Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

mt4-mcp

21673

mergeos-bounties/mt4-mcp

Skill Claude CodeCodex

MetaTrader 4 account/quotes/orders (mock + live bridge). CLI mt4-mcp + MCP stdio serve. Use when the user mentions mt4-mcp, /mt4-mcp, or related domain work. One-command Grok install from GitHub.

not rated 2 2mo ago A 62 tokens original MIT

golang

21674

car12o/agents

Skill Claude CodeCodex

Write idiomatic, production-grade Go. Self-contained — all rules inline, no reference files. Use when editing .go files, go.mod, go.sum, or Go tests, or when asked to design, generate, or review Go code. Covers style, control flow, errors, concurrency, context, testing, performance, security, modules, JSON, database…

not rated 2 changed 25d ago A 90 tokens

code-oz

21675

omerakben/code-oz

Skill Claude CodeCodex

Drive the code-oz agentic SDLC runtime to build or fix code with enforced gates and cross-family review. Use when the user asks to build, implement, or fix something in a code repository and wants gated, reviewed delivery rather than ad-hoc edits.

not rated 2 3mo ago A 57 tokens original MIT

nirium-agentic-payments

21676

nirium-protocol/nirium-sdk

Skill Claude CodeCodex

Scaffold and run an x402 paid API server on Stellar with open-source client libraries: charge AI agents per API call with x402Serve(), a function from the nirium SDK that runs entirely on your own server, scaffold that server with nirium-cli in one command, and separately read live protocol data through the nirium-mcp…

not rated 2 changed 1mo ago A 128 tokens original Apache-2.0

swarm-subagent

21677

finml-sage/agent-swarm-protocol

Skill Claude CodeCodex

You are a Claude subagent participating in an Agent Swarm Protocol network. You process incoming messages from other agents and respond appropriately.

not rated 2 5mo ago A 0 tokens original MIT

workable-item-lifecycle

21678

HelixDevelopment/code

Skill Claude CodeCodex

Move a tracked workable item through its lifecycle — start, close, reopen, block or mark obsolete — using the legal status and type values.

not rated 2 22d ago A 27 tokens original MIT

thumbnail-creator

21679

greg-prospyr/thumbcraft-skills

Skill Claude CodeCodex

Generate AI-powered YouTube thumbnails, analyze videos for thumbnail ideas, manage styles/faces/brands, and create SEO-optimized titles and descriptions. Use when users want to create thumbnails, need thumbnail ideas for a video, want to clone a thumbnail style, or need YouTube SEO content.

not rated 2 7mo ago A 62 tokens original MIT

specify

21680

yannlugrin/claude

Skill Claude CodeCodex

Write project specifications (SPECIFICATIONS.md) intended for AI implementation: a staged, decision-centric process where the user arbitrates every decision — intake and exploration, structured drafting under the must/should/facts contract, cold subagent review rounds, premise challenges of foundational decisions, and…

not rated 2 1mo ago A 233 tokens original MIT

architecture

21681

bpkey/skills

Skill Claude CodeCodex

Use whenever designing, reviewing, refactoring, or evolving the STRUCTURE of a codebase — module boundaries, layering, where new code should live, naming a package or service, an architecture-worthy decision, or auditing existing structure. Triggers on phrases like "design the architecture", "where should this live"…

not rated 2 25d ago A 139 tokens

skill-builder

21682

austinpeechatt/claude-code-skills

Skill Claude CodeCodex

Use when creating new skills, optimizing existing skills, or auditing skill quality. Guides skill development following Claude Code official best practices.

not rated 2 7mo ago A 28 tokens

vibe-init

21683

chentao326/vibe-code

Skill Claude Code

A setup guide for starting Vibe Code, a project evaluation tool, in either a new folder or an existing code project. It checks the project, asks setup questions, creates initial files, and can import its history.

not rated 2 4mo ago A 93 tokens original MIT

generate-agents-md

21684

Enterwell/agent-skills

Skill Claude CodeCodex

Create or improve a project-specific AGENTS.md file for software repositories. Use when a user wants durable setup, testing, architecture, safety, and workflow instructions for AI coding agents.

