Skills

A skills library for CAD, robotics, and hardware design agents that enables AI coding agents to generate and preview 3D CAD geometry using build123d and OpenCascade, with export support for STEP, STL, and 3MF formats.

A lightweight AST-based semantic code search tool that reduces token usage by 70%, built on CocoIndex's Rust-based data transformation engine. Integrates with Claude Code, Codex, and Cursor via skill or MCP server, with zero-config setup.

Patterns for protecting patient and clinician data across HIPAA (US), DISHA (India), and GDPR (EU) — data classification (PHI vs PII), Row-Level Security policies, tamper-proof audit logs, encryption, and common leak vectors. Applies when building patient-record features, clinical APIs, or multi-tenant healthcare RLS.

Configures a `PreToolUse` hook in `.claude/settings.json` that inspects every Bash tool call and blocks `git` commands containing `--no-verify` or `--no-gpg-sign` by exiting with code 2. Prevents AI agents from bypassing pre-commit hooks, lint/test gates, and GPG signing policies.

Refactors and improves Terraform modules by analyzing code structure and suggesting modular, reusable code improvements

Transforms AI-generated text into natural, human-sounding writing while preserving meaning and intent.

Universal tool gateway for Starchild agents that fronts 1000+ external apps (Gmail, Slack, GitHub, Google Calendar, Notion, etc.) via the Composio Gateway (`composio-gateway.flycast`). The agent never touches `COMPOSIO_API_KEY` and never calls the Composio SDK directly — it just hits plain HTTP endpoints (`/internal/search`, tool schemas) over the Fly 6PN network, which authenticates automatically by IPv6.

Provides guidance for writing marimo notebooks in the correct Python file format, covering script mode detection, interactive vs. CLI usage, UI widget patterns, and best practices for keeping notebook cells simple.

Google Cloud Agent Platform skill for working with the Skill Registry API, enabling registration, discovery, and management of agent skills within Google's Agent Platform ecosystem.

An onchainos skill for AI coding assistants that provides DEX bridging, token swap, market data, wallet management, security scanning, and DeFi operations across 20+ blockchains using OKX API credentials.

An official Starchild skill focused on coding assistance, providing AI agents with structured guidance for software development tasks within the Starchild agent ecosystem.

A Claude Code plugin marketplace from Trail of Bits providing skills for AI-assisted security analysis, testing, and development workflows.

A skill from OpenReview, an open-source self-hosted AI code review bot that deploys to Vercel and provides on-demand PR reviews powered by Claude with sandboxed execution and inline suggestions.

A skill for automating web browser interactions using Puppeteer and Playwright via MCP tools, supporting page navigation, element clicking and typing, data extraction and scraping, screenshot capture, PDF generation, and multi-page workflow automation.

A skill from the Awesome GitHub Copilot collection that integrates FlowStudio and Power Automate as an MCP server for Copilot. Part of a community-curated repository of agents, skills, workflows, and plugins for enhancing GitHub Copilot.

Audits and remediates SEO across crawlability (`robots.txt`, canonicals, redirect chains), indexability (`hreflang`, sitemaps), Core Web Vitals targets (LCP < 2.5s, INP < 200ms, CLS < 0.1), structured data (`Article`, `Product`, `BreadcrumbList`, `FAQPage`), title/meta rules, and keyword-to-URL mapping. Outputs page-specific recommendations with severity tags rather than generic advice.

Skill for implementing clean architecture patterns, from a collection that covers microinteractions, clean code, lean UX, and software design philosophy.

Searches, reserves, inspects, and cancels KTX/Korail tickets via `korail2` plus a `scripts/ktx_booking.py` helper that reattaches the `x-dynapath-m-token`, `Sid`, and latest app version to bypass Korail's recent Dynapath anti-bot `MACRO ERROR`. Resolves credentials from env vars / agent secret vaults / `~/.config/k-skill/secrets.env` and stops before payment — automating purchase confirmation is explicitly out of scope.

EMR/EHR engineering patterns covering single-page encounter flow (complaint → exam → diagnosis → prescription), smart templates with red-flag alerts, medication safety, ICD-10/SNOMED search, lab-result reference-range highlighting, and tamper-proof audit trails. Every design decision is judged against "could this harm a patient?".

Turn Claude Code into a persistent, self-directing agent system using only native features (crons, dispatch, built-in memory) and MCP servers, replacing standalone frameworks like Hermes and AutoGPT. Use when the user wants continuous autonomous operation, scheduled tasks, computer use, or an assistant that remembers context across sessions.

Fetches design context, screenshots, and assets from Figma, translating Figma nodes into production-ready code with project-specific conventions.

Cross-stack source code asset audit across C/C++, Java/Android, iOS (Obj-C/Swift), and Web (TS/JS/Vue) that classifies every file, detects 50+ embedded third-party libraries with versions, and delivers four-level verdicts (Core Asset / Extract & Merge / Rebuild / Deprecate). Outputs interactive HTML reports and supports fast/standard/deep/full analysis depths plus monorepo hierarchical scans.

OpenCLI's adapter-creation skill — runs the full browser exploration workflow (`explore` → `synthesize` → `generate`), the 5-tier authentication strategy decision tree, and debugging guide so AI agents can build new OpenCLI adapters for any website.

PreToolUse-hook safety net that intercepts destructive Bash/Write/Edit operations (rm -rf, git push --force, DROP TABLE, kubectl delete, --no-verify, etc.) and optionally restricts edits to a specific directory tree. Three modes: Careful (warn on destructive commands), Freeze (lock edits to a dir), and Guard (both combined) for autonomous-agent safety.

Discover, evaluate, and pick healthy Laravel packages through the LaraPlugins.io MCP server — `SearchPluginTool` for keyword / health-score / Laravel / PHP / vendor filtering, and `GetPluginDetailsTool` for per-package metrics, README, and version history. Free, no API key required.

Extracts and analyzes competitors' ads from ad libraries like Facebook and LinkedIn, identifying successful messaging, problems highlighted, use cases targeted, and creative approaches that resonate.

A text-to-speech skill that converts text into speech using Kokoro or Noiz, supporting simple mode and timeline-aligned rendering workflows.

Parses SARIF (Static Analysis Results Interchange Format) files to process outputs from security scanners like CodeQL, Semgrep, and other static analysis tools

An official Starchild skill for managing wallet policies in AI agent interactions. Part of the Starchild official skills collection, installable via npx skills and compatible with the Starchild agent framework.

Professional DOCX document creation, editing, and formatting via the OpenXML SDK (.NET) with three pipelines — CREATE from scratch, FILL/EDIT existing content, and FORMAT-APPLY template styling with XSD validation. Runs via CLI (`dotnet run --project scripts/dotnet/MiniMaxAIDocx.Cli --`) or direct C# scripts against vetted Samples.