Skill Claude CodeCodex
Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
5 1mo ago A 41 tokens
copy · 98% MIT
Skill Claude CodeCodex
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
5 1mo ago A 59 tokens
copy · 98% MIT
aegisops-ai
03Skill Claude CodeCodex
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.
5 1mo ago A 41 tokens
copy · 95% MIT
Skill Claude CodeCodex
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
5 1mo ago A 22 tokens
original MIT
Skill Claude CodeCodex
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks.
5 1mo ago B 38 tokens
copy · 97% MIT
Skill Claude CodeCodex
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly…
5 1mo ago A 170 tokens
original MIT
Skill Claude CodeCodex
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
5 1mo ago A 51 tokens
copy · 98% MIT
agent-memory
08Skill Claude CodeCodex
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
5 1mo ago A 18 tokens
copy · 92% MIT
Skill Claude CodeCodex
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
5 1mo ago A 25 tokens
copy · 97% MIT
Skill Claude CodeCodex
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
5 1mo ago A 38 tokens
copy · 97% MIT
Skill Claude CodeCodex
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
5 1mo ago A 41 tokens
copy · 95% MIT
Skill Claude CodeCodex
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
5 1mo ago A 24 tokens
copy · 92% MIT
agent-squad
13Skill Claude CodeCodex
Main agent orchestrator that coordinates a specialized squad of agents.
5 1mo ago A 15 tokens
copy · 97% MIT
alex
14Skill Claude CodeCodex
Turns requirements into a precise, dependency-aware implementation plan.
5 1mo ago A 13 tokens
copy · 97% MIT
aria
15Skill Claude CodeCodex
Designs the data model, API contracts, and structural foundation of the system.
5 1mo ago A 18 tokens
copy · 100% MIT
dep
16Skill Claude CodeCodex
Handles containerization, CI/CD pipelines, and deployment setup.
5 1mo ago A 14 tokens
copy · 97% MIT
luna
17Skill Claude CodeCodex
Reviews code for objective correctness, security, and reliability.
5 1mo ago A 14 tokens
copy · 95% MIT
mason
18Skill Claude CodeCodex
Produces clean, functional code that matches the architecture and checklists.
5 1mo ago A 16 tokens
copy · 97% MIT
max
19Skill Claude CodeCodex
Cleans up and improves existing code without changing behavior.
5 1mo ago A 13 tokens
copy · 97% MIT
quinn
20Skill Claude CodeCodex
Proves the system works by writing and executing comprehensive test suites.
5 1mo ago A 16 tokens
copy · 97% MIT
rex
21Skill Claude CodeCodex
Translates user intent into a precise, unambiguous specification and requirements.
5 1mo ago A 17 tokens
copy · 95% MIT
Skill Claude CodeCodex
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
5 1mo ago A 57 tokens
copy · 100% MIT
Skill Claude CodeCodex
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that…
5 1mo ago A 73 tokens
copy · 100% MIT
agentfolio
24Skill Claude CodeCodex
Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.
5 1mo ago A 23 tokens
copy · 91% MIT