Skip to main content
NeVibeCode · 3,316 items

Codex skills, plugins, subagents, slash commands and mcp servers

Everything that installs into Codex: skills, plugins, subagents, slash commands and mcp servers. Each card has an install command and example prompts.

3,316 items
vector-cluster ruvnet skill Clusters code files with graph community detection. Use it to inspect related areas of a project and spot outliers. Claude Code Cursor GitHub Copilot 728installs migrate-validate ruvnet skill A skill that automatically validates pending database migrations for errors: broken foreign key references, incomplete rollbacks, naming violations. Catches issues before they reach the database. Claude Code Cursor GitHub Copilot 728installs iot-witness-verify ruvnet skill Verifies witness chain integrity for Cognitum Seed devices and detects provenance gaps. Useful for uncovering broken hash chains and missing epochs. Claude Code Cursor GitHub Copilot 728installs kg-traverse ruvnet skill Explores AgentDB knowledge graph relationships starting from a seed entity. It pinpoints dependency chains and indirect connections when analyzing code impact. Claude Code Cursor GitHub Copilot 727installs skillify Yeachan-Heo skill Converts a successful multi-step workflow from your current session into a reusable skill draft with YAML frontmatter. Claude Code Cursor GitHub Copilot 638installs computer-use-agents sickn33 skill Guides the architecture of AI agents that control screens, cursors, and keystrokes using Anthropic Computer Use or OpenAI Operator. Useful for sandboxed desktop and GUI automation. Claude Code Cursor GitHub Copilot 959installs voice-ai-development sickn33 skill This skill guides work on voice applications and real-time voice agents. Use it when a task involves speech recognition, speech synthesis, or streamed audio. Claude Code Cursor GitHub Copilot 959installs mermaid-to-proverif trailofbits skill Turns a Mermaid sequence diagram of a crypto protocol into a ProVerif model — a .pv file you can check for secrecy, authentication and forward secrecy. Claude Code Cursor GitHub Copilot 3,900installs graph-evolution trailofbits skill Compares Trailmark code graphs across two code snapshots to spot structural security changes. It catches attack path expansion and privilege shifts that text diffs overlook. Claude Code Cursor GitHub Copilot 3,900installs trailmark-structural trailofbits skill Builds a Trailmark graph for a target directory and reports complexity, taint, blast radius, privilege boundaries, and attack surface data. Claude Code Cursor GitHub Copilot 3,900installs audit-augmentation trailofbits skill Projects SARIF static analysis reports, weAudit notes, and binary graphs onto Trailmark code graphs. Useful when mapping vulnerabilities to call graphs and data taint paths. Claude Code Cursor GitHub Copilot 3,900installs libraries-dev Jakubantalik skill Selects and integrates Libraries.dev React UI effects for AI interfaces, covering loaders, voice glows, animated borders, and bot avatars. Claude Code Cursor GitHub Copilot 991installs cost-compact-context ruvnet skill A skill that wraps getTokenOptimizer().getCompactContext() for token cost analysis. Retrieves compacted context from ReasoningBank, reports tokens saved via bridge measurements, and exposes agent-booster availability. Claude Code Cursor GitHub Copilot 726installs agent-tool-builder sickn33 skill A skill for writing tool schemas an agent can actually use: JSON Schema, descriptions, validation, error paths. Useful when it keeps calling the wrong function. Claude Code Cursor GitHub Copilot 958installs plaid-fintech sickn33 skill Provides integration patterns for the Plaid API, covering Link tokens, ACH Auth, transaction sync, balance checks, and webhook handling. Claude Code Cursor GitHub Copilot 956installs vector-hyperbolic ruvnet skill Places hierarchical data in the Poincaré ball: radius from tree depth, direction from a text embedding. For dependency trees, ontologies, class hierarchies. Claude Code Cursor GitHub Copilot 724installs dialogue-systems gamedev-skills skill Guides the design of branching game dialogue, condition-gated choices, and the choice between Ink, Yarn Spinner, or a custom JSON runner. Claude Code Cursor GitHub Copilot 6,500installs convex-create-component convex skill A skill to design and build reusable Convex components with isolated tables and a clear API boundary. Useful when you need to extract backend logic into a self-contained module or package an integration that owns its own data. Claude Code Cursor GitHub Copilot 130,600installs browser-form-fill ruvnet skill Fills web forms using a structured JSON field map and saved selector templates. It automates data entry and form submission directly in browser sessions. Claude Code Cursor GitHub