ai-agent skills

17,532 tagged ai-agent, measured the same way as everything else here.

Browse within: LLM 340agent 300cli 284openclaw 219ai-tools 197chatgpt 193agentic-ai 180cybersecurity 161Multi-Agent 132agentskills 123curated 122myclaw 122skill-collection 121coding-agent 113

bossmate

625

yinren112/bossmate

Skill Codex

A job-search workflow for BOSS, a Chinese recruitment platform, controlled through a browser you log into yourself.

not rated 18 1mo ago A 129 tokens original MIT

create-plugin

627

oneworks-ai/app

Skill Codex

A guide for creating or changing OneWorks plugins, including their interface entry points and local services. OneWorks is the plugin platform this guide targets.

not rated 18 13d ago A SkillSpector: pass 73 tokens original MIT

mapick

628

mapick-ai/mapick

Skill Claude CodeCodex

Mapick — Skill recommendation & privacy protection for OpenClaw. Scans your local skills, suggests what you're missing, and keeps other skills from seeing your sensitive data.

not rated 18 3mo ago C 37 tokens original MIT

pulser

629

TheStack-ai/pulser

Skill Claude Code

Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter, conflicts, usage-hooks), classifies skill types, generates prescriptions, and runs eval tests. Use when checking skill quality, auditing…

not rated 18 2mo ago A 126 tokens original MIT

openfuse

630

openfused/openfused

Skill Claude CodeCodex

Open protocol for AI agent communication. Encrypted mail, subscribe/broadcast newsletters, trust tiers, DNS discovery. Use when sending messages between agents, subscribing to agent broadcasts, managing cryptographic trust/identity, syncing with peers, or any inter-agent communication. Triggers on "openfuse", "agent…

not rated 18 2mo ago B 91 tokens original MIT

privacy

631

gpdir16/tabyAgent

Skill Claude CodeCodex

Privacy tools and alternatives to mainstream services with verified details on licensing, ads, and pricing.

not rated 18 12d ago A 20 tokens AGPL-3.0

garmin-pulse

632

freakyflow/garminskill

Skill Claude Code

Syncs daily health and fitness data from Garmin Connect into markdown files. Provides sleep, activity, heart rate, stress, body battery, HRV, SpO2, and weight data.

not rated 18 7mo ago A 43 tokens

6missedcalls/personal-finance-skill

Skill Claude CodeCodex

Personal finance management skill providing 75 tools across 7 extensions for bank account aggregation (Plaid), brokerage trading (Alpaca), portfolio monitoring (IBKR), tax optimization, market intelligence (Finnhub, SEC EDGAR, FRED, BLS, Alpha Vantage), social sentiment (StockTwits, X/Twitter, Quiver), and financial…

not rated 18 6mo ago A 104 tokens original MIT

nova-grounding

634

bigduu/Nova

Skill Claude CodeCodex

AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.

not rated 18 changed 9d ago A 40 tokens original MIT

ros2-skill

635

adityakamath/ros2-skill

Skill Claude Code

Use this skill for any ROS 2 robot task: topics (subscribe, publish, capture images, find by type), services (list, call), actions (list, send goals), parameters (get, set, presets), nodes, lifecycle management, controllers (ros2control), Nav2 navigation (go, rotate, cancel, costmap-clear, waypoints, move-timed…

not rated 18 1mo ago A 148 tokens original Apache-2.0

wjx-survey-ppt

636

wjxcom/wjx-ai-kit

Skill Claude CodeCodex

Instructions for turning Wenjuanxing questionnaire responses into a presentation report. Wenjuanxing, also called 问卷星, is a platform for creating surveys and collecting answers.