not rated 2 4mo ago A 41 tokens original MIT

review-pr

21685

edlng/agents

Skill Codex

Reviews a pull request against the linked Jira ticket and the existing codebase. Parallel reviewers per discipline, findings merged and checked by a skeptic validator pass. Output is local only: printed in chat, rendered as a temporary self-contained HTML report, and saved as a findings JSON file. Nothing is posted to…

not rated 2 changed today A 83 tokens

fable-mode

21686

richardoros/fable-mode

Skill Claude CodeCodex

Staged orchestration for genuinely multi-stage builds — stage map, warm implementer / fresh adversarial verifier, witnessed-red TDD, re-verify on every change. Builds on the always-on operating discipline in /.claude/CLAUDE.md (verify by re-execution, [confirmed]/[inferred] labeling, cost/blast gating), which applies…

not rated 2 3mo ago A 147 tokens original MIT

aws

21687

whchoi98/claude-code-skills

Skill Claude CodeCodex

An AWS management skill for working with Amazon Web Services, a cloud platform that provides servers, storage, and other infrastructure.

not rated 2 9mo ago B 35 tokens

symphony-workflow

21688

MH4GF/claude-code

Skill Claude CodeCodex

A shared procedure for background coding sessions that are assigned issues by Symphony, an orchestration tool. It covers checking the issue tracker, recording work, moving work to human review, and merging changes.

not rated 2 changed 27d ago A 74 tokens original MIT

stories-yasko

21689

yasikvlad/stories-yasko

Skill Claude CodeCodex

A framework for creating sequences of Instagram Stories, Instagram's short-lived vertical posts, in Russian. It combines a viral story structure, ideas from neuroscience, and sales-oriented audience warming.

not rated 2 6mo ago A 182 tokens

hypertrophy-training

21690

fabiandistler/agents

Skill Claude CodeCodex

Evidence-based hypertrophy programming and auto-regulation with plateau diagnosis for experienced trainees. Covers set volume, RIR targets, Stimulus:Fatigue ratio, rest, muscle lengths, elevated injury risk, and returning after injury.

not rated 2 changed 7d ago A 50 tokens

kruize-optimization

21691

causaai/causa-backend

Skill Claude CodeCodex

Activate whenever RESOURCE COST RECOMMENDATIONS (Kruize) or RESOURCE PERFORMANCE RECOMMENDATIONS (Kruize) sections are present in the diagnostic context. Interprets Kruize CPU and memory right-sizing recommendations for containers.

not rated 2 1mo ago A 53 tokens original Apache-2.0

OneKeyHQ/QA-AGENTS

Skill Claude CodeCodex

A generator for Apifox API test cases. Apifox is a tool for designing, documenting, and testing web APIs, and this add-on includes a command for listing API endpoints.

not rated 2 16d ago A 0 tokens

Lycorius03/ai-skills

Skill Claude CodeCodex

Use this skill when an agent must turn sparse paper requirements into a reusable academic writing prompt, optionally self-inject that prompt to generate a Markdown paper, and/or convert the Markdown into a correctly formatted DOCX thesis with automatic TOC, sectioned page numbers, citation discipline, and repeated…

not rated 2 5mo ago A 71 tokens original MIT

codabench-bundle

21694

ihsaan-ullah/auto-codabench

Skill Claude CodeCodex needs its repo

Technical schema and conventions for a Codabench competition bundle (competition.yaml, pages, phases, scoring program, ingestion program, scores.json↔leaderboard mapping, zip layout). Use when generating any file inside a bundle.

not rated 2 2mo ago A 51 tokens original MIT

help

21695

a5c-ai/babysitter-codex

Skill Claude CodeCodex

Skill "help" from a5c-ai/babysitter-codex, covering help, if no arguments provided and if arguments provided.

not rated 2 1mo ago A 32 tokens

stream-coding

21696

TeamDay-AI/agents

Skill Claude CodeCodex

Documentation-first development methodology. The goal is AI-ready documentation - when docs are clear enough, code generation becomes automatic. Triggers on "Build", "Create", "Implement", "Document", or "Spec out". Version 3.4 adds complete 13-item Clarity Gate with scoring rubric and self-assessment.

not rated 2 5mo ago A 68 tokens

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: