Capability
Calls outside services agent skills
Skills whose scripts or instructions call hosts outside your machine. Counted among the 742 skills with full pages, whose files the directory reads in full.
Highest-scoring with this capability: semgrep from trailofbits/skills (92/100), tao-run-deft-object-detection from NVIDIA/skills (92/100) and agent-ready from mblode/agent-skills (91/100).
- 71 listed skills
- 35 repositories
By category
Video, Image, Audio and Creative (20) · AI Agents and LLM Engineering (10) · DevOps and Cloud (6) · Productivity and Knowledge Work (6) · Documents and Office Files (6) · Developer Tools and Frameworks (5) · Science and Research (4) · Frontend and Design (4) · Testing and QA (3) · Security (3) · Marketing and SEO (2) · Data, Analytics and Databases (1) · Writing and Editing (1)
All 71 skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| ad-delayer 86/100 · B | Bria-AI/bria-skill | Turns a flat ad image back into editable layers, returning background, product shot, logo, headline, body copy, and CTA as separate assets. |
| ad-resize 86/100 · B | Bria-AI/bria-skill | Resizes a flat ad image into feed, story, and banner sizes, redoing the layout for each shape rather than cropping or stretching. |
| add-webmcp 83/100 · B | browserbase/skills | Analyzes an existing web application for safe user-visible capabilities, implements first-party WebMCP tools, and validates discovery and invocation with Stagehand. |
| agent-ready 91/100 · A | mblode/agent-skills | Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents hitting 404s on guessed URLs. |
| aig-scanner 82/100 · B | Tencent/AI-Infra-Guard | Runs AI security scans of infrastructure, AI tools and skills, and AI agents, and evaluates LLM jailbreak resistance with Tencent's AI-Infra-Guard. |
| anydesign 84/100 · B | avelikiy/great_cto | Analyzes images, websites, and Figma files to extract their design and generate a design.md with a token system, component inventory, and reconstruction notes. |
| atlassian 83/100 · B | sanjay3290/ai-skills | Manages Jira issues and Confluence wiki pages in Atlassian Cloud, including JQL and CQL searches, workflows, transitions, comments, and browsing spaces. |
| auteur 89/100 · B | agiwhitelist/auteur | Designs and builds complete web experiences, including landing pages, cinematic scroll-directed sites, and multi-screen products, as one consistent design system with generated assets. |
| automotive 82/100 · B | Bria-AI/bria-skill | Edits vehicle images of cars, trucks, SUVs, and motorcycles, including scenes, reflections, tire refinement, window and wheel segmentation, atmospheric effects, and lighting. |
| avoid-ai-writing 82/100 · B | conorbronsdon/avoid-ai-writing | Audits and rewrites content to remove AI writing patterns, and supports a detect-only mode. |
| aws-agentic-ai 83/100 · B | zxkane/aws-skills | Guides deploying and managing AI agents on AWS Bedrock AgentCore, covering Gateway, Runtime, Memory, Identity, Observability, Evaluations, MCP tool integration, and governance workflows. |
| azure-devops 83/100 · B | sanjay3290/ai-skills | Manages Azure DevOps projects, work items, repos, pull requests, pipelines, wikis, test plans, security alerts, variable groups, environments, branch policies, and attachments. |
| blog-audio 82/100 · B | infrasity-labs/dev-gtm-claude-skills | Generates MP3 audio narration of blog posts with Google Gemini text-to-speech, including summaries, full read-alouds, and two-speaker podcast mode, with HTML5 embed code. |
| blog-google 80/100 · B | infrasity-labs/dev-gtm-claude-skills | Connects blog performance work to Google APIs, covering PageSpeed Insights, Core Web Vitals, Search Console, URL Inspection, Indexing, GA4 organic traffic, and keyword research. |
| blog-notebooklm 82/100 · B | infrasity-labs/dev-gtm-claude-skills | Queries Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents, and manages the notebook library and Google authentication. |
| bria-ai 80/100 · B | Bria-AI/bria-skill | Generates images from text prompts, edits them with natural language, removes backgrounds for transparent PNGs, and creates product lifestyle shots through the Bria.ai API. |
| browser-to-api 80/100 · B | browserbase/skills | Turns a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a browser-trace capture, to discover endpoints from a browser session. |
| browser-trace 80/100 · B | browserbase/skills | Captures a DevTools-protocol trace of browser automation, including CDP events, screenshots, and DOM dumps, and splits it into per-page searchable buckets for debugging. |
| citation-management 89/100 · B | K-Dense-AI/claude-scientific-skills | Manages academic citations by searching OpenAlex, PubMed, and Google Scholar, extracting metadata, validating references, and generating formatted BibTeX entries. |
| cloud-trace-querying 89/100 · B | google/skills | Queries Cloud Trace spans, filters by latency or error status, correlates distributed traces with Cloud Logging, and diagnoses latency bottlenecks across Google Cloud services. |
| cookie-sync 80/100 · B | browserbase/skills | Syncs cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites as the user. |