not rated 18 +1 changed 9d ago A SkillSpector: pass 140 tokens original MIT

explore

637

v0lka/skills

Skill Claude CodeCodex

Explore → Plan → Implement. A thinking partner for exploring ideas, investigating problems, and clarifying requirements, that transitions into a structured roadmap specification (tasks in What/How/Where/Acceptance criteria format) for user approval, then implements the approved plan. Use when the user wants to think…

not rated 18 1mo ago A SkillSpector: warn 80 tokens original MIT

agent-reach

638

noahneancy-byte/netreach

Skill Claude CodeCodex

A skill for reaching online sources through several search and platform-specific tools. It covers web pages, GitHub, video subtitles, RSS feeds, and selected discussion platforms.

not rated 18 +12 25d ago A 278 tokens original MIT

knowledge-base

639

zach-blumenfeld/knowledge-index

Skill Claude CodeCodex

Search, navigate, and read a markdown knowledge base — a directory of notes, docs, or a wiki — via an auto-built knowledge-graph index over documents, their sections, and the wikilinks between them, retrieving the right slice instead of grepping and reading whole files. Use when working in a folder of markdown …

not rated 18 +7 19d ago A ✓ AI review 94 tokens original Apache-2.0

clumsies

640

lilhammerfun/clumsies

Skill Claude CodeCodex

Use Clumsies in a bound project to retrieve relevant Memory, including project-maintained skills and procedures. Use for substantive project tasks when the Clumsies memory MCP tool is available; skills stored in Memory remain ordinary project guidance.

not rated 18 +1 2d ago A 50 tokens original MIT

agent-copy

641

shane9coy/Agent-Skill-Architecture-Guide

Skill Claude CodeCodex

Use when the user asks to copy, install, refresh, or update a repo-root AGENTS.md file from their canonical global instruction source. Also use when the user says "agent copy" or wants a repo-local AGENTS.md with global operating rules plus project-specific guidance.

not rated 17 3mo ago A 58 tokens original MIT

dense-ui-metrics

642

HarKro753/claude-copy

Skill Claude Code

Mathematical spacing, sizing, weight, line-height, letter-spacing, radius, and padding rules for "productive" SaaS interfaces, across density regimes: Dense (Linear / Doppler / Raycast / Vercel), Comfortable/roomier (Cal.com style), and anything in between. Use this whenever you are building OR refining any such UI …

not rated 17 1mo ago A 229 tokens original MIT

research-paper-review

643

BESSER-PEARL/research-agent-skills

Skill Claude CodeCodex

Review and analyze academic research papers. Use this skill when the user asks to review a paper, analyze a publication, summarize research, critique methodology, extract key findings, compare papers, check for numerical inconsistencies, or assess novelty and contributions of academic work. Also triggers when the user…

not rated 17 2mo ago A 87 tokens original MIT

zettelkasten-brain

644

cx2002302-lang/zettelkasten-second-memory

Skill Claude CodeCodex

A knowledge-management system based on Zettelkasten, a method of keeping small linked notes so ideas can be found and connected later. It provides tools for searching, creating, updating, reviewing, archiving, and analyzing notes.

not rated 17 1mo ago A 36 tokens original MIT

web-search

646

vericle/heyclaw

Skill Claude CodeCodex

Search for and verify up-to-date information on the Internet.

not rated 17 1mo ago A 15 tokens original MIT

vibedev

647

4pixeltechBR/VibeDev

Skill Claude CodeCodex

Framework de governança para desenvolvimento de software com IA — guia completo para vibe coders sem experiência em engenharia. Cobre dois cenários: projeto novo do zero (Trilha Verde) e resgate de projeto existente com problemas estruturais (Trilha Vermelha). Funciona em Claude Code, Cursor, Antigravity, OpenCode…

not rated 17 +1 1mo ago A 156 tokens original MIT

aartiq/nowaikit

Skill Claude CodeCodex

Audit ServiceNow CMDB health using NowAIKit MCP tools — find duplicate, orphaned, and stale CIs, score completeness, and propose remediation. Use when the user asks to check CMDB health, data quality, CSDM conformance, or clean up the CMDB.

not rated 17 +1 yesterday A 67 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: