Loading...
Loading...
Found 541 Skills
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'deep research', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'.
Install and configure NVIDIA NemoClaw (sandboxed OpenClaw agent platform) on Linux. Handles cloudflared tunnels, Docker cgroup fixes, OpenShell, sandbox creation, remote access via Cloudflare Tunnel, and known bug workarounds. Triggers: "install nemoclaw", "setup nemoclaw", "nvidia nemoclaw", "openclaw setup", "nemoclaw on spark", "nemoclaw on dgx".
Use this skill when implementing game programming patterns - state machines for character/AI behavior, object pooling for performance-critical spawning, event systems for decoupled game communication, or the command pattern for input handling, undo/redo, and replays. Triggers on game architecture, game loop design, entity management, finite state machines, object pools, observer/event bus, command queues, and gameplay programming patterns.
Use this skill when architecting on Google Cloud Platform, selecting GCP services, or implementing data and compute solutions. Triggers on Cloud Run, BigQuery, Pub/Sub, GKE, Cloud Functions, Cloud Storage, Firestore, Spanner, Cloud SQL, IAM, VPC, and any task requiring GCP architecture decisions or service selection.
Use this skill when optimizing email deliverability, sender reputation, or authentication. Triggers on SPF record setup, DKIM signing configuration, DMARC policy deployment, IP warm-up planning, bounce handling strategy, sender reputation monitoring, inbox placement troubleshooting, email infrastructure hardening, DNS TXT record configuration for email, and diagnosing why emails land in spam. Acts as a senior email infrastructure advisor for engineers and marketers managing transactional or marketing email.
P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].
Use when building or revising a PPT/演示文稿 in a portable, self-contained workflow folder, especially when the job spans storyline design, page briefs, page-level text compression, fixed-text image prompts, style-selectable slide image generation, sample-pack generation, page repair, and PPTX packaging without depending on repo files outside this skill folder.
Teaches AI to design landing pages that feel like $150k agency work. Defines exact fonts, spacing, shadows, card structures, animations, and Korean typography standards that make Supanova-generated pages feel expensive and intentional. Blocks all common defaults that make AI designs look cheap or generic.
This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities. Use this skill for probabilistic modeling, batch correction, dimensionality reduction, differential expression, cell type annotation, multimodal integration, and spatial analysis tasks.
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Design and implement multi-cloud strategies spanning AWS, Azure, and GCP with vendor lock-in avoidance, hybrid deployments, and federation.