NeVibeCode · 3,286 items
GitHub Copilot skills, plugins, subagents, slash commands and mcp servers
Everything that installs into GitHub Copilot: skills, plugins, subagents, slash commands and mcp servers. Each card has an install command and example prompts.
context-compression skill A skill for managing context compression when agent sessions exceed token limits. Instead of naive truncation, it maintains structured summaries with file inventory, decisions, and state.
Claude Code CX Codex Cursor
1,400installs
test-driven-development skill Guides coding agents through a strict test-driven development workflow: red, green, and refactor. Useful when fixing bugs or implementing new features with regression checks.
Claude Code CX Codex Cursor
1,400installs
security-auditor skill Turns your AI coder into a security expert: conducts audits, analyzes vulnerabilities, reviews SDLC and compliance with OWASP, GDPR, PCI-DSS standards.
Claude Code CX Codex Cursor
1,400installs
organization-best-practices skill Sets up multi-tenant organizations, invitations, and permissions in Better Auth. Helps manage teams and custom RBAC rules without digging through documentation.
Claude Code CX Codex Cursor
36,400installs
cli-anything-obsidian skill Manage an Obsidian vault from the terminal: read, create, search, and update notes or run editor commands. It suits agents that need to work without the GUI.
Claude Code CX Codex Cursor
917installs
resource-curator skill Audits, discovers, and organizes external learning resources for JavaScript concept documentation. It weeds out broken links and obsolete syntax.
Claude Code CX Codex Cursor
319installs
scale-and-responsive skill A skill to set up responsive scaling for Phaser 4 games: choose a scale mode, center the canvas, enable fullscreen, and handle window resize events.
Claude Code CX Codex Cursor
910installs
game-feel skill Teaches the agent to add feedback to game actions: camera shake, hit-stop, eased tweens, squash and stretch, knockback. For mechanics that work but feel weightless.
Claude Code CX Codex Cursor
9,400installs
landing-page-design skill Complete system for landing pages: intake, structure, copywriting, visual rules. Consult before choosing fonts, spacing, colors, or writing headlines.
Claude Code CX Codex Cursor
1,700installs
write-docs skill Skill for writing and updating tldraw SDK documentation. Guides you through creating articles, updating existing docs, and following the project's style.
Claude Code CX Codex Cursor
486installs
loading-assets skill This skill guides Phaser 4 asset loading through the Loader plugin. Use it when working with preload(), spritesheets, audio, tilemaps, or load progress.
Claude Code CX Codex Cursor
901installs
kumo-design skill Cloudflare product design rules for coding agents: guides layout, typography, dialogs, and animations in Kumo UI dashboards.
Claude Code CX Codex Cursor
1,500installs
token-integration-analyzer skill Checks ERC20 and ERC721 implementations plus code that integrates external tokens. Use it before accepting tokens with non-standard transfer or approval behaviour.
Claude Code CX Codex Cursor
5,500installs
tweens skill Teaches coding agents how to animate properties in Phaser 4 using TweenManager, tween chains, stagger offsets, and number counters.
Claude Code CX Codex Cursor
891installs
improve-claude-md skill Rewrites your CLAUDE.md file using <important if="condition"> XML blocks. It keeps Claude Code focused on relevant rules without dropping project guidelines.
Claude Code CX Codex Cursor
2,500installs
intended-vs-implemented skill Audits the gap between documented architecture and actual code boundaries. Catches missed permission checks and untrusted data exposure in AI-built codebases.
Claude Code CX Codex Cursor
1,800installs
game-ui-ux skill Engine-neutral game UI architecture skill for responsive layouts, screen stacks, gamepad focus, and event-driven HUD updates.
Claude Code CX Codex Cursor
9,200installs
codex-delegate skill Hands a bounded coding task to the OpenAI Codex CLI and leaves you the diff and the commit. Useful when Codex does the typing and you do the review.
Claude Code CX Codex Cursor
7,700installs
fix-merge-conflicts skill Resolves merge conflicts in a branch, then checks the build and tests before wrapping up. Use it when several conflicted files need focused fixes without a refactor.
Claude Code CX Codex Cursor
2,700installs
thermo-nuclear-review skill A skill for comprehensive analysis of branch changes: checks code for bugs, broken functionality, security vulnerabilities, and feature-gate leaks. Use when you need thorough review before merge.
Claude Code CX Codex Cursor
2,700installs
azure-text-to-speech skill Synthesizes neural voiceover audio using the Azure AI Speech REST API. Ideal for OpenMontage pipelines that need multilingual narration voices.
Claude Code CX Codex Cursor
589installs
visual-verdict skill A visual QA skill that compares generated UI screenshots against reference images and returns a structured JSON verdict for layout iterations.
Claude Code CX Codex Cursor
890installs
learn-reverse-engineering skill Interactive tutor for reading compiled programs. One lesson per invocation: from file formats and disassembly to symbolic execution and AI-assisted analysis. Requires Python 3.10+ and your own source code.
Claude Code CX Codex Cursor
425installs
tavily-best-practices skill This skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system.
Claude Code CX Codex Cursor
20,600installs
write-concept skill Creates and reviews JavaScript concept pages for 33 JavaScript Concepts. Use it when adding, rewriting, or checking material in /docs/concepts/.
Claude Code CX Codex Cursor
305installs
cargo-fuzz skill Sets up cargo-fuzz inside a Cargo-based Rust crate and walks through the harness, sanitizers and crash triage.
Claude Code CX Codex Cursor
5,400installs
guidelines-advisor skill Audits smart contract codebases against Trail of Bits guidelines. It spots upgradeability pitfalls, flawed inheritance, and testing gaps.
Claude Code CX Codex Cursor
5,400installs
coverage-analysis skill Measures code reached by a fuzzing campaign and helps explain stalled path discovery. Use it to inspect harness changes, corpus results, and unreachable branches.
Claude Code CX Codex Cursor
5,400installs
clean-user-facing-text skill Cleans reader-facing prose by auditing invisible Unicode and smoothing repetitive AI cadences. Keeps code, facts, and author voice intact.
Claude Code CX Codex Cursor
439installs
pr-review skill Two-phase pull request review for skill repositories, combining automated schema checks with content audits.
Claude Code CX Codex Cursor
1,800installs
react19-concurrent-patterns
official skill Preserves React 18 concurrent patterns during React 19 migrations and guides the adoption of use(), useOptimistic, and Actions.
1,100installs
mcp-security-audit
official skill Audits MCP server configurations for exposed secrets, shell injection, mutable package references, and unapproved servers. Use it before changing .mcp.json.
1,100installs
lsp-setup
official skill Installs a language server and configures LSP for Copilot CLI. Use it when you need code navigation such as go-to-definition or find-references.
1,100installs
integrate-context-matic
official skill This skill finds third-party APIs and helps integrate their SDKs through the context-matic MCP server. Use it for external API work.
1,100installs
arize-trace
official skill Export Arize traces and spans by ID, then inspect them to investigate errors or LLM app behavior. Use it when you need to examine trace data already collected.
1,100installs
arize-prompt-optimization
official skill This skill analyzes prompts through production traces, evaluations, and annotations. Use it when you need better model responses or want to debug a system prompt.
1,100installs
arize-instrumentation
official skill This skill helps add Arize AX tracing to an LLM application. The agent inspects the project first, then proposes instrumentation for approval.
1,100installs
arize-experiment
official skill Runs Arize experiments with the ax CLI to benchmark models and export evaluation scores across dataset versions.
1,100installs
arize-evaluator
official skill Runs LLM-as-judge workflows in Arize for spans and experiments, with evaluator management, task control, column mapping, and continuous monitoring.
1,100installs
arize-dataset
official skill This skill manages Arize datasets and examples through ax. Use it for test sets, evaluation examples, and dataset exports.
1,100installs
2,441–2,480 of 3,286