17,533 tagged ai-agent, measured the same way as everything else here.
Browse within: LLM 341agent 300cli 284openclaw 220ai-tools 197chatgpt 193agentic-ai 180cybersecurity 160Multi-Agent 132agentskills 123curated 122myclaw 122skill-collection 121coding-agent 113
Skill Codex
Use this skill when the user asks about crypto technical analysis, technical indicators, trend direction, overbought/oversold, support/resistance, momentum, volatility, volume, or money flow analysis. Trigger keywords include: technical analysis, indicator, trend, overbought, oversold, support, resistance, momentum…
User0856/snaprender-integrations
Skill Claude CodeCodex
Give your agent eyes on the web — screenshot any URL as an image file, or extract page content as markdown/text/HTML. Supports device emulation (iPhone, iPad, Pixel, MacBook), dark mode, full-page scroll, ad blocking. Uses exec tool with curl (NEVER the browser tool). $SNAPRENDERAPIKEY is pre-set. See instructions…
Skill Claude CodeCodex
Use when the user wants to publish a new release, says "release", "publish release", "cut a release", or "new version". Covers tag creation, CI-driven build, and troubleshooting.
Skill Claude CodeCodex
Code quality bar for implementation work: linting, formatting, tests, and test coverage for new features and bug fixes. Use when frontend-developer or backend-developer (or PM) delegates or reviews implementation.
Skill Claude CodeCodex
AI agent security gateway — policy enforcement, taint tracking, tool poisoning detection, DLP chain analysis, and SARIF output for CI/CD.
Skill Claude CodeCodex
Drive X from an AI agent: post, search, read, DM via MCP.
npcworkspace-cmyk/eric-task-master
Skill Claude CodeCodex
Run durable local Chrome automation with the installed Task Master CLI. Use when an Agent needs to create and execute a one-off browser task, follow its progress, or manage its Chrome Profile.
Skill Claude CodeCodex
Use when a manager, dispatcher, or safety director needs to have a coaching conversation with a driver — about a safety event (harsh brake, hard turn, distraction), an HOS violation, a customer complaint, a missed delivery, repeated minor incidents, or to deliver positive recognition. Covers conversation structure…
JunMystery/Agent-Guidance-Python
Skill Claude CodeCodex needs its repo
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, atomic commits, worktrees, change summaries, and disciplined version control for AI agents and developer teams.
Skill Claude Code
Audit an existing PostHog integration for correctness and best practices.
Skill Claude Code
App Store Connect (appstoreconnect.apple.com). Use this skill for ANY App Store Connect request — reading, creating, updating, and deleting data. Whenever a task involves App Store Connect, use this skill instead of calling the API directly.
Skill Claude CodeCodex
Compete in daily crypto prediction competitions on conviction.fm. Create AI agents with natural language strategies, enter token pair pools, and climb the leaderboard. Uses MCP to provide tools for pool data, agent creation, position entry, and strategy management.
asolfre/plantuml-rendering-skill
Skill Claude CodeCodex
Render PlantUML text and .puml files into image outputs (PNG). Use this skill whenever the user mentions PlantUML, .puml files, UML diagram source text, or asks to render/export/generate a sequence/class/activity/component diagram image. Trigger even when the user does not explicitly say "PlantUML" but provides…
drowned-fish1/deepseek-harness-skillx
Skill Codex
A meta-skill for finding and safely evaluating an outside agent skill when the skills already installed do not cover a task. It treats outside instructions as untrusted material until they have been reviewed.
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment - skill TDD: pressure scenarios, unaware subagents, fail-then-fix-then-pass loops.
guyuefangyuanl/deepseek-better-harness
Skill Claude CodeCodex
Use when auditing DSH or cross-harness skills, presets, hooks, tools, commands, MCP configuration, or other agent assets for discovery, routing, integrity, and safe ownership. Do NOT use for code-style review, raw session analysis, or repository outcome scoring.
Skill Claude CodeCodex
Use when building, extending, or fixing tools/plugins for DeepSeek Harness (dsh) — writing a dsh plugin entry module, registering a tool with defineTool, authoring parameters/output JSON Schemas, the dsh bundle manifest, or cordis.patch.yml, or when a plugin fails to load, a tool is missing from the agent, or tool…
SheldonZhuang/housing-sentinel-ai
Skill Claude CodeCodex
A tool for judging whether to buy property in 12 Chinese cities based on official transaction data. It compares an aggressive buying approach with a defensive wait-and-see approach.
Skill Claude CodeCodex
Runtime security layer for AI agent commerce — card credentials inject directly into the browser DOM via CDP, never entering the agent's context window. No SaaS, no login, fully local.
Skill Claude CodeCodex
Collective web intelligence for browser agents. Discover site capabilities, get CSS selectors, extract structured data, and report outcomes. When one agent learns how to use a website, every agent benefits.
Skill Codex
Verify whether an AI, automation, vendor, or agent claim represents a real external outcome rather than activity. Use before accepting claims such as completed, shipped, adopted, paid, hired, saved time, reduced cost, removed risk, fulfilled an obligation, or received a recipient response; when reviewing agent runs…
Skill Claude CodeCodex
Overtone intelligence toolkit. Retrieves contextually analyzed news AND answers emotional/narrative questions across coverage: tone distribution, anger/sadness/fear spike alerts for a topic (pollable), emerging under-reported concepts, topics whose dominant tone is shifting fastest, and hourly/daily tone timeseries…
Skill Claude Code
Use when answering questions about live football/soccer matches, scores, player profiles, team information, or league standings. Provides match summaries and player profile links from Vublox. For fan footage and full details, users should visit the match or profile page on Vublox.
Skill Claude CodeCodex
AI agent skill for Solana prediction markets. 76 MCP tools. Safe-by-default. Agent builds, user signs. Zero private keys.
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: