Migrate feature flags from Eppo to Confidence SDK. Use when the user says /migrate-eppo, asks to migrate Eppo flags, or transform SDK code to Confidence.
Use when running, testing, or benchmarking ezpz on an HPC system (Aurora, Sunspot, Polaris, Perlmutter) — job submission, environment setup, and the failure modes that silently produce wrong results.
Infers directional cellular trajectories from scRNA-seq using spliced/unspliced ratios. Use when predicting cell fates, differentiation endpoints, or driver genes from a single snapshot — covers scVelo, VeloVI, Chronocell, and CellRank. Needs intron-aware quantification; for the upstream counting use starsolo-spliced-unspliced.
Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.
Mastermind monitor — long-running executor that watches Linear, GitHub, Monotask boards and folders for new tasks, claims and runs them with the right agent, and reports progress.
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
Use when working with any public API (Stripe, GitHub, Spotify, AWS, Twilio, Slack, Google, etc.) and needing accurate endpoint signatures, parameter types, auth schemes, or response schemas. Use BEFORE consulting training data, doc sites, Stack Overflow, or context7 to avoid outdated/stale API info.
Convert PDF files to clean Markdown offline and deterministically, with tables (ruled and borderless/booktabs) and sidebars placed inline and PDF metadata stripped. Use whenever the user wants a PDF turned into Markdown or text, wants a paper/report/scan extracted, asks what is in a PDF, or mentions pdf2md or pdf-to-md-transformer. Handles scanned PDFs via Tesseract OCR.
REQUIRED ENTRY POINT for ALL Unreal Engine tasks. Must trigger for UE5, Blueprints, C++, UMG, Editor, UObject, multiplayer, compilation, or any engine interaction.
Set up Butler for a household, one step at a time, matching the Build Your Butler course. Steps are install (review and complete the household after the guided first run), calendar, brain (Claude API key), inbox (Gmail and the daily schedule), replies, money (Lunch Money), projects, letters and phone (Tailscale portal). Use when the user runs /butler-setup, with or without a step, or asks to set up, install or continue setting up Butler.
Join a Google Meet, Zoom, or Teams meeting as an AI presenter and DELIVER a presentation — slides on the bot's camera, narrated aloud, auto-advancing. Hand it a DOCUMENT (PDF, PowerPoint, or Word) or a TOPIC. A PowerPoint (already a deck) is shown as-is; a Word/PDF document is turned into a meaningful deck the agent authors from the source's text AND figures. Cross-platform and self-contained. Use when the user wants their agent to present something in a live meeting.
Use when creating or editing a Struphy simulation parameter file (params_*.py) - choosing a model, configuring domain/grid/time-stepping, species/backgrounds/perturbations and propagator options, then running the simulation. Triggers on requests like "set up a simulation", "create a params file for a model", "configure a model run", or "how do I run struphy". For reading and plotting results, use the postprocess-simulation skill.
Build, start, run and drive cc-backend end to end — an isolated server with the internal metric store, ingest line protocol, start jobs, query GraphQL/REST, smoke-test metric queries and scopes. Use when asked to run, start, launch, smoke-test or live-check cc-backend, or to verify a change against the running server rather than only the test suite.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.