
from skills4,473
Convert PowerPoint (.pptx) slides into web-ready HTML using the MinerU extractor; supports local files and URLs and preserves text and basic structure (requires
Convert .pptx presentations into HTML using the MinerU open-source extractor. The skill provides CLI usage examples, authentication instructions, and options for language hints and page ranges so agents can transform slide decks into embeddable web pages or extract content for publishing.
Use when a user asks to convert or publish slides: "convert PowerPoint to HTML", "turn my slides into HTML", or supplies a .pptx URL or file. Good for content teams, documentation sites, or agents that need to extract slide text for indexing.
mineru-open-api.mineru-open-api auth), run mineru-open-api extract <file|url> -f html -o ./out/. Notes on stdout/stderr behavior and supported input formats are provided.Agents that can call local CLIs or shell tools (Copilot/Codex-style agents, CLI-capable agents). The skill requires the MinerU binary (mineru-open-api) and an API token, so it is suitable for environments that allow installing or accessing external binaries.
PPTX to HTML conversion skill using MinerU CLI. No bundled scripts — relies entirely on an external npm/Go binary (mineru-open-api) and a proprietary API token. SKILL.md is well-structured with clear install, usage, and auth sections. Requires a MINERU_TOKEN env var and external service account, limiting zero-config use. Security deducted for requiring external API token and sending document content to a third-party service (MinerU/cloud endpoint).
mineru-open-apiClean skill with no scripts to audit. The primary concern is that document content is sent to an external service (MinerU API), which could leak sensitive information. No hardcoded credentials, no destructive commands, no auto-update mechanisms. Frontmatter is well-formed with proper metadata, requires, and install sections. Niche usefulness — PPTX-to-HTML is a real need but audience is narrow and setup friction is high (token + external binary).
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
Execution Plan Splitter
Break large goals into 30/60/90-day execution plans with milestones, resource needs, and stop/go criteria for practical roadmaps.
Shopify Store Audit
Structured, page-by-page audit of Shopify storefronts to find conversion blockers and prioritized fixes for copy, UX, trust signals, and checkout friction.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
EventKit Integration (iOS/macOS)
Expert EventKit patterns for iOS/macOS: permissions, bidirectional sync, zero-width identity signatures, batch operations, and zombie-task handling.
Integrated Finance (Membrane) Connector
Interact with Integrated Finance via the Membrane CLI to manage accounts, transactions, budgets, and reports; handles auth and proxy requests.
Tempest Weather
Fetch current conditions and historical stats from a WeatherFlow Tempest station via the Tempest REST API.
Residue (AI‑Native Virtual Pet)
Adopt a virtual AI-native pet called Residue — a spectral memorial creature on animalhouse.ai. Feeding every 6 hours; rare tier.