All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,018 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.
Skill Claude CodeCodex
Generate Amazon and cross-border ecommerce product images from a product business card. Use when the user asks for a white-background image, showcase image, selling-point image, hero image, detail image, lifestyle image, one or more ecommerce images, or a complete image set. Always collect the business card first…
Skill Claude CodeCodex needs its repo
Produces sideshow release/feature videos by driving the real viewer in a recording Chromium against a live server — 1920x1080 stage with window chrome, captions, and title cards, encoded with ffmpeg. Use for release roundups, single-feature demos, PR walkthroughs, and social announcements.
Skill Claude CodeCodex
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
Skill Claude CodeCodex
Internal sub-procedure (not a standalone entry point) — the shared footage-analysis pipeline that produces audio transcripts, contact sheets, and Sonnet-written summaries. Invoked end-to-end by the process-library and reprocess-with-contact-sheets skills; don't trigger it on its own.
Skill Claude Code
Thorough, user-invoked tech debt and architecture audit of the current codebase. Produces TECHDEBTAUDIT.md with file-cited findings, severity, effort estimates, and a required "looks bad but is actually fine" section. Use when the user asks for a debt audit, codebase health check, architecture review, or code quality…
Plugin Claude Code
Bundles 1 skill, 9 commands, 2 hooks · 691 tokens together
Cyber threat intelligence and OSINT toolkit — structured investigations with sourced, trust-scored findings. Bundles the skill, the /cti command set, the typed intel MCP surface, and the RULE 1 / outbound-action safety hooks as one installable unit.
Skill Claude CodeCodex
A planning guide for Cyrene’s Plan Mode, used before code or file changes are made. It helps turn a broad request into an agreed implementation plan based on the project’s actual code and constraints.
emersonfelipesp/netbox-proxbox
Command Claude Code
This directory contains Django management commands for the ProxBox plugin.
op7418/Document-illustrator-skill
Skill Claude Code
A tool that reads a document, identifies its main topics, and generates matching illustrations. It supports Markdown, plain text, PDFs, and other document formats.
Agent Claude Code
Senior advisor for hard problems. Consult when stuck on architecture decisions, ambiguous tradeoffs, or when an approach isn't working. Returns guidance, not implementation.
Skill Claude CodeCodex
Joyride core — REPL evaluation, async patterns, VS Code API access, Flares, JS interop, and available libraries. Use when: working with Joyride evaluation, writing ClojureScript in any Joyride context, creating Flares/WebViews, exploring VS Code APIs via the REPL, or using joyrideevaluatecode.
Skill Claude Code
A skill that reviews remembered feedback about marketplace skills against the current files. It checks whether past problems still exist and updates either the skill or the stored memory.
Skill Claude Code
Share the current session and a share-ready Summary to the Spool hub via the spool CLI ("share to spool", "publish this session", withdraw a share, or a pasted spool session link) — and recall past AI sessions from inside any agent by searching all Claude Code, Codex, Gemini CLI, OpenCode, and Pi history when the user…
Skill Claude CodeCodex
Maintain a per-repo napkin as a continuously curated runbook (not a session log). Activates EVERY session. Read and curate it before work, keep only recurring high-value guidance, organize by priority-sorted categories, and cap each category at top 10 items. The napkin lives at .claude/napkin.md.
Skill Claude CodeCodex
DEPRECATED - this skill is unmaintained. Use the official Angular skills at https://github.com/angular/skills instead. Create modern Angular standalone components following v20+ best practices. Use for building UI components with signal-based inputs/outputs, OnPush change detection, host bindings, content projection…
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "moose-dev", hosted remotely at localhost, as configured in 514-labs/moosestack.
Skill Claude CodeCodex
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…
Skill Claude CodeCodex
Peter Lynch AI — GARP / PEG, consumer growth, everyday observations.
Skill Claude CodeCodex
Guide an AI assistant through this repo's 2D animation sprite-sheet workflow. Use when creating animation-safe character image prompts, writing image-to-video prompts, extracting frames from animation videos, matting backgrounds, building and validating horizontal 256 x 256 sprite sheets, promoting final outputs, or…
Command Claude Code
Automated multi-agent development workflow with quality gates from idea to production code.
Skill Codex
Route Grace repository work to current workflow, domain, contract, runtime, testing, and documentation guidance.
Skill Claude CodeCodex
Queries HuskarUI metadata with Python and guides HuskarUI-first QML/C++ code. Invoke when choosing components, checking examples, or generating HuskarUI UI.
Skill Claude CodeCodex
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
Plugin Claude Code
Bundles 8 skills · 493 tokens together
Skills for building LLM evals. Starts with interactive error discovery: build a review app, sample diverse traces, and organize human annotations into failure modes.
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: