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.

dirextalk-deployer

2377

YingSuiAI/dirextalk-deployer

Skill Claude CodeCodex needs its repo

Deploy, resume, verify, update, recover, reset, or destroy production Dirextalk services and nodes on AWS. Use when the user explicitly invokes $dirextalk-deployer or asks in natural language for one of these Dirextalk lifecycle operations.

not rated 457 11d ago A SkillSpector: pass 58 tokens original MIT

davinci-autoedit-agent

2378

liuluhaixiu/DaVinci-AutoEdit-Agent

Skill Codex

End-to-end, approval-gated video editing workflow for arbitrary user-selected video, audio, and optional image media. Use when Codex must scan footage, review and classify material, develop a topic into a script, optionally generate TTS, create an edit blueprint, or build and audit a DaVinci Resolve timeline without…

not rated 457 +15 3mo ago A SkillSpector: warn 86 tokens original MIT

ecosystem-usage

2379

nuxt/nuxt.com

Skill Claude CodeCodex

Measure Nuxt and Nuxt UI MCP traffic plus agent-facing Markdown usage with Vercel Observability.

not rated 457 +1 2d ago A 21 tokens original MIT

xquik

2380

understudy-ai/understudy

Skill Claude CodeCodex

Use Xquik REST and MCP APIs for X data workflows: search public posts, inspect users, export datasets, download media, monitor accounts or keywords, and send webhook events. Use when the user needs X data from Xquik rather than account-scoped X API actions through xurl.

not rated 456 +1 2mo ago A SkillSpector: warn 63 tokens original MIT

thesis-docx

2381

the-shy123456/thesis-docx

Skill Claude CodeCodex

Create, revise, and format thesis or dissertation Word documents with strict academic formatting control. Use when an AI agent needs to generate or revise thesis content, normalize Word styles, follow a school template, fix captions or page numbers or section levels, or produce evidence-based Mermaid figures and…

not rated 456 +1 5mo ago A 72 tokens original MIT

gtd

2382

scunning1975/MixtapeTools

Skill Claude Code

Warrant-first research GTD system. Manages the capture-clarify-organize-reflect-engage cycle for causal inference research. Scaffolds hypotheses/, insights/, decisions/ directories. Interrogates conjectures, files results, tracks binding decisions, checks pipeline freshness, drives the courtroom checklist.

not rated 456 +6 17d ago A 63 tokens

x-mcp

2383

xpzouying/x-mcp

Skill Claude CodeCodex

An automation assistant for Xiaohongshu, a Chinese social-media platform also known as Little Red Book. It supports account checks, searching and viewing posts, engagement, publishing, and cover creation.

not rated 456 +6 3d ago A 71 tokens

nvmolkit-usage

2384

NVIDIA-BioNeMo/bionemo-agent-toolkit

Skill Claude CodeCodex

Write code that calls the installed nvMolKit Python API for GPU-accelerated, batched RDKit-style operations - Morgan fingerprints, Tanimoto/cosine similarity, ETKDG conformer embedding, MMFF/UFF optimization, TFD, conformer RMSD, Butina clustering, and substructure search. Use when the user is importing nvmolkit.…

not rated 456 +9 2d ago A 136 tokens

resume-optimizer

2385

wyh0626/resume-optimizer

Skill Claude CodeCodex

A Chinese-language assistant for auditing and improving job resumes. It rewrites duty-focused descriptions around outcomes, adjusts content to a target job description, and can produce a shorter one-page version.

not rated 456 +14 1mo ago A 178 tokens original MIT

research

2386

SynaLinks/synalinks

Skill Claude CodeCodex

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices.

not rated 455 yesterday not scanned tokens not measured original Apache-2.0

skill-creator

2387

PleasePrompto/ductor

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 455 +1 1mo ago A 45 tokens copy · 89% MIT

agent-spec-estimate

2388

ZhangHanDong/agent-spec

Skill Claude CodeCodex

An effort-estimation method for agent-spec Task Contracts, which are structured descriptions of software work. It estimates work in rounds, meaning cycles of an AI agent doing and checking tasks.

not rated 455 +4 14d ago A SkillSpector: pass 116 tokens original MIT

workflow-orchestrator

2389

SHAdd0WTAka/Zen-Ai-Pentest

Skill Claude CodeCodex

Module Loop and Iteration Skill for orchestrating multi-phase penetration testing workflows. Use when coordinating sequential tool execution, managing dependencies between reconnaissance and vulnerability scanning modules, implementing adaptive fallback strategies, or managing workflow state across iterations.…

not rated 455 +4 2d ago A SkillSpector: pass 85 tokens original MIT

notebooklm-research

2390

claude-world/notebooklm-skill

Skill Claude CodeCodex

Automate source-grounded research with Google NotebookLM. Create notebooks from URLs, text, or local files; ask cited questions; run fast or deep web research; create articles and social drafts; and generate or download audio, video, cinematic video, slides, reports, study guides, quizzes, flashcards, mind maps…

not rated 455 +1 1mo ago A 114 tokens original MIT

zerotoken-openclaw

2392

AMOS144/ZeroToken

Skill Claude CodeCodex

Use when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.

not rated 454 4mo ago A SkillSpector: pass 36 tokens original MIT

sys-info

2393

barry-ran/QuickDesk

Skill Claude CodeCodex

Retrieve system information and list running processes on a remote host via QuickDesk. Use when the user asks to check server health, monitor CPU or memory usage, view disk space, list running processes, or query OS and uptime details on a remote machine.

not rated 454 +17 27d ago A SkillSpector: pass 53 tokens original MIT

ai-check

2394

harshaneel/humanize

Skill Claude CodeCodex

Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run ai-check on this", or "score this text". Also use when reviewing a draft for AI tells before publishing, or when a piece of text reads as suspiciously polished, generic, or pattern-y and the user wants a…

not rated 454 +34 2mo ago A SkillSpector: pass 81 tokens original MIT

agr-cli

2395

computerlovetech/agr

Skill Claude CodeCodex

Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI. Use whenever the user mentions agr, agr.toml, agr.lock, agrx, or asks to: add a skill ("install the pdf skill", "agr add ..."), sync agent resources across tools, share skills…

not rated 453 +1 1mo ago A SkillSpector: warn 147 tokens original MIT

ask-agents

2396

chrisblattman/claudeblattman

Skill Codex

Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks to ask Claude, ask Gemini, ask both, get a second opinion, split reviewer roles, or compare external agents.

not rated 453 +2 3mo ago A SkillSpector: warn 55 tokens original MIT

MinaSaad1/pbi-cli

Skill Claude CodeCodex

Vibe-code Power BI custom visuals end-to-end: scaffold a TypeScript project, iterate on src/visual.ts and capabilities.json, validate with the Power BI Visuals SDK toolchain, package to .pbiviz, and import into a PBIR report. Invoke this skill whenever the user mentions "custom visual", "pbiviz"…

not rated 453 +1 yesterday A SkillSpector: warn 152 tokens original MIT

ryantsai/KKTerm

Skill Claude CodeCodex

Improve KKTerm Dashboard AI Created Widget visual design, layout hierarchy, desktop utility polish, design-system consistency, compact states, and redesign critique.

not rated 453 +3 today A 33 tokens

stop-ai-slop-jp

2399

iKora128/stop-ai-slop-jp

Skill Claude CodeCodex

A Japanese-language editing guide for making AI-written drafts sound more like writing from a specific person. It focuses on clear claims, natural rhythm, and naming who did what.

not rated 453 +5 3mo ago A 80 tokens original MIT

bytedance/agentkit-samples

Skill Codex ✓ vendor

Guide a user conversationally through generating a new ad video from a template video and a user-provided product image. The host agent performs video understanding, detailed analysis, and rewrite planning; BytePlus Seedance is used only for final video generation with local product images as generation references.

not rated 453 +4 changed 9d ago A SkillSpector: warn 71 tokens original Apache-2.0

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: