Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.

Ingest tabular Parquet files into Rerun chunk streams with rerun.experimental.ParquetReader. Read when converting trajectory or sensor tables (LeRobot-style parquet, exported logs) into entities and components — column grouping, timeline/index columns, static columns, and lenses (DeriveLens) that assemble the typed components (Transform3D, Scalars) from the reader's grouped struct/scalar output. Builds on rerun-chunk-processing and rerun-data-model.

Core mechanics of the Rerun Chunk Processing API (rerun.experimental) — LazyChunkStream pipelines, Chunk, lenses (MutateLens/DeriveLens/Selector), RrdReader, writing optimized RRDs. Read BEFORE writing any ingestion/conversion/preprocessing code (convert an MCAP, build a recording from a dataset, preprocess an .rrd, port an old converter): it mandates reader+lens pipelines and steers away from hand-built chunks — no Chunk.from_columns for data a reader/lens can produce, no per-message rr.log, no manual pa.array assembly. Source-specific knowledge lives in the importer skills (rerun-mcap, rerun-urdf, rerun-parquet, rerun-mp4, rerun-lerobot); read rerun-data-model first to decide what the data should become.

Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself.

Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions and drafts.

Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.

Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. Use when: building landing pages, marketing sites, product pages, dashboards, generating media assets (image/video/audio/music), writing conversion copy, creating generative art, or implementing cinematic scroll animations.

Bioinformatics with Biopython for sequence manipulation, file parsing, BLAST, and phylogenetics. Use when working with DNA/RNA/protein sequences or biological databases.

Security auditing for code, configs, and infrastructure. Use when the user wants to audit or improve security: scan for vulnerabilities (SQL injection, XSS, command injection, path traversal), detect hardcoded secrets and credentials, review auth and authorization, check dependencies for known CVEs, audit config files for insecure defaults, or generate security reports. Trigger on "security audit", "vulnerability scan", "code review for security", "find secrets", "check for vulnerabilities", "OWASP", "CVE", or questions about code security.

Use this skill when a task needs to run Lynx bundles with the node-lynx CLI, capture screenshots, open a macOS preview window, use DebugRouter OpenCard, inspect rendered content through CDP, or integrate node-lynx through JavaScript or TypeScript APIs.

Orchestrates comprehensive production readiness reviews and assessments for GKE clusters and workloads across scalability, security, reliability, observability, backup/DR, and cost optimization. Use when asked to productionize, prepare, assess, audit, or review a GKE cluster or workload before going live to production. Don't use for deep-dive single-domain implementation (use specific domain skills like gke-workload-scaling, gke-platform-security, gke-workload-security, gke-service-networking, gke-reliability instead).

CLI tool for creating, managing, and exporting AI-generated presentations via the Banana Slides API. Use when the user asks to: (1) generate a PPT/presentation/slides from an idea, outline, or description, (2) export a project to PPTX, PDF, or images, (3) batch-generate multiple presentations, (4) manage projects, pages, materials, or templates programmatically, (5) renovate/redesign an existing PPT or PDF, (6) edit slide images with natural language.

Use when asked to build, preview, or verify the Flet documentation website, including checking for broken links, broken images, and unresolved reST cross-references.

Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.

Use when creating, opening, or editing LibreOffice Impress ODP presentations, or PPTX decks only when PowerPoint compatibility is explicitly required.

Use for complex Agent Zero Browser form workflows involving selects, checkboxes, radios, file uploads, contenteditable fields, multi-step validation, or visually verified submission.

Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.