| create-creator-takes-h3 77/100 · C | gooseworks-ai/goose-skills | Generates a continuous AI creator talking-to-camera video track from an approved script by planning takes and reusing the first take's voice. |
| create-image-fal 86/100 · B | gooseworks-ai/goose-skills | Generates or edits images with FAL image models such as nano-banana edit, gpt-image and flux, billed through the fal-proxy. |
| create-image-gpt-image-fal 83/100 · B | gooseworks-ai/goose-skills | Generates a single photoreal or designed image with OpenAI gpt-image through fal.ai, using the edit variant when a reference image is provided. |
| fal-redesign 73/100 · C | fal-ai-community/skills | Redesigns a coded website by screenshotting it, generating a reference image with fal.ai, and writing a Markdown build-spec with hard constraints and tokens.json. |
| frontend-slides 73/100 · C | zarazhangrui/frontend-slides | Creates animation-rich HTML presentations from scratch or by converting PowerPoint files, helping non-designers discover their aesthetic through visual exploration. |
| gif-sticker-maker 75/100 · C | MiniMax-AI/skills | Converts photos of people, pets, objects, or logos into four animated GIF stickers with captions, including cartoon and Funko Pop styles. |
| google-calendar 80/100 · B | sanjay3290/ai-skills | Manages Google Calendar by listing calendars, viewing events, creating, updating and deleting events, finding free time, and responding to meeting invitations. |
| google-cloud-filestore-auditing 89/100 · B | google/skills | Audits Filestore instances on Google Cloud for disaster recovery readiness, overly permissive NFS export rules, and reliability compliance with Physical Zone Isolation and Separation. |
| google-cloud-filestore-log-troubleshooting 90/100 · A | google/skills | Diagnoses and resolves Filestore client mount failures, EACCES permission errors, and ETIMEDOUT network timeouts on Google Cloud, including NFS mounts that hang or fail. |
| google-sheets 80/100 · B | sanjay3290/ai-skills | Reads and writes Google Sheets spreadsheets, including getting content, updating cells, appending rows, fetching ranges, searching for spreadsheets, and viewing metadata. |
| google-slides 80/100 · B | sanjay3290/ai-skills | Reads and writes Google Slides presentations, including getting text, finding and creating presentations, adding slides, and replacing text, with standalone OAuth authentication. |
| graphos-factory 79/100 · C | apollographql/skills | Builds and maintains an Apollo Connectors subgraph from a REST API in a git workspace, recording design decisions and verification evidence. |
| hand-drawn-diagrams 79/100 · C | muthuishere/hand-drawn-diagrams | Creates hand-drawn Excalidraw diagrams, flows, explainers, wireframes, and page mockups, defaulting to monochrome sketch output. |
| hf-cloud-sagemaker-production-defaults 80/100 · B | huggingface/skills | Creates SageMaker endpoints (real-time, scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default, using provided deploy scripts. |
| huggingface-tool-builder 83/100 · B | huggingface/skills | Builds reusable scripts that fetch, enrich, or process data from the Hugging Face API, especially when chaining API calls or automating repeated tasks. |
| image-utils 84/100 · B | Bria-AI/bria-skill | Manipulates images with Python Pillow, including resizing, cropping, compositing, format conversion, watermarks, brightness and contrast adjustments, and web optimization. |
| impeccable 86/100 · B | pbakaus/impeccable | Guides frontend and native interface design through focused playbooks for hierarchy, typography, accessibility, responsive layouts, motion and UX copy. |
| isaac-mission-control-showcase 81/100 · B | NVIDIA/skills | Runs and validates an end-to-end Mission Control showcase using a local Isaac Sim GUI and a simulated robot in a warehouse scenario. |
| kaggle 90/100 · A | shepsci/kaggle-skill | Handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup. |
| literature-review 89/100 · B | K-Dense-AI/claude-scientific-skills | Conducts systematic, scoping, and narrative literature reviews using sources such as PubMed, arXiv, and bioRxiv, tracking search coverage and evidence limitations. |
| llm-wiki 80/100 · B | praneybehl/llm-wiki-plugin | Builds and maintains an LLM-curated knowledge base as linked Markdown from papers, articles, and notes, and answers questions with citations. |
| mcp-builder 89/100 · B | anthropics/skills | Guides building MCP servers that let LLMs use external services through tools, in Python with FastMCP or TypeScript with the MCP SDK. |
| minimax-docx 76/100 · C | MiniMax-AI/skills | Creates, edits, and formats Word DOCX documents with the OpenXML SDK for .NET, including filling existing documents and applying templates with XSD validation. |
| minimax-pdf 73/100 · C | MiniMax-AI/skills | Creates PDFs from scratch, fills in PDF form fields, and reformats existing documents when visual quality and design identity matter. |
| naming 77/100 · C | glacierphonk/naming | Names products, SaaS, brands, open source projects, bots, and apps using a metaphor-driven process that produces memorable, meaningful names and avoids AI slop. |
