A conversational tool for reading OPC listings of events and competitions. OPC is a website for people running one-person businesses, and its event content includes startup contests, hackathons, academic competitions, and industry conferences.
Persistent semantic memory across sessions, stored in a local HNSW vector index with local embeddings and no external API calls. Use when the user asks you to remember something for later, refers to something decided or discussed in an earlier session, asks what you already know about a topic or project, or when you…
Performs verified local nucleotide-sequence computation with Computase. Use when an agent needs sequence composition or GC bounds, a reverse complement, translation, candidate ORFs, or IUPAC motif sites through Computase MCP tools or the isolated Skill runner.
Precision editing of existing Excalidraw elements using structured selection feedback. Use when the agent needs to (1) inspect elements the user has clicked on via getselection, (2) run automated quality checks (textOverflow, overlaps, spacing, readability), (3) precisely modify elements with updateelement, (4) verify…
A skill for resolving images selected in the Seetuu desktop app through a handoff link. Seetuu is an image-selection tool, and the handoff link identifies the selected images.
An image-analysis skill that sends a local image, web image, or base64 image to a vision service and returns an answer to a question about it. It can handle image descriptions, visual questions, and OCR, which means extracting text from an image.
A writing tool for building interactive story games, such as text adventures, branching fiction, mystery investigations, and light puzzles. It exports the result as a single HTML file that can be opened directly in a browser.
Use when the user asks a data question in plain English that needs SQL across one or more configured databases (ClickHouse, Teradata, PostgreSQL/GaussDB, MySQL, SQL Server, DB2, Oracle, Mongo). Governed NL→SQL via the chat-sql MCP server — results are PII-masked and writes are limited to scratch tables the assistant…
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
Apply security, read-only, authorization, and same-layer verification rules to agent-operated LinkedIn workflows. Use before account-visible changes, private request replay, broad captures, or provider AI tasks.
Fallback vision for agents that CANNOT see images themselves. If you can read images natively (multimodal model, image-capable Read tool), do NOT use this skill — look at the image directly instead. Only use for image questions, OCR, UI inspection, or visual debugging when native vision is unavailable or failed, and…
Discover and inspect Figma designs from URLs, natural-language descriptions, or reference screenshots. Use for cross-team design search, flow explanation, design-to-code, and visual/spec/asset inspection through the figmalens MCP tools or CLI.
Vision methodology and file-output conventions for the j-can-see MCP server. TRIGGER GATE — on models WITH native vision input, invoke this skill only when the user explicitly asks for j-can-see, or when native vision has actually failed on the task (cannot open/read an image, unusable output). Otherwise read images…
Anchor this session to a named Chat Across environment and auto-sync a compacted context brief both ways. Use when the user says "chat-across " or asks to connect/anchor to a Chat Across environment.
How to use the remarkable-mcp server: call remarkableexecute with JavaScript that uses rme. to list, read, write, upload, and organize reMarkable notebooks. Use when the user mentions reMarkable, tablet notes, xochitl, e-ink, Type Folio, uploading a PDF/EPUB, exporting handwriting, drawing Mermaid on the tablet, or…
Use when an engineering task may benefit from an independent Claude Code investigation, review, or alternative implementation and the value of delegation must be weighed against cost and risk.
★not rated 0 13d agoA38 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: