Unified search
Start with the task. Skillstore will show complete packs first, then individual skills when they are a better match.
Showing results for "agent"
Use these when you need one narrow capability instead of a whole pack.
Orchestrate Flow Nexus Agent Swarms
Coordinating many AI agents across cloud workflows is hard to plan and monitor. This skill gives patterns for Flow Nexus swarms, queues, templates, and workflow automation.
Why this variant is first
Protect AI Harnesses with HOL Guard
Local AI harnesses can expose risky tools, plugins, and configuration changes. HOL Guard guides controlled setup, approval review, evidence collection, and package verification.
Resolve ERC-8004 Trustless Agents
Teams need reliable agent identity and reputation context across chains. This skill guides Claude, Codex, and Claude Code through ERC-8004 resolution and AgentCard scaffolding.
Review Agent Skills Before Install
Installing a skill can expose files, accounts, tools, and payment flows. This skill reviews public skill text before install and returns risks, missing signals, and patch priorities.
Route Convex Development Workflows
Convex projects span functions, schemas, realtime, storage, agents, and security, so teams can lose time choosing guidance. This skill maps each request to the right specialized Convex skill and documentation source.
Use Your Browser Safely
Web tasks often need different access paths, from public sources to signed-in browser sessions. This skill helps Claude, Codex, and Claude Code choose the least intrusive workflow.
Debug Failures With Root Cause Discipline
Bug fixes often fail when agents patch symptoms before understanding causes. This skill guides Claude, Codex, and Claude Code through structured investigation and verification.
Improve Claude Code Workflows
Unclear prompts and crowded sessions reduce coding quality. This skill provides practical workflows for planning, verification, context control, automation, and independent review.
Build Claude Code Skill Templates
Creating reusable AI skills requires consistent files and metadata. This skill guides Claude Code and Codex through a structured template workflow.
Evaluate Google ADK Agents with agents-cli
Agent teams need repeatable evidence before changing prompts, tools, or deployment settings. This skill guides dataset design, metric selection, grading, comparison, and failure analysis for Google ADK agents.
Build A2A Protocol Agents
Teams need a practical path to connect agents across frameworks. This skill guides A2A servers, clients, Agent Cards, streaming, and orchestration.
Debug Root Causes Systematically
Random fixes waste time and often create new defects. This skill guides Claude, Codex, and Claude Code through evidence gathering, hypothesis testing, and verified fixes.
Why this variant is first
obra-systematic-debugging
2026-09-09
cycleaddict-systematic-debugging
2026-09-09