Shape agent capabilities into your workflow.

Safe Solana Builder is an AI coding skill for Claude or Cursor that applies a security-first workflow before Solana code is written. It selects Anchor, native Rust, or Pinocchio, assesses risk, and applies rules for account validation, PDAs, CPIs, arithmetic, Token-2022, and related failure modes. Each request can produce a full project scaffold, compilable program, test file, and security checklist; security edge-case tests are scaffolded with TODO bodies, positioning the skill as a first hardening layer before audit.

FlowForge generates draw.io XML from a description or design document inside Claude Code. It can produce flowcharts, architecture views, comparisons, trees, timelines, and other structured diagrams using explicit coordinates and styles. The resulting files remain editable in draw.io desktop, diagrams.net, VS Code extensions, Confluence, and other compatible tools, with selectable layout patterns and visual themes.

Squid is a Claude Code plugin that turns a feature specification into a reviewed pull request through five specialized agents: product architecture, software engineering, testing, PR review, and on-call validation. It automates planning, worktree setup, per-task implementation, review, and CI while keeping two human gates for plan approval and final merge. The workflow is designed around one feature at a time.

Apple-Hig-Designer is a Claude Code skill for shaping web and mobile interfaces around Apple Human Interface Guidelines, including typography, system colors, an eight-point spacing grid, component patterns, animation, and accessibility. After installing it at user or project level, users can request Apple-style screens or blend HIG foundations with another visual direction. Bundled React examples, CSS design tokens, and reference material support generation, but it is not a standalone visual design application.

low-level-dev-skills is a catalog of agent skills for C and C++, Rust, Zig, GPU work, embedded systems, and Linux kernel or driver development. It covers compilers, build systems, debuggers, profilers, sanitizers, binary analysis, and related workflows. Users can install the full suite or select individual skills for Claude Code, Codex, Cursor, and many other coding agents.

Install this skill to give coding agents deeper ROS 2 guidance across workspace setup, QoS, lifecycle nodes, ros2_control, Nav2, MoveIt 2, real-time behavior, testing, and deployment. Detailed references load progressively, while bundled scripts can scaffold packages and perform limited validation. Claude Code can run some checks through hooks; other agents require manual commands. Jazzy and Humble are the safest targets, while Rolling carries additional compatibility caveats.

This local-first skill helps an agent lead a GA4 and Google Tag Manager project from site analysis through review and delivery. It groups pages by business purpose, drafts or audits an event schema, compares it with a live GTM setup, and can continue into generation, synchronization, and preview verification only within the requested scope. It supports generic sites and a separate Shopify path. Browser-backed steps use Playwright, GTM synchronization uses Google OAuth, and richer anonymous diagnostics remain opt-in beyond a limited startup signal.

AgentFigureGallery gives coding agents a real visual reference library instead of relying on prompt-only descriptions of scientific style. Search the browser gallery, mark examples as liked, rejected, or selected, and export those choices as a bundle for Claude Code, Codex, Cursor, or another agent to use while writing plotting code. An optional full-public pack contains 16,341 candidates across ten plot types, while a small built-in pack supports quick smoke tests. Included example workflows can export PNG, PDF, SVG, and combined previews.

Skill Optimizer separates the agent-skill lifecycle into three workflows. skill-miner examines agent history, memories, archives, and repeated tasks for evidence-backed candidates; skill-personalizer adapts skills to a user's phrasing, tools, paths, and verification habits; skill-generalizer removes private context for public distribution. It also audits undertriggering, noisy activation, unnecessary questions, conflicts, and token costs. A deterministic scanner supports session data from Codex, Claude Code, Gemini, and exported transcripts.

mermaid-skill turns descriptions of processes, API calls, data relationships, or timelines into version-control-friendly `.mmd` source. It chooses an appropriate diagram type, validates the syntax before export, and inspects the rendered image for clipped labels, excessive density, or poor orientation. More than eleven Mermaid formats are covered, with PNG, SVG, and PDF export through a local `mmdc` installation or the Kroki API.

Collect single-choice, multi-choice, and free-form questions from parallel AI agents in a separate terminal inbox, then route your answers back to the correct sessions. AUQ integrates through MCP, an OpenCode plugin, or Agent Skills and works over SSH with native notifications; Bun is recommended for its default terminal renderer.

This repository packages 20 modular Agent Skills for idiomatic Go development, distilled from Google, Effective Go, Uber, and community guidance. Coding agents can load procedures for code review, concurrency, context handling, errors, interfaces, naming, performance, testing, and related decisions, supported by 48 references and eight check scripts. The collection works across multiple coding tools through the common Agent Skills installation flow. Version-sensitive recommendations are tracked separately so users can check minimum Go releases and fallbacks.

Math Modeling Skills provides one skill for solving and another for paper writing across CUMCM and MCM/ICM problem types. It helps teams decompose a prompt, search literature, select models, use algorithm cookbooks and code templates, then move into abstracts, validation, figures, English polishing, and formatting checks. It is a structured competition workflow rather than a substitute for verifying the mathematics, code outputs, and final argument.

This skill turns a working prototype into a structured Figma review artifact. It creates a frame for each meaningful interaction state, maps elements to available design-system components, and adds flow arrows, conditions, edge cases, annotations, and optional Code Connect links. It requires Figma MCP tooling, and clients with limited tool support may produce a specification document instead of building the file directly.

Agentlas OS and its Hephaestus engine compile plain-language requests into portable agent or team packages with roles, tools, memory boundaries, permissions, routing, and verification contracts. Users can borrow public Hub specialists or store owned packages in a private Agent Cloud, while the chosen host executes them. Credentials, local files, and machine permissions stay local.

Octagon Skills provides agent workflows for financial statements, growth metrics, valuation, stock performance, market data, and broader company research. The skills are installed through npx, a Claude plugin, or manual copying, while live data access is supplied by the separate Octagon MCP service. Users therefore need to configure that MCP connection and an Octagon API key before the data-driven workflows can run as intended.

Open Record/Replay captures a demonstrated macOS workflow as structured mouse, keyboard, window, selection, and accessibility events. The resulting session can be validated and packaged as input for an agent to create a reusable skill, which is useful for cross-application tasks without a clean API. The project is alpha software, requires macOS permissions, and does not include screenshots in its current core recording path.

MapLibre Agent Skills gives coding assistants curated context for decisions that commonly go wrong in mapping projects. Current skills cover choosing tile sources, building serverless PMTiles workflows, and migrating Mapbox GL JS applications to MapLibre. They are plain Markdown files that can be installed together or individually with `npx skills`, or copied into an agent's project instructions; the repository supplies guidance rather than a map runtime.