ai-agents skills

52,374 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 351agentic-ai 299antigravity 221agent 212chatgpt 209agentic-skills 192ai-workflows 185agents 168coding-agents 164ai-assistant 133cli 124claude-code-skills 101agent-infrastructure 100claude-cli 100

using-devql

385

bitloops/bitloops

Skill Claude CodeCodex

Use when answering repo-understanding questions in a Bitloops repo with DevQL guidance enabled, especially when you need to locate code by path, line range, exact symbol, or approximate/conceptual search before reading files.

not rated 240 +1 3mo ago A SkillSpector: pass 48 tokens original Apache-2.0

bx33661/Wireshark-MCP

Skill Codex

Investigate pcap/pcapng captures with Wireshark MCP to answer traffic, security, and network troubleshooting questions. Select bounded queries, verify packet evidence, and report what the capture can and cannot establish. Use the CLI skill when the user chooses direct tshark execution.

not rated 241 +12 changed 6d ago A SkillSpector: pass 63 tokens original MIT

kane-cli

387

LambdaTest/kane-cli

Skill Claude CodeCodex

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…

not rated 238 +1 changed today A 159 tokens copy · 100% Apache-2.0

qa

388

arcee-ai/nac

Skill Codex

Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…

not rated 243 +22 yesterday A SkillSpector: warn 100 tokens original Apache-2.0

smell-check

389

Zhen-Bo/smell-check

Skill Claude CodeCodex

Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength. Use for smell audit, code smell scan, whole-repo audit, tech debt scan, test smell check, maintainability audit, or duplication and nesting…

not rated 237 +1 14d ago A 94 tokens original MIT

onionclaw

390

christinminor459/OnionClaw

Skill Claude CodeCodex

Search the Tor dark web, fetch .onion hidden service pages, rotate Tor identity, and run structured OSINT investigations. Use when user asks to search dark web, investigate .onion sites, find if data appeared on dark web, conduct Tor-based OSINT, look up dark web leaks, fetch any .onion URL, check for leaked…

not rated 237 +1 today B 82 tokens

baidu-drive

391

baidu-netdisk/bdpan-storage

Skill Claude Code needs its repo

A Chinese-language command-line workflow for managing files in Baidu Drive, a cloud storage service. It supports file transfers and organization, plus backup and recovery of certain agent memory data.

not rated 239 +11 changed 7d ago A Socket: passSnyk: failSkillSpector: warn 174 tokens original Apache-2.0

maestro-work

392

ReinaMacCredy/maestro

Skill Claude CodeCodex

Drive one accepted implementation unit - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier; red tests only inside a Full bundle.

not rated 232 +1 changed 6d ago A SkillSpector: pass 34 tokens original MIT

modernize-tests

393

aduermael/herm

Skill Claude CodeCodex

Modernize test suites to use modern Swift Testing features or migrate from XCTest.

not rated 232 1mo ago A SkillSpector: pass 19 tokens original MIT

codex-chatgpt-bridge

394

Zhenyu98/codex-chatgpt-bridge

Skill Codex

Use when Codex needs to coordinate ChatGPT, Chrome, Cloudflare tunnels, verified bridge Restart/Reboot recovery, or task routing between local code execution and ChatGPT reasoning/review. Handles the bridge controller and scheduled task, start/off/status/doctor/rotate flows, Worker KV refresh, ChatGPT app setup…

not rated 231 +13 1mo ago A SkillSpector: pass 97 tokens original MIT

social-account-doctor

395

JuneYaooo/social-account-doctor

Skill Claude CodeCodex

A workflow for researching and improving social-media accounts and videos on Chinese platforms such as Xiaohongshu, Douyin, Kuaishou, WeChat Channels, and Bilibili. It compares accounts, breaks down popular posts, and helps draft new content from supplied material.

not rated 231 +11 28d ago B 320 tokens original MIT

deploying

396

GoogleCloudPlatform/race-condition

Skill Claude Code

Guides deployment of Race Condition to a GCP project. Use when deploying to the cloud, setting up infrastructure with Terraform, or troubleshooting a deployment. This is for cloud deployment -- for local development, use the getting-started skill instead.

not rated 229 +2 yesterday A 51 tokens

coding-standards

397

shinpr/ai-coding-project-boilerplate

Skill Claude Code

Detects code smells, anti-patterns, and readability issues. Use when implementing features, reviewing code, or refactoring.

not rated 228 changed today A SkillSpector: warn 30 tokens original MIT

google-workspace

398

graniet/kheish

Skill Claude CodeCodex

Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via gws CLI (googleworkspace/cli). Uses OAuth2 with automatic token refresh via bridge script. Requires gws binary.

not rated 227 1mo ago A SkillSpector: warn 40 tokens original Apache-2.0

beacon-skill

399

Scottcjn/beacon-skill

Skill Claude CodeCodex

Agent-to-agent protocol for social coordination, crypto payments, and P2P mesh.

not rated 227 +2 5d ago B 0 tokens original MIT

project-cairn

400

iBlinkQ/project-cairn

Skill Claude CodeCodex

Standardize how an AI-collaboration project turns work into reusable knowledge. Use when initializing or retrofitting Project Cairn in a project, recording progress after meaningful work, maintaining AGENTS/CLAUDE/cairn docs, auditing project knowledge for drift or missing records, pulling and citing external…

not rated 226 +3 8d ago A 78 tokens original MIT

k8s-pod-rightsizer

401

initializ/forge

Skill Claude CodeCodex

Analyze Kubernetes workload metrics and produce policy-constrained CPU/memory rightsizing recommendations with optional patch generation and rollback-safe apply.

not rated 226 +1 today A SkillSpector: warn 33 tokens original Apache-2.0

slm-recall

402

qualixar/superlocalmemory

Skill Claude Code needs its repo

Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.

not rated 226 changed today A 60 tokens AGPL-3.0

code-reviewer

403

didilili/deepsearch-agents

Skill Claude CodeCodex

A code-review guide written in Chinese for examining source code for bugs, security risks, performance problems, and quality issues.

not rated 223 +9 3mo ago A 30 tokens

weather-skill

404

simranjeet97/Awsome_AI_Agents

Skill Claude CodeCodex

Fetches real-time weather conditions for any city or location worldwide. Use this skill when the user asks about weather, temperature, rain, forecast, or climate conditions for a specific place.

not rated 221 +2 4mo ago A 41 tokens original Apache-2.0

fluxcd/agent-skills

Skill Claude CodeCodex

Run the upstream Flux controller minor release procedure for helm-controller, image-automation-controller, image-reflector-controller, kustomize-controller, notification-controller, source-controller, and source-watcher. Use when cutting a new controller minor release (vX.Y.0): creating the release series branch…

not rated 220 +2 4d ago A SkillSpector: warn 89 tokens original Apache-2.0

design-taste-frontend

406

coco-research/coco

Skill Claude CodeCodex

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

not rated 220 +1 today A 61 tokens

omp

407

aigorahub/elves

Skill Claude CodeCodex

Bounded Oh My Pi (omp) provider shortcut via Elves. Use when the user says /omp or "use omp" for a one-shot task.

not rated 220 +1 changed 7d ago A SkillSpector: pass 34 tokens original MIT

gui

408

svd-ai-lab/sim-cli

Skill Claude CodeCodex

Cross-driver GUI actuation for CAE solvers running under sim-cli. Use to click buttons, fill fields, dismiss dialogs, and capture window screenshots against GUI-capable driver windows through sim exec.

not rated 220 +5 4d ago A SkillSpector: pass 43 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: