Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.
Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tree-sitting (structural) with semantic (why/what-for) layer.
Produce a self-contained HTML artifact instead of a markdown document when the request is for content that benefits from spatial layout, color, real diagrams, interactivity, or a round-trip editor. Use this skill aggressively whenever the user asks for a "doc," "writeup," "plan," "spec," "report," "explainer," "summary," "comparison," "review," "PR description," "mockup," "diagram," "flowchart," "deck," "slides," "status update," "post-mortem," "incident report," "playground," or a one-off "editor" or "tool" for triaging/reordering/tuning anything — even if they don't explicitly say "HTML" or "artifact." Also trigger when the user asks Claude to "explain," "summarize," "compare," "explore options for," "brainstorm directions for," or "walk through" a non-trivial topic. Stay in markdown only for short conversational replies, code-only outputs, terminal-style command answers, and content that's genuinely just a few sentences.
Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to mapping-codebases but for prose documents.
Query, filter, and transform Markdown structurally with mq — a jq-like CLI for Markdown. Use to extract headings/sections/code-blocks/links from .md files, build a table of contents, pull code blocks of a given language, slice or reshape LLM prompt/output Markdown, or batch-transform docs. Triggers on "extract sections from this markdown", "get all the code blocks", "jq for markdown", "mq", or any structural query over Markdown that grep/Read can't do cleanly.
Preprocesses photographed sheets of many business cards — slicing each into overlapping high-resolution tiles and de-glaring them with container tooling (OpenCV/ImageMagick) — then reads every card via cheap parallel temperature-0 API calls (Haiku or Sonnet) using a distilled extraction prompt, and writes deduped contact fields to a CSV. Use when a user has photos or scans holding multiple business cards per image, mentions glare or unreadable cards, batch card transcription, contact extraction, or wants to read many cards without an expensive in-conversation pass. Triggers on 'business cards', 'card scan', 'extract contacts', 'read these cards', 'card glare', 'too many cards per photo'.
Use when normalized resume material is ready and must be rewritten, organized, and assembled into a 1-2 page LaTeX resume without inventing facts.
Use when creating, rewriting, or converting a source-backed 1-2 page resume from chat, documents, PDFs, images, or mixed artifacts.
Use when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
Use when a LaTeX resume draft exists and needs factual review, ATS or research-resume risk checks, build validation, packaging, and final delivery.