| nano-banana-pro 70/100 · C | swarmclawai/swarmclaw | Generates or edits images with Gemini 3 Pro Image, supporting text-to-image generation, single-image editing, and composition of up to 14 images. |
| notebooklm 83/100 · B | sanjay3290/ai-skills | Queries and manages Google NotebookLM notebooks, including persistent profile authentication, source sync, batch queries, and structured exports. |
| onekgpd 87/100 · B | K-Dense-AI/claude-scientific-skills | Queries the 1000 Genomes Project dataset to find which individuals carry specific variants, return variants with allele frequencies, and check relatedness between individuals. |
| ontology-explorer 82/100 · B | HeshamFS/materials-simulation-skills | Parses, navigates, and queries materials science ontology structures, including class hierarchies, property definitions, term search, and OWL/XML summaries, currently for CMSO and ASMO. |
| openai-image-gen 73/100 · C | swarmclawai/swarmclaw | Generates images through the OpenAI Images API with GPT Image, DALL-E 3, or DALL-E 2, supporting batch generation and HTML gallery output. |
| optimize-agent-prompt 81/100 · B | browserbase/skills | Builds and improves Browserbase Agent API demos by running a fixed task, collecting logs, scoring results, revising one system-prompt heuristic, and confirming convergence. |
| physical-ai-defect-image-generation 79/100 · C | NVIDIA/skills | Orchestrates defect image generation with NVIDIA Cosmos AnomalyGen on OSMO for PCBA, metal surface, and glass inspection, including setup, finetuning checkpoints, and deployment configuration. |
| physical-ai-video-data-augmentation 83/100 · B | NVIDIA/skills | Runs video data augmentation and auto-labeling workflows on OSMO, covering flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. |
| playwright-skill 85/100 · B | lackeyjb/playwright-skill | Automates browsers with Playwright, auto-detecting dev servers and writing reusable test scripts for screenshots, responsive checks, UX validation, login flows, and link checks. |
| playwright-skill 86/100 · B | LambdaTest/agent-skills | Generates Playwright automation scripts and end-to-end tests in TypeScript, JavaScript, Python, Java, or C#, run locally or on TestMu AI cloud. |
| remove-background 86/100 · B | Bria-AI/bria-skill | Removes backgrounds from images to produce transparent PNGs, cutouts, and masks by segmenting foreground from background, using Bria RMBG 2.0. |
| render-chatgpt-chat 81/100 · B | gooseworks-ai/goose-skills | Assembles a ChatGPT chat-reveal video ad from thread and timeline JSON, using a recorded mobile chat and a designed end card. |
| render-proof-points-overlay 89/100 · B | gooseworks-ai/goose-skills | Builds proof-point pill overlays for a perfect-score UGC video ad and composites them onto a base clip, then adds the music bed. |
| render-whiteboard-explainer 81/100 · B | gooseworks-ai/goose-skills | Assembles a whiteboard explainer video ad from a beats file, with narration, a hand-lettered title, bulleted rows and traced drawings. |
| safe-browser 75/100 · C | browserbase/skills | Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access. |
| semgrep 92/100 · A | trailofbits/skills | Runs a Semgrep security scan over a codebase, detecting languages, selecting rulesets, requiring approval of the plan, and merging output to SARIF. |
| skill-scanner 88/100 · B | getsentry/skills | Scans agent skills for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks before installation. |
| slidewright 90/100 · A | tronghieu/agent-skills | Builds interactive presentation websites for slide decks projected to a room, including slide editing, deck restyling, phone remote control, and PDF export. |
| tao-run-deft-cr-its-mining 87/100 · B | NVIDIA/skills | Runs a mining-based DEFT improvement loop for ITS Cosmos-Reason binary video questions, focusing on classification and evaluation without reasoning, driven by gap analysis. |
| tao-run-deft-object-detection 92/100 · A | NVIDIA/skills | Runs the DEFT data augmentation loop for Grounding DINO object detection, with baseline inference, gap analysis, unique-neighbor mining, retraining, and source pool preparation. |
| venice-text-routing 80/100 · B | veniceai/skills | Routes a prompt to the right Venice text model based on privacy tier, modality, capability, uncensored needs, and cost, when a local agent escalates. |
| video-remove-background 86/100 · B | Bria-AI/bria-skill | Removes backgrounds from videos to produce transparent videos and alpha-channel clips without green-screen footage, using Bria's video editing pipeline. |
| vox-director 85/100 · B | Alisa0808/vox-director | Turns one topic into a Vox-style paper-collage explainer or ad video, automating script, motion, voice-over, music, and captions via Atlas Cloud and ffmpeg. |
| vss-deploy-detection-tracking-2d 90/100 · A | NVIDIA/skills | Deploys, runs, debugs, tears down, and calls the REST API of the RTVI-CV 2D detection and tracking microservice. |
| youtube-transcript 80/100 · B | tubeagentkit/youtube-transcript-skills | Fetches YouTube video transcripts through the metered getyoutubetranscript.com API, and also searches YouTube, resolves channel handles, lists playlist videos, and checks credit balance. |