Copilot 717installs debug Yeachan-Heo skill Diagnoses broken OMC sessions, workflow failures, and repo state issues using traces and targeted reproduction. Claude Code Cursor GitHub Copilot 629installs ce-pov EveryInc skill Forms a grounded verdict on whether an external solution, document, or approach fits your project. Judges only by evidence from your codebase and constraints. Claude Code Cursor GitHub Copilot 1,000installs ce-promote EveryInc skill Drafts launch posts and changelog blurbs directly from git diffs or pull requests. Useful for engineers who want ready-to-use release copy without waiting on marketing. Claude Code Cursor GitHub Copilot 1,000installs quant-analyst sickn33 skill A quant skill for the agent: financial models, strategy backtests and risk metrics, built on pandas, numpy and scipy. Claude Code Cursor GitHub Copilot 942installs wp-block-themes WordPress skill Guides the agent through building WordPress block themes, editing theme.json, and organizing templates. Useful when styles fail to apply in the Site Editor. Claude Code Cursor GitHub Copilot 5,800installs create-game-assets gamedev-skills skill A skill that carries a game's art from style brief and asset manifest to alpha checks and contact sheets. Handy once sprites start drifting out of style. Claude Code Cursor GitHub Copilot 6,400installs router gamedev-skills skill Dispatches game development tasks to specialized skills by detecting the project engine and classifying gameplay or shipping workflows. Claude Code Cursor GitHub Copilot 6,400installs godot-ui-control gamedev-skills skill A Claude Code skill that teaches the agent to lay out Godot 4.7 HUDs and menus with Control nodes: anchors, containers, themes and focus. Claude Code Cursor GitHub Copilot 6,400installs solid vercel-labs skill Skill to render JSON-specs into reactive SolidJS components. Use it when building UI catalogs, wiring providers, or debugging Solid reactivity patterns. Claude Code Cursor GitHub Copilot 1,100installs redux vercel-labs skill A Redux adapter for json-render: it points the renderer at a store slice instead of its own state. Useful when app state already lives in Redux. Claude Code Cursor GitHub Copilot 1,100installs shadcn-svelte vercel-labs skill Pre-built definitions and implementations of 36 shadcn components for json-render apps. Built on Svelte 5 and Tailwind CSS. Claude Code Cursor GitHub Copilot 1,100installs agent-manager-skill sickn33 skill A procedure for driving several local CLI agents in tmux sessions: start, stop, tail logs, hand out tasks. Useful when work runs in parallel. Claude Code Cursor GitHub Copilot 932installs planning-with-files sickn33 skill Keeps task context in markdown files inside the project folder, turning disk storage into agent working memory. Useful for multi-step builds and research tasks. Claude Code Cursor GitHub Copilot 932installs remember Yeachan-Heo skill A skill to decide where discovered knowledge belongs: project memory for durable facts, notepad for short-lived context, docs for instructions. Keeps findings from getting lost in chat. Claude Code Cursor GitHub Copilot 617installs php-pro Seth Hobson subagent Writes idiomatic PHP 8+ code focused on low memory usage. Employs generators, SPL data structures, and native standard library features. Claude Code Cursor 2,019installs mantis-meta-agent official google skill A campaign supervisor for Mantis security review: it keeps the loop running pass after pass and holds state and snapshots. Built for reviews that run long unattended. Claude Code Cursor GitHub Copilot 1,500installs mantis-reflect official google skill Extracts insights, failures, and false assumptions from Mantis agent transcripts, appending them to workspace/learnings.jsonl. Claude Code Cursor GitHub Copilot 1,500installs mantis-pipeline-adapter official google skill A consulting skill that walks you through building your own deterministic harness for running Mantis skills. Claude Code Cursor GitHub Copilot 1,500installs mantis-patch official google skill Generates minimal security fixes in isolated environments, applies patches, and verifies them against reproduced vulnerability findings. Claude Code Cursor GitHub Copilot 1,500installs mantis-calibrate official google skill Turns confirmed findings into a final risk score from 1 to 10, weighing reproduction evidence against architectural impact. Runs at the end of the pipeline, before the report. Claude Code Cursor GitHub Copilot 1,500installs mantis-reproduce official google skill Generates and executes crash reproducers in isolated sandboxes to verify security flaws. It helps confirm findings before patching. Claude Code Cursor GitHub Copilot 1,500installs

2,841–2,880 of 3,316

More in NeVibeCode

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor