1,516 tagged ai-agent, measured the same way as everything else here.
Browse within: claude-code-plugin 196ai-tools 161ai-skills 151ai-coding 137ai-assistant 114plugin 110Workflow Automation 106agent-orchestration 95ai-automation 83ai-workflow 76agent-os 64antigravity 63Autonomous 61ai-governance 54
Agent Claude CodeCursor
System architect. Use proactively when designing cross-cutting features, API or schema changes, auth flows, or recording technical decisions before FE/BE implementation.
Agent Claude Code
Read-only defect hunter for swarm workflows. Given a scope and a lens, finds real, evidenced defects and returns them as structured findings. Never edits files.
Agent Claude Code
This document defines the design for a portable agent skill that teaches any agent how to use Fabric correctly.
Agent Claude Code
Callwright is a self-hosted, single-user Node.js MCP server that validates, composes, and dispatches outbound calls through Retell, then retrieves and learns from their outcomes.
Agent Claude CodeOpenCode
OpenCode E2E worker.
Agent Claude Code
Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, creating distribution plots, running hypothesis tests on A/B experiment data, comparing model metrics across…
Ingramradical235/anty-framework
Agent Claude Code
KPI tracking, post-execution verification, root cause analysis, cycle detection, retention cohort analysis, unit economics, and anti-pattern detection.
Agent Claude Code
Deep, sourced web-research engine. Confirms every datum with ≥2 independent sources, extracts verbatim quotes, flags contradictions and unknowns. Output: findings+provenance JSON artifact (written to file) + one-line return. Shared worker for ds-research and ds-brief.
Agent Claude Code
You are a QA Specialist with deep expertise in software testing strategy, test automation, and quality engineering. You believe that testing is not a phase—it is a practice that happens throughout development. You are pragmatic: you know when 100% coverage is unnecessary and when 80% coverage is dangerous.
originalrashmi/rc-engine-product-framework
Agent Claude Code
RC Engine uses a parent-child agent model. The alpha agent (defined in /CLAUDE.md) orchestrates four specialized child agents. Each child agent owns a specific set of tools and operates within strict boundaries.
Agent Claude Code
An agent setup that adds long-term memory and proactive suggestions to a daily programming assistant.
huuanh20/awesome-ai-agent-skills
Agent Claude Code
General-purpose Playwright screenshot agent. Auto-detects capture mode from inputs — section-centered viewport (show-off), element clip, or full page. Optional BGSOURCE triggers composite step (background photo + card overlay). Spawned by /show-off and any task needing screenshots.
scitex-ai/claude-code-telegrammer
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Claude Code
Research assistant for PubMed Search MCP plus Zotero Keeper MCP. Uses collaboration-safe search, duplicate-check, and import workflow.
Agent Claude Code
Independent verification agent. Checks outputs from other agents for register violations, missing sources, logical errors, and drift. Use when verifying facts, reviewing code quality, or auditing conclusions.
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Claude Code
Analyzes RFID card dump files offline — Mifare Classic/Ultralight dumps (sector trailers, access-bits decode, value blocks, ASCII content) and LF sniff captures. Use when the user wants to understand what's inside a dumped card without touching the device.
eibrahim/dedicated-mac-mini-ai-bot-setup-mcp
Agent Claude Code
Use this agent when a founder, operator, or agency owner wants to evaluate a dedicated Mac mini AI operator setup, choose the first workflow to automate, compare a managed local operator against API-token-heavy SaaS stacks, or prepare an install handoff. This agent is read-only and should never create fake leads…
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: