245 published skills · page 3 of 3
- ▌ Homework Notebook Review · practicalswan bundleReview homework notebooks for completeness, reproducibility, safe execution, and academic-integrity boundaries.
- ▌ Huggingface Local Models · practicalswan bundleUse to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
- ▌ Huggingface Tool Builder · practicalswan bundleUse this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
- ▌ Meta Pattern Recognition · practicalswan bundleSpot patterns appearing in 3+ domains to find universal principles
- ▌ Stitch Extract Design Md · practicalswan bundleExtract a Stitch-compatible DESIGN.md from frontend source code, stylesheets, Tailwind config, theme files, and component patterns.
- ▌ Hf Cloud Python Env Setup · practicalswan bundleSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
- ▌ Notebook Execution Safety · practicalswan bundleReview Jupyter notebooks for side effects, dependencies, and safe execution strategy before running or editing them.
- ▌ Remembering Conversations · practicalswan bundleSearch previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
- ▌ Resolving Merge Conflicts · practicalswan bundleUse when you need to resolve an in-progress git merge/rebase conflict.
- ▌ Voice Preserving Rewriter · practicalswan bundleUse when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.
- ▌ Accelerated Computing Cudf · practicalswan bundleOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
- ▌ Documentation Verification · practicalswan bundleValidate documentation before merging - check completeness, broken links, code example accuracy, and factual correctness. Use when reviewing docs for quality gates or running pre-merge doc validation.
- ▌ Huggingface Vision Trainer · practicalswan bundleTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
- ▌ Spreadsheet Formula Helper · practicalswan bundleWrite and debug spreadsheet formulas (Excel/Google Sheets), pivot tables, and array formulas; translate between dialects; use when users need working formulas with examples and edge-case checks.
- ▌ Stitch Extract Static HTML · practicalswan bundleCapture a self-contained static HTML snapshot from a running app or mock component so it can be reviewed or uploaded to Stitch.
- ▌ Tracing Knowledge Lineages · practicalswan bundleUnderstand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures
- ▌ Breaking Changes Management · practicalswan bundleManage breaking API changes, migration guides, deprecation notices, and semver versioning. Use when introducing breaking changes, writing migration paths, updating changelogs, or releasing major versions.
- ▌ Dispatching Parallel Agents · practicalswan bundleUse multiple Claude agents to investigate and fix independent problems concurrently
- ▌ Huggingface Community Evals · practicalswan bundleRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
- ▌ Huggingface Paper Publisher · practicalswan bundlePublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
- ▌ Stitch Manage Design System · practicalswan bundleCreate, list, and apply Stitch design systems from DESIGN.md using the verified Stitch MCP design-system tools and safe upload fallbacks.
- ▌ Stitch React Vite Dashboard · practicalswan bundleConvert approved Stitch exports into accessible React and Vite dashboards with DESIGN.md tokens, TanStack Query data boundaries, responsive layouts, and optional read-only Web3 integrations.
- ▌ Subagent Driven Development · practicalswan bundleExecute implementation plan by dispatching fresh subagent for each task, with code review between tasks
- ▌ Train Sentence Transformers · practicalswan bundleTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
- ▌ Excalidraw Diagram Generator · practicalswan bundleGenerate .excalidraw diagrams from natural language. Use when creating flowcharts, mind maps, system architecture diagrams, sequence diagrams, ER diagrams, network diagrams, or any visual process visualization.
- ▌ Infostealer Malware Detector · practicalswan bundleDetects and removes infostealer malware (credential stealers, data exfiltrators) via full-system file search, cryptographic hashing, and public threat-intelligence cross-checks (VirusTotal, MalwareBazaar). Primary method is always custom hash-based detection. Windows Defender (or any platform-native AV) is allowed **only when necessary** (e.g. inconclusive hashes or deep remediation) and **must never be the default option**. The agent must exhaust the custom workflow first. Works on Windows/macOS/Linux.
- ▌ Improve Codebase Architecture · practicalswan bundleScan a codebase for deepening opportunities, present them as a visual HTML report, then guide a user-directed decision loop for the selected candidate.
- ▌ Testing Skills With Subagents · practicalswan bundleRED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
- ▌ Competition Submission Checker · practicalswan bundleValidate GCI competition predictions and notebook outputs against expected schema, metric, and submission constraints.
- ▌ Deepstream Import Vision Model · practicalswan bundleNVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pipelines with export, TensorRT build, and benchmark steps.
- ▌ Finishing A Development Branch · practicalswan bundleComplete feature development with structured options for merge, PR, or cleanup
- ▌ Hf Cloud AWS Context Discovery · practicalswan bundleDiscover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
- ▌ Huggingface Lora Space Builder · practicalswan bundleBuild and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.
- ▌ Preserving Productive Tensions · practicalswan bundleRecognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution
- ▌ Verification Before Completion · practicalswan bundleRun verification commands and confirm output before claiming success
- ▌ Mongodb Atlas Stream Processing · practicalswan bundleManages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.
- ▌ Final Assignment Citation Review · practicalswan bundleReview final-assignment materials for requirements, citations, AI-use disclosure, and data-analysis completeness.
- ▌ Hf Cloud Sagemaker Iam Preflight · practicalswan bundleEnsure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
- ▌ Hf Cloud Serving Image Selection · practicalswan bundlePick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
- ▌ Step By Step Web Project Builder · practicalswan bundleActivate for building or scaffolding web apps when the user is learning (e.g., todo apps, portfolios, dashboards).
- ▌ Supabase Postgres Best Practices · practicalswan bundlePostgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.
- ▌ Mongodb Natural Language Querying · practicalswan bundleGenerate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with query syntax, or discusses finding/filtering/grouping MongoDB documents. Also use for translating SQL-like requests to MongoDB syntax. Does NOT handle Atlas Search ($search operator), vector/semantic search ($vectorSearch operator), fuzzy matching, autocomplete indexes, or relevance scoring - use search-and-ai for those. Does NOT analyze or optimize existing queries - use mongodb-query-optimizer for that. Does NOT handle aggregation pipelines that involve write operations. Requires MongoDB MCP server.
- ▌ Hf Cloud Sagemaker Deployment Planner · practicalswan bundlePlan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
- ▌ Hf Cloud Sagemaker Production Defaults · practicalswan bundleCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.
- ▌ Pulling Updates From Skills Repository · practicalswan bundleSync local skills repository with upstream changes from obra/superpowers-skills