Claude Skills by bdambrosio

Bind a variable to an existing resource without creating or changing content

Create a Collection object and bind to variable

Create a persistent Note object and bind to variable

Global embedding-based search across all Notes; returns a Collection of matches

Filter Collection by field conditions (SQL WHERE)

Flatten Collection to single Note

Retrieve metadata attached to a Note or Collection

Load persistent Note or Collection by ID or name, with optional slice

Apply operation to each item in Collection

Mark a Note or Collection as persistent so it survives goal-completion cleanup

Extract single field value from each Note in Collection

Extract metadata/structured fields from each Note in Collection (SQL SELECT)

Attach or update metadata on a Note or Collection

Transform a Note's internal structure into a Collection of Notes.

Generate an internal reflection on the state of the plan

Tests calculate tool with arithmetic, trig, and variable substitution

Tests filter-structured primitive (WHERE clause)

Tests join primitive (INNER JOIN)

Tests pluck primitive (SELECT single field)

Tests project primitive (SELECT fields)

Test JSON SQL primitives with search-web output

Test JSON SQL primitives with semantic-scholar output

Creates test data for JSON SQL primitive tests

Tests sort primitive (ORDER BY)

Tests map primitive with additional operation arguments

Drains buffered page-visit URLs from the browser extension listener

Detects new files in the Obsidian vault Clippings folder (from Web Clipper)

Monitors RSS feeds for new items matching configured keywords

Time heartbeat for chat-mode autonomy — fires every schedule period to trigger concern cadence checks

Check whether text matches a natural-language condition. Returns "true" or "false". Auto-chunks long texts and short-circuits on first match.

Compute the value of a math expression. Handles arithmetic, algebra, trig, calculus. Use this instead of LLM arithmetic — calculate is exact and deterministic.

Read recent emails from a Gmail inbox via IMAP. Returns text with subject, sender, date, and body per email. Read-only — never marks messages as read.

Run a bash/shell script — for system commands the existing tools don't cover. Trusted by default; treat with the same care as any code-execution action.

Fetch the text content of a web page or PDF from a URL. Handles HTML, PDF, Markdown, plain text — auto-detects format.

Filter a list of items to those matching a natural-language condition (e.g. "only the items that mention X"). NOT YET WIRED in chat-mode — present in src/tools/ for future enablement.

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.

Read, search, write, and list notes in the user's Obsidian vault. Multi-action — set `action` first, then provide the args required by that action.

Search the web for information on a topic. Returns a synthesized summary with citations. Use when you need current information or facts not in training data.

Search academic papers and journals. Returns paper text — full text when available via GROBID, otherwise abstracts. Use for scholarly literature, not general web content.

Look up the current stock price (price, change, volume) for a ticker symbol. End-of-day data on the free tier.

Find a substring or pattern in a text document. Returns position with surrounding context. Deterministic — use this instead of asking the LLM to find substrings.

Identify and extract JSON from mixed content, optionally extracting specific fields

Extract markdown document structure and content from mixed/embedded text (NOT for converting plain text TO markdown)

Returns API instructions (not data) for retrieving Bluesky metrics via AT Protocol. Read the returned instructions, then use fetch-text + extract to get actual data.

Browser automation via agent-browser CLI. Navigate, snapshot accessibility tree, interact by element ref.

Collect system and cognitive health metrics. Returns a structured health report with status classifications (ok/warning/critical) for hardware, OS, and cognitive subsystems.

Delegate coding, research, and code analysis tasks to Claude Code CLI. PREFERRED tool for reading, searching, or analyzing source code (including your own — use target=self). Use whenever a goal asks you to look at, analyze, or reason about code files (your src/, your codebase, your implementation, fs/src/). Ground claims about your own architecture, capabilities, or behavior in actual source code rather than generating from general knowledge.

Generate a new tool. Python tools go to staging for review. Instruction tools (no code) are created and registered immediately.

Extract named entities, topics, and relationships from text or structured content

Extract bibliography/references from PDF files using GROBID and return a Collection of Notes (one per reference).