one-off snapshot without re-aiming use camera-capture; for a manual fixed angle use head-move.
Capture a still photo from the ChatterBot head camera. The captured frame is attached to your own visual input, so you can SEE it and answer questions about what is in view — whether the user is present, whether there is a cat, what the scene looks like. The camera rides the pan/tilt head, so it shows whatever the head is currently aimed at; aim first with head-move if needed. To also show the photo to the user on screen, follow with the display tool (the observation includes a ready <img> URL). Use when the user asks what you see, to take a picture or snapshot, or to check whether something or someone is in view.
Move the ChatterBot head — aim the pan/tilt camera or play an expressive gesture. The bot is a stationary companion head; this points its gaze, it does NOT drive or navigate. Use when the user asks you to look somewhere, turn toward/away, look up/down, re-center, or nod/shake/scan. Angles are degrees 0-180 with 90 centered (pan 0=full right, 180=full left; tilt 0=down, 180=up, mounting-dependent). Give pan and/or tilt for absolute aim, OR a gesture (not both). Returns the confirmed pose once the head settles.
Return one genuine saying of Ramana Maharshi, drawn verbatim from his recorded talks, with source attribution. Use when delivering an authentic Ramana quote with attribution — not a paraphrase or a synthesized reflection. The returned text is a raw quote; add your own brief framing before presenting it.
Generate an original image from a text description, locally (Bonsai-Image 4B, ternary-quantized, on a long-lived studio server). Use when the user wants a picture, illustration, avatar, or face created from a description that does not already exist on the web. For existing photos of real things, prefer image search instead; for simple diagrams or line drawings, prefer authoring inline SVG.