Skills directory · page 31

Upgrade a live Hermes install and diagnose update drift: decide whether an update is worth a maintenance window, snapshot before mutation, run the official updater, and verify the runtime afterwards. Use for failed updates, stale unattended timers, dependency-sync gates, detached release checkouts, or post-update health checks. Not for model/provider configuration and not for editing the install's own source.

Design, implement, and refactor port-and-adapter systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services.

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. Use when introducing or refactoring toward Ports and Adapters, or when domain logic has become entangled with I/O.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingfa

Discover 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.

Set 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.

Plan 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.

Ensure 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.

Create 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.

Pick 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.

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

A HIPAA-specific entry point for healthcare privacy and security work. Use when a task explicitly concerns HIPAA, PHI handling, covered entities, BAAs, breach posture, or US healthcare compliance requirements.

HIPAA-specific entrypoint for healthcare privacy and security work. Use when a task is explicitly framed around HIPAA, PHI handling, covered entities, BAAs, breach posture, or US healthcare compliance requirements.

Baixa os encartes vigentes do Hiperideal (Salvador, BA) a partir do JSON embutido na página de encartes, rasterizando os PDFs. Use quando o usuário mencionar "baixar encartes Hiperideal", "encartes Hiperideal" ou colar a URL hiperideal.com.br/especial/encartes.

Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Use when delegating grunt work to free opencode workers instead of spending Claude tokens: one worker or a scout, coder and tester swarm in worktrees. Triggers on 'spawn a worker', 'swarm', 'delegate to opencode' or /oc.

Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification.

Produce an evidence-cited, cross-agent self-report with deterministic usage facets and a rigorously bounded blind-spot audit. Use only when explicitly asked for "my usage insights", "audit my work patterns", "where am I wasting effort", "blind spots", or a periodic "self-retro". Do not use for raw records or cross-agent search, a single-session summary, qualifying findings into approved assets (use hoa-introspect-distill), or direct skill creation (use hoa-skill-work). Heavyweight and explicit-invocation-only; never invoke as a side effect of another skill.

Qualify supplied repeatable-work findings into individually approved skill or opted-in rule/config candidates. Use when the user wants candidates assessed before choosing an asset, or approves one candidate from an hoa-introspect report. Use hoa-skill-work for direct creation or evolution of a defined skill; use hoa-introspect to discover work patterns in history.

Evidence-ranks skill behavior against its intended outcome and next consumer without changing the subject. Use when auditing a skill or reviewing a changed skill block. Use when candidate skill replies need judgment against task requirements. Use hoa-skill-work for requested skill creation or evolution; use hoa-introspect-distill for recurring-work candidates considered for distillation.

Build a complete skill around a defined capability, or evolve an existing skill from a concrete failure or improvement target. Use when the user asks to create or change a skill. Use hoa-skill-review for read-only audits and candidate-output judgments; use hoa-introspect-distill for recurring-work findings that need qualification and item approval, when available.

Load when a merged release must update a Homebrew tap and local installation

Readiness checklist for homelab VLAN segmentation, local DNS filtering (Pi-hole, AdGuard Home), and WireGuard-style remote access. Use when planning or reviewing home network changes — splitting a flat network into trusted, IoT, guest, or management VLANs, moving DHCP to a local resolver, or adding VPN access — before changing router, firewall, DHCP, or VPN configuration.

Practical home and homelab network planning for gateways, switches, access points, IP ranges, DHCP reservations, DNS, cabling, and common beginner mistakes. Use when planning or fixing a home or homelab network — gateway, switch, AP, IP ranges, DHCP, DNS, or cabling.

Pi-hole installation, blocklist management, DNS-over-HTTPS setup, DHCP integration, local DNS records, and troubleshooting broken DNS resolution on a home network. Use when the task explicitly involves Pi-hole — installing it, managing blocklists, configuring DoH or DHCP, adding local DNS records, or diagnosing DNS resolution with Pi-hole in the path.

Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and wireless SSID mapping. Use when splitting a home network into IoT, guest, trusted, and server VLANs on UniFi, pfSense/OPNsense, or MikroTik.

WireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a home network from mobile and laptop clients. Use when setting up WireGuard for remote access to a home network, or deciding between split and full tunnel routing.

Trace Paperclip runs, requests, and full CI suites in Honeycomb. Use to find traces, diagnose latency, design readable and foldable waterfalls, configure opt-in OpenTelemetry, or add missing spans.

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Create attention-grabbing hooks and headlines using 15 proven formulas, sticky techniques, and the 4 U's test. This skill provides systematic frameworks for generating volume (10+ options) and selecting the best performers. Use for newsletter subject lines, social media hooks, blog headlines, or any content that needs to stop the scroll.

Use this skill when the user asks to create hookify rules, write hook rules, configure hookify, add hookify rules, or needs guidance on hookify rule syntax and patterns.

Create and configure hookify rules — markdown files with YAML frontmatter that match bash, file, prompt, or stop events by regex or conditions and show warn/block messages to the agent. Use when creating a hookify rule, writing hook rule syntax, configuring hookify, or adding pattern guardrails such as blocking dangerous commands, .env edits, or debug code.

Writing style reference based on case studies of successful newsletters. This skill should be used when the user wants to write in the distinctive voice and style of professional newsletter writers, or when creating content that needs to feel authentic and human rather than AI-generated.

Build one self-contained HTML file — no build step, no dependencies, no CDN — to explain, plan, report, review, diagram, compare, or prototype something a human should read, share, or poke at. Use when the deliverable has color, layout, diagrams, tables, or interaction, or when the user asks for an artifact, explainer, plan write-up, diagram, or design variants. Not for markdown-shaped notes, brand-matching a known site's look, or generative canvas art.

This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks", "deface web applications", or "test content injection vulnerabilities". It provides comprehensive HTML injection attack techniques and testing methodologies.

Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out, or to save the current task's findings as an interactive HTML debrief/report.

Use for /hub-init, or to start an AgentHub competition: task, agent count and evaluation criteria.

Use for /hub-run, or to run a whole AgentHub competition end to end: init, baseline, spawn, eval and merge.

Use for /hub-status, or to check AgentHub agent progress, branches and DAG state.

Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs. Use when: hubspot, hubspot api, hubspot crm, hubspot integration, contacts api.

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.

Run 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.

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

Use 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.

Build 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.

Publish 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.

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.