All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 433,670 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 ✓ vendor
Format automated Next.js release, backport, and canary measurements for team-adx-science. Highlight regressions and evals to investigate, with full results in a thread.
Skill Codex
Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 12 skills · 264 tokens together
Readwise and Reader for Claude Code — MCP server + agent skills. Triage your inbox, catch up on feeds, quiz yourself on what you've read, and more.
Skill Claude Code
An authorized red-team framework for testing systems through stated assumptions. Red teaming is a permitted security exercise that imitates attacks to find weaknesses.
AaravKashyap12/advise-project-approach
Plugin Claude Code
Bundles 1 skill · 118 tokens together
Make AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.
Plugin Claude Code ✓ vendor
Bundles 46 skills, 5 commands, 3 agents, 3 hooks, 1 MCP server · 3,541 tokens together
Build and deploy web apps and agents.
Skill Claude CodeCodex
Work with external data processor/report projects through EDT-MCP: metadata, forms, builds, and one-run debug launch. Not for prebuilt files outside an EDT project.
Skill Codex
Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…
Skill Codex
Use when an agent is running inside Zentty or needs to discover panes, split or grid layouts, float, minimize or dock panes, open temporary command overlays, focus panes, type into or read other panes, watch agent and pane events, search earlier agent sessions in this project, launch nested coding agents, or notify…
Agent Claude Code needs its repo
Independent verification of a factory change. Reads the diff cold, re-runs gates itself, and reaches its own verdict without trusting the implementer's account. Use after factory-implement completes and before any PR is opened.
Skill Claude CodeCodex
Shopify Admin & Storefront GraphQL APIs via curl. Products, orders, customers, inventory, metafields.
Hook Claude Code
Runs on the AfterAgent event, executing stop-hook.sh. From gemini-cli-extensions/ralph.
Skill Claude CodeCodex
How to recover when a tool call fails — diagnose, not blindly retry.
Skill Claude CodeCodex
Claude Code Source - Buildable Research Fork. Reverse-engineered build system, runnable with Bun.
Skill Claude CodeCodex
Diagnose ClickHouse cluster health and provide concrete remediation.
fleurytian/awesome-claude-skills
Skill Claude CodeCodex
A Chinese-language writing guide for emotionally driven articles, storytelling, and social commentary. It covers headlines, openings, emotional engagement, memorable lines, and narrative structure.
Skill Claude CodeCodex ✓ vendor
Turn Trailblaze App demo bundles (demo.yaml, actions.ndjson, screenshots, hierarchies) into runnable trails or add another platform's recording to an existing trail; verify by running.
superdesigndev/loopany-platform
Skill Claude CodeCodex
Create, update, and evolve scheduled Loopany agent loops from a coding session. Use when the user wants to turn a task they just did into a recurring/scheduled loop, edit an existing loop's schedule or instructions, or asks to build a Loopany loop. A loop can carry a goal (a finish line) and completes itself when the…
Skill Claude CodeCodex
Control agents within Termic and configure shared skills, MCP servers, and agent personas. Use for task delegation across projects, peer reviews in tabs, asynchronous coordination, or profile customization formats and model selection.
Skill Claude Code
A three-stage development method for Python projects built with pydantic-resolve, starting with agreed data models and ending with application interfaces. It uses an ER diagram, which shows database entities and their relationships, plus ORM models that represent database records in code.
scasella/claude-dynamic-workflows-codex
Plugin Claude Code
Bundles 1 skill · 100 tokens together
Run Claude Code dynamic-workflow scripts on a local Codex App Server — fan out Codex/GPT agents with the agent/parallel/pipeline DSL, sessionful steerable workers, supervised fleets (--multi), live viewers, and run analytics.
Skill Claude CodeCodex
Manage the AI organization - hire, fire, promote, delegate, and review boards.
Plugin Claude Code
Bundles 17 skills, 3 agents, 2 hooks · 558 tokens together
Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.
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: