ai-agents skills

52,398 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 338agentic-ai 282agent 210antigravity 210chatgpt 199agentic-skills 192ai-workflows 185agents 165coding-agents 152cli 144ai-assistant 126openclaw 95claude-code-skills 91agent-infrastructure 90

ad-creative-paid-ads

1105

ItamarZand88/awesome-agent-conventions

Skill Claude CodeCodex

Skill "ad-creative-paid-ads" from ItamarZand88/awesome-agent-conventions, covering ad creative, before starting, 1. product & offer, 2. audience and 3. platform & stage.

not rated 31 1mo ago A 0 tokens original MIT

tryworld-paper

1106

TryWorld2026/paper-algorithm

Skill Codex

A workflow for turning a Chinese voiceover script and optional images into a branded 16:9 AI-knowledge video in the “Paper Algorithm” style.

not rated 31 +1 changed 9d ago A 215 tokens CC-BY-SA-4.0

derive-capacity

1107

aenix-io/aeman

Skill Claude CodeCodex

Work out how many points a week each person on the aeman board actually gets through, from the cards they have closed, and set it as their capacity after the lead confirms. Use when a team lead asks about throughput, weekly capacity, how much a person or a team can take, or wants the numbers over the columns filled in.

not rated 31 yesterday A 72 tokens original Apache-2.0

tdd

1108

Shelpuk-AI-Technology-Consulting/agent-skill-tdd

Skill Claude CodeCodex

Use for every coding task. Enforce strict TDD workflow: activate Serena, investigate first, clarify+confirm requirements, write per-task REQUIREMENTS.md in .requirements/ /, verify APIs via web search, then implement in tiny test-verified steps.

not rated 30 5mo ago A 59 tokens original MIT

janee

1109

rsdouglas/janee

Skill Claude CodeCodex

Secure API proxy that stores credentials encrypted and injects auth server-side. Use when: (1) making any external API call — "call the Stripe API", "enrich my data [from PeopleDataLabs]", "create an image [using Nano Banana API]", "use a [RapidAPI service]", (2) the user shares an API key, token, or secret — "here's…

not rated 30 6mo ago A 176 tokens original MIT

x402-list

1110

mcccsm/x402-list-mcp

Skill Claude CodeCodex

Discover x402 payment services and on-chain-verified facilitator settlement volume via the x402-list directory. Use when a user or agent needs to find an API/service that accepts x402 (HTTP 402 stablecoin) payments, compare services by reliability and price, check service uptime/health, see whether a service has…

not rated 30 changed 9d ago A 99 tokens original MIT

original-design

1113

sanky369/vibe-building-skills

Skill Claude CodeCodex

Facilitates an interactive session that turns a product or subject into an original, internally consistent visual design language for any artifact — infographics, video storyboards, websites, or mobile app UI/UX. Use when the user wants an original design language, identity, or art direction, or when a design feels…

not rated 30 2mo ago A 153 tokens original MIT

gnt-check-action

1114

gnt-ai/gnt

Skill Claude CodeCodex

Check a side-effectful action against this organization's approved gnt rules before taking it, and stop on a blocked or needshuman verdict.

not rated 30 5d ago A SkillSpector: pass 33 tokens original Apache-2.0

challenge-04

1115

Berserk-hub150/skillhawk

Skill Claude CodeCodex

Start a local preview service when the developer needs it and keep lifecycle control visible to the user.

not rated 30 +2 today A SkillSpector: warn 0 tokens original MIT

Konata9/chinese-lottery-predict-skills

Skill Claude CodeCodex

A Chinese-language skill for suggesting numbers for China’s Double Color Ball and Super Lotto games using real draw data. The suggestions are explicitly for entertainment because lottery draws are random.

not rated 30 +1 1mo ago A 49 tokens original MIT

delegation

1117

ai-ecoverse/slicc

Skill Claude Code

Use this when deciding whether to do work yourself or delegate to a scoop, when fanning out parallel scoops, or when picking models for sub-agents. Covers scoop lifecycle (when to drop), parallel orchestration (scoopmute, scoopunmute, scoopwait), one-shot ephemeral sub-agents via the agent shell command, and model…

not rated 30 changed yesterday A SkillSpector: warn 101 tokens original Apache-2.0

ce-compound

1118

elleryfamilia/loadout

Skill Claude Code

Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.

not rated 30 +2 yesterday A 32 tokens original MIT

itr-prep-skill

1119

NidheeshJain/itr-prep-skill

Skill Claude CodeCodex

End-to-end assistant for filing Indian Income Tax Returns (ITR-1/2/3/4) for any assessment year. Takes a user from raw documents (Form 16, AIS, Form 26AS, broker tax P&L, payslips, bank statements) to a fully reconciled, schedule-by-schedule computation and a portal-ready data pack — including form selection…

not rated 29 1mo ago A 308 tokens original MIT

trope-cua

1120

tropeai/trope-cua

Skill Claude CodeCodex

Drive native Windows apps with Trope CUA via the trope-cua CLI or MCP server. Use when the user asks to operate, inspect, automate, or test a real Windows GUI app while preserving the user's foreground app and real cursor whenever possible.

not rated 29 1mo ago A 55 tokens original MIT

llama-parse

1121

hankunpeng/skills

Skill Claude CodeCodex

Use this skill to parse complex documents (PDFs, Word documents, PowerPoint presentations, Excel spreadsheets, or images) into clean Markdown or structured JSON using the LlamaParse API. Make sure to use this skill whenever the user asks to extract tables from PDFs, handle complex document structures (multi-column…

not rated 29 3d ago A SkillSpector: warn 97 tokens original MIT

product-idea-excavator

1122

derrickgong87/product-idea-excavator

Skill Claude CodeCodex

A guided interview for turning an early product or startup idea into a detailed product requirements document, or PRD. A PRD is a written description of what a product should do and how it should be built.

not rated 29 4mo ago A 149 tokens original MIT

handoffkit

1123

dyngai/handoffkit

Skill Codex

Built by DynG AI for PlatformPilot.ai-style multi-agent systems. Use when designing or reasoning about message-passing agent coordination in ANY language: actor-style mailboxes, select, point-to-point routing, pub/sub, fan-in joins/quorums, ownership handoff, budgets, dead letters, and traces. Trigger words include…

not rated 29 +1 2mo ago A 114 tokens original MIT

code-review-practices

1124

armanzeroeight/fastagent-plugins

Skill Claude CodeCodex

Provides practical guidance for conducting thorough code reviews that identify issues early, promote knowledge sharing, and deliver constructive feedback. This skill should be used when reviewing pull requests, establishing team review standards, or mentoring developers on effective review practices.

not rated 29 1mo ago A SkillSpector: pass 51 tokens original MIT

vibeflow-prompt-pack

1125

pe-menezes/vibeflow

Skill Claude CodeCodex

Generates a self-contained prompt pack from a spec. Embeds real code patterns from .vibeflow/ so any coding agent follows the project's conventions. Use when handing off implementation to a separate session or agent.

not rated 29 7d ago A SkillSpector: warn 52 tokens original MIT

skill-creator

1126

panaversity/agentfactory-business-plugins

Skill Claude Code

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 29 5mo ago A 64 tokens copy · 88% Apache-2.0

team-style-guide

1127

miniLV/Plexus

Skill Claude CodeCodex

Team coding style baseline shared across every AI agent.

not rated 29 +1 11d ago A 14 tokens original Apache-2.0

build-personal-brain

1128

mikeshu2001/personal-brain-builder

Skill Codex

Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…

not rated 29 11d ago A SkillSpector: warn 81 tokens original MIT

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: