ai-agents skills

52,432 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 333agentic-ai 283antigravity 212agent 204chatgpt 199agentic-skills 192ai-workflows 185agents 165coding-agents 154cli 144ai-assistant 126claude-code-skills 96agent-infrastructure 95claude-cli 95

local-places

577

geezerrrr/motive

Skill Claude CodeCodex

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

not rated 117 +1 6mo ago A 22 tokens original MIT

samarailly51-pixel/claimpilot-harness

Skill Codex

Review and structure auto insurance bodily injury claims, including intake triage, evidence completeness, injury causation, treatment chronology, medical necessity, wage-loss support, negotiation risks, and human escalation. Use when analyzing bodily injury claim files, designing claims-agent workflows, drafting…

not rated 117 20d ago A SkillSpector: warn 76 tokens original MIT

cdaf

580

UditAkhourii/cdaf

Skill Claude CodeCodex

Read CDAF sidecar files (.cdaf) instead of processing video with vision. Use whenever a task involves understanding, summarizing, searching, editing, or selecting from video files (b-roll, raw clips, footage libraries) — check for a .cdaf sidecar FIRST before analyzing any video directly.

not rated 117 +3 16d ago A SkillSpector: pass 65 tokens original MIT

requirement-ledger

581

adand-91/requirement-ledger

Skill Codex

Guide Codex in turning a user-selected conversation, Agent Skill, Git project, or recent-work window into a context-aware personal improvement plan. When the host exposes bounded task history, retrieve related authorised context; otherwise request a bounded selection or export. Use for one-time audit, daily…

not rated 117 +6 changed 9d ago A 109 tokens original MIT

harness-24h

582

thu-nmrc/OpenHarness

Skill Claude CodeCodex

A production-grade framework for long-running, autonomous agents based on Harness Engineering principles. Features three-layer self-healing memory, circuit breaker protection, KAIROS dream-mode consolidation, and multi-agent coordination. When a user describes a task idea, Agent automatically initializes the…

not rated 116 5mo ago A 76 tokens

Systematic debugging

583

Kilbex/Vigla

Skill Claude CodeCodex

Use when you hit a bug, test failure, or unexpected behavior — find the root cause before changing code.

not rated 116 11d ago A SkillSpector: pass 26 tokens original Apache-2.0

apple-dev-docs

584

BingoWon/apple-rag-mcp

Skill Codex

Search and retrieve Apple's official developer documentation, WWDC video transcripts, and framework references using semantic RAG. Use when the user asks about Apple platforms (iOS, macOS, watchOS, tvOS, visionOS), frameworks (SwiftUI, UIKit, ARKit, Core Data, HealthKit, StoreKit, etc.), Swift language features, Xcode…

not rated 116 +1 4d ago A SkillSpector: warn 89 tokens original MIT

README 文档生成

585

cdavid817/vanehub-ai

Skill Claude CodeCodex

Use this skill to create or improve README content. Cover what the project does, setup, common commands, configuration, development workflow, and troubleshooting.

not rated 116 +1 3d ago A SkillSpector: pass 21 tokens original Apache-2.0

simplecadapi

586

NiJingzhe/SimpleCADAPI

Skill Claude CodeCodex

Build, assemble, inspect, reconstruct, and export parametric CAD models with the SimpleCADAPI Python SDK. Use for SimpleCAD geometry modeling, constrained sketches, parts and assemblies, standard gears and bearings, STEP/BREP inspection and reconstruction, durable product packages, model JSON replay, and CAD backend…

not rated 116 +7 changed 2d ago A 65 tokens original Apache-2.0

gridgeist

587

ohmiler/gridgeist

Skill Codex

Use when creating, redesigning, or reviewing web interfaces that need product-specific structure, clear hierarchy, responsive composition, accessible interaction, or relief from generic AI-generated SaaS aesthetics. Adapt grid, typography, imagery, motion, and product evidence to the established brand—including…

not rated 115 1mo ago A SkillSpector: pass 101 tokens original MIT

clawd-control

588

Temaki-AI/clawd-control

Skill Claude CodeCodex

Monitor and manage your Clawdbot agent fleet from within an agent. Query health, sessions, usage, and trigger actions via the Clawd Control dashboard API.

