Start with the job, then find an open-source answer

LLM SAST Skills turns a compatible coding assistant into a coordinated static-analysis workflow. It first maps the stack, architecture, entry points, data flows, and trust boundaries, then runs thirteen vulnerability-focused skills in parallel to discover and verify issues such as SQL injection, XSS, RCE, SSRF, authorization flaws, path traversal, unsafe uploads, and business-logic bugs. A final skill consolidates evidence, remediation guidance, and dynamic test instructions by severity. Existing CLAUDE.md or AGENTS.md files may conflict with its orchestrator.

Agentic SEO Skill routes website audits, technical SEO, content review, structured data, sitemaps, images, and GEO work to specialized skills and agents. Users can request a focused check or a full-site audit in natural language, while optional scripts collect page, crawl, performance, and metadata evidence for reports and prioritized action plans. It installs in native formats for Claude Code, Codex, Cursor, Windsurf, and several other agent environments; some collectors require Python packages or external services.

LibreCrawl is a browser-based SEO crawler that can run locally or as a multi-user service. It maps internal and external links, extracts page metadata and headings, detects issues, tracks progress, and exports CSV, JSON, or XML, with optional JavaScript rendering, PageSpeed data, and custom analysis plugins. Deployment requires Docker or Python, and large sites take time to complete; browser-based rendering is also slower than ordinary HTTP crawling.

SciWrite applies a systematic editorial process derived from Kristin Sainani’s Writing in the Sciences course to scientific and engineering manuscripts. It reviews issues such as clutter, passive or weak verbs, and sentence structure in sequential passes, then suggests clearer alternatives. The skill can be installed in Claude or adapted to other tools that accept reusable instructions.

hue is a design skill for Claude Code and Codex that analyzes a brand from a URL, name, or screenshot, then turns the findings into a reusable coding skill. The generated system defines color, typography, spacing, components, light and dark modes, and page composition so separate AI sessions can build more consistent interfaces. A validation script checks the result for broken token references, placeholders, contrast issues, and structural errors before it is used.

Tauri Specta keeps the boundary between a Rust backend and a Tauri frontend type-safe by generating bindings for commands instead of requiring duplicated interface definitions. Version 2 also supports generating event types, which helps applications keep emitted and consumed payloads aligned as the Rust code changes. Compatibility is deliberately strict: Specta v1 pairs with Tauri v1, while Specta v2 pairs with Tauri v2. The two cross-version combinations are not supported, so projects must select the matching release line before integrating it.

Harbour connects iOS, iPadOS, and macOS devices to multiple Portainer servers and endpoints. Users can inspect container health, environment values, mounts, networks, and logs, change container state, remove containers, and deploy or edit complete stacks. Widgets, Shortcuts, Handoff, Spotlight, and background notifications extend the Apple-platform workflow. A working Portainer installation is required, and creating or editing individual containers is not currently supported.

Pexo adds a multi-shot video workflow to Claude Code, Cursor, OpenClaw, and other compatible agents. It accepts text, images, webpages, scripts, or audio, then selects models, plans shots, creates assets, and assembles voiceover, music, subtitles, transitions, and lip sync into a finished video. The workflow requires a Pexo API key.

This collection provides domain-focused Claude skills for security, privacy, legal, and governance work across frameworks such as ISO 27001, SOC 2, GDPR, HIPAA, FedRAMP, PCI DSS, and the EU AI Act. The skills support gap assessments, first-draft policies, control narratives, evidence preparation, document review, and technical recommendations tied to specific regulatory requirements.

Lokus stores notes as standard Markdown files on the user's device and can open an existing folder or Obsidian vault. Beyond rich editing, it offers wiki links, graph and canvas views, database-style collections, templates, full-text search, plugins, and MCP integration while remaining usable offline; encrypted Supabase sync is optional. The current desktop release is still beta, and mobile applications and collaborative editing remain roadmap items.

VT Code is a Rust coding agent for long-running automation, available through an interactive TUI or headless commands and compatible with more than 21 cloud and local model providers. Restricted shell sandboxing, tool guardrails, and audit logs define its execution boundaries, while worktree isolation and Skills/MCP support extend workflows. Local inference through Ollama, LM Studio, and llama.cpp is still marked experimental.

Markpad is a lightweight Markdown viewer and editor for Windows, macOS, and Linux. It combines tabbed editing with split preview, syntax highlighting, a table of contents, Vim mode, and rendering for KaTeX equations and Mermaid diagrams. Documents can be exported to PDF or HTML, and the app states that it includes no telemetry. Installers and selected package-manager options are available.

Groq Code CLI is an open coding CLI designed as a compact, modifiable starting point rather than a feature-heavy framework. It keeps familiar terminal interactions, tools, and command structure while making it easier to add custom tools, slash commands, or UI changes. It runs on Groq models and requires a Groq API key.

Marketing Skills offers more than 160 Markdown-based playbooks for technical SEO, keyword research, page creation, paid ads, channels, launches, and analytics. You can install only the skills needed for a task in Cursor, Claude Code, OpenClaw, or other compatible agents. Tailored results depend on supplying project context such as the product, audience, brand, and target keywords.

Typstudio is an offline desktop editor for Typst documents, with syntax highlighting, compiler-error markers, autocomplete, real-time preview, and export. Development builds exist for Linux, macOS, and Windows, but there is no stable release. The maintainer says the project has not been actively maintained for about a year and may be archived, so it is better suited to experimentation than dependable daily use.

kicad-happy gives Claude Code, Codex, and other agents workflows for parsing KiCad projects, checking nets, voltages, layouts, signal integrity, and EMC risks, and preparing component, BOM, and fabrication work. SPICE analysis requires a compatible simulator such as ngspice, LTspice, or Xyce. Distributor lookups can use optional API keys and otherwise fall back to web search.

Open Science Desktop combines exploration, literature review, experiment code, notebooks, figures, reports, runs, and paper writing in one macOS, Windows, and Linux application. Each artifact can be traced back to its inputs, code, environment, model output, and conversation, while a bundled OpenCode sidecar keeps models, skills, and MCP connectors replaceable. Workspace data stays local by default, although selected content may still be sent to the model provider configured for a task.

Scarf is a native macOS client and iPhone companion for the Hermes AI agent. It provides multi-window, multi-server access to chat, sessions, memory, skills, MCP servers, scheduled jobs, settings, and runtime health, connecting either to a local Hermes installation or to remote hosts over SSH. Scarf is a management interface rather than a standalone agent runtime, so an existing Hermes environment is required. The iPhone companion reaches the same server over SSH and is currently distributed through TestFlight.