ai-agents skills

52,251 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 347agentic-ai 322agent 227antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 89agent-infrastructure 88

ocr-and-documents

4226

nobodyohm-web/Thot

Skill Claude CodeCodex

Extract text from PDFs/scans (pymupdf, marker-pdf).

not rated 0 23d ago A 21 tokens copy · 80% MIT

averray-worker

4227

averray-agent/agent

Skill Claude CodeCodex

Use Averray's MCP workflow to sign in with your own wallet, choose eligible work, claim and submit it, confirm settlement, and withdraw earnings.

not rated 0 changed yesterday A 35 tokens

clervo/clervo

Skill Claude CodeCodex

Classify Clervo authority and enforce exact-ticket or exact-maintenance execution before repository work. Use for Clervo product engineering, control-plane maintenance, implementation requests, reviews, diagnoses, stage transitions, ticket continuation, verification, evidence recording, commits, or any request whose…

not rated 0 4d ago A 67 tokens

coding-guardrails

4229

frankxai/agentic-ops-hub

Skill Claude CodeCodex

Unified LLM coding rules, simplicity guidelines, surgical changes, and thinking protocols for all AI agents. Triggers on: code rules, guardrails, coding guidelines, coding conventions, coding style, surgical changes, goal-driven.

not rated 0 today A 50 tokens

nikira-studio/agent-core

Skill Claude CodeCodex

Start with workspacesync for the workspace scope and reuse its execution ID. Search memory for stable project facts and decisions. Write activity updates while working. A fresh activity can return a bounded sincelastactive fallback digest when the execution is not caught up; process it without treating it as complete…

not rated 0 changed 3d ago A 0 tokens original MIT

arwp-growth-loop

4231

dkharlanau/agent-ready-web-profile

Skill Claude CodeCodex

Run an evidence-backed website growth loop for Search, Google Discover and recommendations, generative Search, Bing AI citations, ChatGPT Search and agent readability. Use when asked to make a site rank or discover better, get into recommendations, improve AI-search visibility, apply current ARWP guidance, or…

not rated 0 changed 3d ago A 100 tokens original

blueocean-memory

4232

thammarongg/blueocean-vector

Skill Claude CodeCodex

Use at the start of any coding session to recall project context stored by other agents/tools, and every time you reach a decision a future session would otherwise have to work out again. Applies when starting work on a project, resuming after a break, switching from another tool (Codex, Cursor, Gemini/Antigravity…

not rated 0 11d ago A 106 tokens original MIT

excellent-project-docs

4233

mushroomTW/MushroomTW-Skills

Skill Codex

Write, improve, audit, or synchronize a repository's README.md and the companion files GitHub reads from the root or .github/ (CONTRIBUTING, CODEOFCONDUCT, SECURITY, SUPPORT, CHANGELOG, ARCHITECTURE, ROADMAP, GOVERNANCE, issue and PR templates), with every claim traced to repository evidence. Use when the user asks…

not rated 0 changed 3d ago A 151 tokens original MIT

agy-delegate

4234

PyModel/claude-agy-mcp

Skill Claude CodeCodex

Delegate a coding task to the Google Antigravity CLI (agy) as a separate implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use Antigravity…

not rated 0 4d ago A 132 tokens original MIT

codex-a2a-setup

4235

phamviet86/codex-a2a-gateway

Skill Claude CodeCodex

Configure or repair an installed Codex A2A Gateway on a workstation, including its Codex MCP client or inbound A2A service and Hermes client. Use for setup and readiness, not ordinary delegation.

not rated 0 2d ago A 49 tokens original Apache-2.0

devtwin

4236

JaydeepDhamecha/devtwin

Skill Claude CodeCodex

DevTwin gives an AI coding agent a live, structured view of a development environment. It answers the questions an agent normally has to guess at: what kind of project is this, what runtimes and dependencies does it need, what is actually installed, which services should be running, and why did that command just fail.

not rated 0 yesterday A 0 tokens original Apache-2.0

protocol-audit

4237

srmackey/insitu

Skill Claude Code

Audit a chair's composed Insitu protocol for contradictions, unresolved references, stale doctrine, unneeded weight, and shape. Use when asked to audit, review, or trim a protocol, when a chair's core feels heavy or wrong, or when two loaded rules seem to disagree. Produces a proposal and never edits. Not for…

not rated 0 today A 89 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: