All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 433,274 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Command Claude Code
A command that finds missing or unclear decisions in a feature specification by asking focused questions and recording the answers in the specification.
Skill Claude CodeCodex
Guide Claude to use SigCLI correctly — check auth, login, get credentials, configure providers, and onboard new websites. Trigger when using sig commands, editing /.sig/config.yaml, or needing authenticated API access.
Dicklesworthstone/misc_coding_agent_tips_and_scripts
Skill Claude CodeCodex
Encrypt, submit, scan, and decrypt age-encrypted GitHub Issues (X25519). Use when reporting vulnerabilities, scanning for encrypted issues, or decrypting security reports.
Skill Claude CodeCodex
Common software architecture patterns, ADR templates, and anti-pattern detection. Supports architectural review, design decisions, and system documentation.
Skill Claude Code
Meta Ads (Facebook/Instagram) management skill for B2B campaigns. Covers audience strategy, campaign structure, creative testing, and lead form optimization specifically for B2B SaaS on Meta's platform. MANDATORY TRIGGERS: Meta Ads, Facebook Ads, Instagram Ads, Facebook campaign, Meta campaign, Facebook advertising…
Skill Claude CodeCodex
Ground a database schema change in this application's real structure using Laravel Truss. Use when adding or altering tables, columns, indexes, or foreign keys, when a migration needs to match what is already there, or when you need to know what a migration actually changed. Structure only, never data.
Skill Claude CodeCodex
A tool for creating and publishing Chinese-language articles to WeChat Official Accounts, a platform for businesses and creators.
Skill Codex
A tool for creating AI-tool tutorial video covers for Xiaohongshu and Bilibili, two Chinese social-video platforms. It supports script-based and agent-directed creation, with output for three aspect ratios and an optional creator avatar.
xiaoyuboi/cloudflare-tunnel-skill
Skill Codex
Use when a user wants to expose a local HTTP/HTTPS service to the public internet with Cloudflare Tunnel. Supports temporary Quick Tunnel URLs for previews and named tunnels with fixed custom domains for stable public mapping.
Skill Codex
Use when Codex needs to coordinate ChatGPT, Chrome, Cloudflare tunnels, verified bridge Restart/Reboot recovery, or task routing between local code execution and ChatGPT reasoning/review. Handles the bridge controller and scheduled task, start/off/status/doctor/rotate flows, Worker KV refresh, ChatGPT app setup…
MCP server Claude CodeCodexCursor +2
MCP server "larkx" as configured in cv-cat/LarkAgentX. Runs locally from the larkx Python package.
Cursor rule Cursor
Go project rules covering code style, error handling, concurrency, performance, structure, and allowed Git commands.
Skill Claude CodeCodex
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
Skill Claude CodeCodex
A production workflow for making hand-drawn whiteboard explainer videos with animated drawings, voice-over, subtitles, cover images, and publishing text.
Cursor rule Cursor
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
Skill Claude CodeCodex
Apply Buddhist epistemic and decision-making principles as practical work disciplines to improve reasoning quality, anti-hallucination, debugging discipline, and steadiness under pressure. Use this skill whenever the user asks to "think more carefully," verify claims, debug a stubborn problem, decide between a hack…
MCP server Claude CodeCodexCursor +2
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links. Runs locally from the google-surf-mcp npm package. Needs 29 environment variables to run.
Skill Claude CodeCodex
General-purpose Static Application Security Testing (SAST) skill for code vulnerability analysis. Trigger when the user asks to: "analyze code for vulnerabilities", "review code security", "find security bugs", "do a SAST scan", "check for [vulnerability type] in code", "audit source code", or requests a security code…
Skill Codex
Design, implement, audit, or refactor web and game-adjacent interfaces using an evidence-based Hypergryph visual language with two independent choices: product family and application depth (1 minimal, 2 moderate, 3 complex, 4 maximal). Use for Hypergryph-, Arknights-, Endfield-, Rhodes Island-, industrial sci-fi-…
Plugin Claude Code
Bundles 3 skills · 247 tokens together
Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.
MCP server Claude CodeCodexCursor +2
Apache-2.0 read-only Model Context Protocol (MCP) server for GeoLens. Lets coding agents discover datasets, inspect schemas, and ask spatial questions against any GeoLens instance. Runs locally from the geolens-mcp Python package. Needs 3 environment variables to run.
Skill Codex
A graphics tool that redraws an image as a black-background pixel artwork using flowing particles or ordered dot patterns. It can produce a still PNG image and a looping GIF or MP4 animation.
Skill Claude CodeCodex
The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subjectdefinitions, summary, retentionanalysis, detaileddescription, overallsoundscape, nondiegeticmusic - with / / / roles, the retention vocabulary, summary task types, how the node's image1..image9 sockets…
Skill Claude CodeCodex
Show side-by-side visual options (UI mockups, architecture diagrams, code patterns, images) in a deck and collect the user's picks with designdeck. Use for decisions that are easier to see than read, including plan/PRD reviews and generate-more requests from an open deck. Text-only choices go to interview.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: