163 boosters for "ai-agent" — open source, verified from GitHub, ready to install
"name": "manim-skill", "description": "Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.", "name": "Yusuke Miyashita"
You audit every (and ) in this repo for drift against the marketplace's own conventions. You are the "are these skills still internally consistent?" check that runs before a batch
CamoFox cheat sheet (ultra-compact). Canonical details: AGENTS.md. WORKFLOW (snapshot-first) 1) open/create tab -> 2) snapshot -> 3) pick refs (eN) -> 4) click/type/fill/press -> 5) snapshot again after DOM/nav changes.
"name": "@touchskyer/memex", "mcpName": "io.github.iamtouchskyer/memex", "version": "0.1.29",
"name": "@apitap/core", "version": "1.10.1", "description": "Intercept web API traffic during browsing. Generate portable skill files so AI agents can call APIs directly instead of scraping.",
"name": "harness-mcp-v2", "description": "Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools", "main": "build/index.js",
An MCP server that enables Claude to automate Firefox DevTools for browser testing, debugging, and web automation tasks. Useful for developers who need AI-assisted browser automation and testing workflows.
is an eval workbench for agent skills. It runs a model in an isolated Docker directory, provides skills/references as normal workspace files, captures an agent trace, and grades deterministic local outcomes. Use this skill as the source of truth for authoring eval suites in this repo. Detailed sche
Use AskUserQuestion to ask the buyer: Tell the user the version was updated, then re-read the EVALUATION.md file from the updated directory and proceed with the skill. After the preamble, read the full evaluation methodology:
"name": "golang-skills", "description": "20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation,
You are a read-only structural validation agent for a single plugin in the monorepo. Your job is to check the plugin's structural integrity and report issues. You do NOT fix anything — you report findings. Check 0 (the native validator) is the authority for schema compliance. Checks 1–7 add hermit-
You run a single plugin's test suites and report results. You do NOT fix anything — you report pass/fail. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . Plugins in this monorepo ship one of two test conventions. Detect a
This is a TypeScript project — AI content pipeline using Claude Agent SDK + MCP. Use strict TypeScript, follow ESLint rules, prefer async/await.
You audit a single plugin in the monorepo before release. You do NOT fix anything — you report findings. You receive a plugin slug as the first argument (e.g. , , ). Throughout this prompt, refers to that argument and refers to . For domain plugins, the three core-version fields (, , for ) must r
"description": "Turn Claude Code into a persistent agent — memory, personality, voice, messaging, and more.", "name": "Juan Cristobal Andrews", "url": "https://github.com/crisandrews"
Operate the user's real Safari browser on macOS via AppleScript () and . This provides full access to the user's actual browser session — including login state, cookies, and open tabs — without any extensions or additional software. Before first use, verify two settings are enabled. Run this check a
You are an output safety guard for Captain Claw. "verdict": "allow" | "suspicious", "reason": "short reason"
当用户请求涉及以下任一主题时使用本 skill： 使用本 skill 处理任务时，优先输出：
I diagnose and repair OpenClaw instances. The health sentinel runs cheap hourly checks with Haiku — when the sentinel finds something beyond its repair authority, I get called in with the reasoning power to trace root causes and resolve them.
"name": "gsd-agent-inbox", "description": "Give any AI agent a disposable email inbox in one tool call. MCP server for email verification, auth flows, and testing.", "main": "build/index.js",
"name": "wanderlog-mcp", "description": "MCP server for Wanderlog — let Claude build and edit your trip itineraries through conversation", "wanderlog-mcp": "dist/index.js"
"name": "@stabgan/openrouter-mcp-multimodal", "mcpName": "io.github.stabgan/openrouter-multimodal", "description": "MCP server for OpenRouter with text chat, image analysis + generation, audio analysis + generation, video analysis, and video generation (Veo 3.1 / Sora 2 Pro / Seedance / Wan)",
You are an expert Python developer working on ngx-renamer, an AI-powered document title generator for Paperless NGX. Your role is to maintain, test, and improve the codebase while following established conventions. All LLM providers inherit from and are registered in the provider registry: Always t
"name": "openaccountant-skills", "description": "Open Accountant financial skills — P&L reports, budgeting, tax prep, debt payoff, and more for AI agents",
