メニュー
Global embedding-based search across all Notes; returns a Collection of matches
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
| name | discover-notes |
| type | primitive |
| description | Global embedding-based search across all Notes; returns a Collection of matches |
query (required): Natural-language search stringout (required): $variable for the resulting Collectionlimit (optional, default 5): Max number of Notes returned (top-K by similarity)threshold (optional, default 0.3): Minimum cosine similarity for a matchREQUIREMENTS:
query and out must be providedRuns an embedding-based search over every Note in the current infospace and returns the top-limit Notes above threshold as a Collection. Each hit is wrapped in a structured search-result Note (same shape as search-web / semantic-scholar results). An empty-case (no matches) still returns success with an empty Collection.
limit is a hard top-K cap. There is no way to express "all matches above threshold" — if you need higher recall (e.g. the goal says "all existing Notes that X"), pass an explicit larger limit (50+ is reasonable for a few-hundred-Note infospace). With the default of 5 the planner cannot distinguish "exhaustive" from "undersampled".
{"type": "discover-notes", "query": "transformer architectures or attention mechanisms", "out": "$matches"}
{"type": "discover-notes", "query": "meeting notes about the Q2 release", "limit": 50, "threshold": 0.25, "out": "$hits"}
Returns success with the Collection bound to out. Use get_items("$var") to read the list of result Note IDs.
query or outlimit=5 for "find all" goals — the result is silently top-5, not exhaustive. Always pass an explicit higher limit when the goal wording signals exhaustiveness.failed — an empty Collection is the legitimate no-match outcome. Branch on len(get_items("$var")), not on the tool's status.discover-notes when the goal names a specific resource (_rss_pending_titles, etc.) — use load for known names, discover-notes for semantic discovery.