Find the open-source solution that fits.

Use this skill when extending WooCommerce through Claude Code. It covers custom product types, payment gateways, shipping methods, HPOS, REST API extensions, cart and checkout customization, and Blocks integration, and can activate automatically for relevant WordPress work or be invoked directly.

Build a persistent technical knowledge base that can tag, search, compare, clone, and track changes across saved GitHub repositories. The skill also manages PDFs with token estimates and structured summaries for repeated reference, and requires Python, Git, and internet access for repository operations.

This OpenClaw skill queries Google through the Serper API, then fetches result pages concurrently and extracts article text with trafilatura instead of returning snippets alone. It offers general and recent-news modes plus locale controls, requires a Serper API key and Python dependency, and falls back to snippets when a page cannot be extracted.

This collection provides four Claude Code skills for Adobe analytics work: conceptual guidance for Adobe Analytics and Customer Journey Analytics, server-to-server OAuth setup for AEP and CJA APIs, and SDR generation with Data View comparison and configuration tracking. Skills can be installed individually or copied together.

This skill connects Claude Code, Codex CLI, Gemini CLI, and other skill-aware assistants to the VAP Media API. Users can request image, video, or music generation as well as media editing or enhancement, then receive the resulting media URL; authenticated use requires a VAP product key.

VAP Media Skill lets compatible AI assistants start image, video, and music generation through one API, poll jobs for results, and run media editing or enhancement operations. It can be installed for Claude Code, Codex CLI, or Gemini CLI, but service calls require a VAP Media API product key.

Naze combines UI structure, state, and interactions in a declarative language that compiles to WebAssembly and renders through Canvas2D rather than the DOM. Its toolchain includes compilation, type checking, testing, examples, and project-context export for AI agents, but the project is still experimental and explicitly not ready for production use.

generate-presentation teaches Claude to choose a deck-level narrative such as the Pyramid Principle, SCQA, AIDA, or a problem-solving flow, then compose individual slides with reusable patterns. The guided process collects the topic, audience, and tone before producing a Markdown outline that can be moved into PowerPoint, Keynote, Gamma, or another presentation tool. It is a skill specification, not a standalone slide-rendering application.

Next-Unicorn scans a codebase for custom implementations that could be replaced by maintained libraries, while also surfacing missing engineering capabilities. The AI agent supplies candidate recommendations rather than relying on a hardcoded package list, and Context7 documentation is used to verify replacements and gaps. The result can include a migration plan, risks, ecosystem dependencies, and a checklist of code that can be removed.

LLM Translator connects to OpenAI-compatible services or local endpoints such as Ollama, LM Studio, and vLLM to translate individual text, files, or batches of documents. Its scripts can preserve formats including Markdown, HTML, and subtitles, with model settings supplied through a config file, environment variables, or command-line options. Hosted providers require your own credentials and may impose cost and rate limits.

This skill uses AppleScript to control a logged-in Chrome session on macOS, retrieve DEV.to's CSRF token, and submit a Markdown article through the site's internal article endpoint. It avoids manipulating the React editor and returns the published URL after submission. Chrome must allow JavaScript from Apple Events, tags are limited to four lowercase values, and an article body should not begin with a YAML-style delimiter.

Skill Security Auditor checks skill files and MCP servers for dangerous commands, prompt injection, credential access, risky tool combinations, supply-chain issues, and MCP-specific flaws such as SSRF or path traversal. It produces a heuristic risk score and report, but its static analysis can miss sophisticated behavior and should be paired with expert inspection.

code-surgeon offers four Claude Code modes for discovery, change review, optimization, and implementation planning. It selects relevant files, maps architecture, identifies likely breakage or bottlenecks, and turns larger work into testable steps. The recommendations are guidance rather than a substitute for developer judgment and testing.

Evidentia extracts DOI, PMID, arXiv, and NCT identifiers from medical writing and checks them against services including CrossRef, PubMed, OpenAlex, arXiv, and ClinicalTrials.gov. The CLI and MCP server classify citations as verified, bibliographically mismatched, hallucinated, or needing content review; the Claude Code skill adds a 15-criterion appraisal of how evidence is used. It is for writers, editors, and researchers, not clinical decision support.

Arcana installs a large library of coding skills and curates which ones enter an agent's active context based on the project, past usage, and a configurable token budget. Its CLI also compresses noisy command output, stores cross-session memories and snapshots, and manages selected MCP servers. It is aimed at developers working across tools such as Claude Code, Codex, Cursor, Gemini, and Aider who want useful context without loading every skill at once.

HBR-Style Visualization provides Claude with design rules, prompt templates, and a quality checklist for flywheels, maturity models, annotated charts, and 2×2 strategy matrices. It centers each graphic on a clear argument and uses restrained color, serif typography, and clean layouts for executive presentations, research figures, and business reports.

Indic Voice Pipeline combines yt-dlp with fine-tuned Whisper models and Qwen3-ASR to process audio or video in 12 Indian languages and export text, subtitles, and structured JSON. Optional pyannote diarization adds speaker labels and requires a Hugging Face token. Transcription runs locally, though model downloads and hardware demands can be substantial.

Provide an address and either plain text or a PDF, and the skill previews the page count and price before submitting the job to Mailclaw. It then returns a Solana USDC payment address, after which the letter is printed, placed in a hand-addressed envelope, photographed, and mailed through USPS. First Class, certified, return-receipt, and international tiers are available.