not rated 114 6mo ago A 37 tokens original MIT

debug

589

mmprotest/villani-code

Skill Claude CodeCodex

Collect failing symptom, isolate reproduction, inspect logs and code paths, propose root cause and verify with tests.

not rated 114 1mo ago A 5 tokens

queue-workflow

590

longbkit/clisbot

Skill Claude CodeCodex

Queue-first continuation and review workflow for clisbot queues. Use when work needs deliberate follow-up against early stopping, shallow passes, prompt echoing, history leaking, duplicate files/functions/sections, naming drift, DRY/KISS regressions, missing docs/tests, or bad fallback behavior.

not rated 114 yesterday A SkillSpector: pass 62 tokens original MIT

code-review

591

hardness1020/Leeway

Skill Claude CodeCodex

Code quality review — identify patterns, anti-patterns, and improvements. Use when performing code reviews, auditing code quality, or evaluating pull requests for readability, maintainability, and correctness.

not rated 114 3mo ago A 40 tokens original MIT

holon-run/uxc

Skill Codex

Operate Binance Spot market, account, and order APIs through UXC with a curated OpenAPI schema, Binance query signing, and separate mainnet/testnet link flows.

not rated 114 +1 2d ago A SkillSpector: pass 42 tokens original MIT

dvalin-security-scan

593

arthurpanhku/dvalincode

Skill Claude CodeCodex

Scan code for injection, hardcoded secrets, XSS, dynamic code execution, and unsafe shell use. Use after writing or modifying code that handles user input, builds queries or commands, touches authentication, or adds a dependency — and whenever the user asks for a security check, audit, or review. Runs locally with no…

not rated 114 +1 changed 8d ago A SkillSpector: warn 77 tokens original MIT

lt2md

594

libnyx/LT2MD

Skill Claude CodeCodex

Convert born-digital, scanned, or mixed PDFs into auditable Markdown while preserving reading order, equations, source-page anchors, and information-bearing images as adjacent non-original text descriptions. Use this skill whenever a user asks to transcribe, OCR, understand, or convert a PDF into Markdown, especially…

not rated 114 20d ago A 115 tokens AGPL-3.0

create-template

595

mathematic-inc/earl

Skill Claude CodeCodex

Creates a new Earl HCL template for a specific API, database, or shell command. Use when adding a new service to Earl's template library, or when a pre-built template doesn't cover a needed command.

not rated 113 2d ago A SkillSpector: warn 45 tokens original Apache-2.0

crm-cli

596

dzhng/crm.cli

Skill Claude CodeCodex

Manage contacts, companies, deals, and pipeline with crm.cli — a headless CLI-first CRM backed by SQLite with a virtual filesystem interface.

not rated 113 +2 4mo ago C 30 tokens original MIT

alex-durango/pingfusi

Skill Codex

Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…

not rated 113 +3 3d ago A SkillSpector: pass 95 tokens original MIT

rustchain-mcp

598

Scottcjn/rustchain-mcp

Skill Claude CodeCodex

This skill allows Claude Code to interact with the RustChain blockchain, monitor the network, and hunt for bounties.

not rated 113 +2 changed 4d ago A 0 tokens original MIT

x-algorithm

599

carson2222/skills

Skill Claude CodeCodex

Write X (Twitter) posts that the For You algorithm actually rewards. Grounded in the open-sourced X recommendation system — the Grok-based transformer ranker, Phoenix retrieval, Thunder in-network store, and Grox content-understanding pipeline. Use when the user wants to write a post, thread, reply, or quote; plan a…

not rated 112 2mo ago A SkillSpector: pass 152 tokens original Apache-2.0

prd-writing

600

itseffi/agentic-os

Skill Codex

Write a structured PRD for high-risk, cross-team, or multi-sprint initiatives before implementation.

not rated 112 +3 16d ago A 23 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: