Agent skills for Grok Build

A simple Polish agent memory system – identity (CLAUDE.md), on-demand map (MEMORY.md), client notes and learning loop (uwagai.md)…

End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap…

Root cause analysis on production LLM traces.

Read-only observation of an agent's parent, siblings, and direct children.

Coordinates multi-agent workflows across 251 specialized domain roles with centralized task dispatching and independent quality review…

Meta-skill that orchestrates all agents of the ecosystem.

Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Design and deploy AI agent identities, multi-agent teams, and role-specific profiles for Hermes Agent.

Port Claude Code plugins to Codex or Agy packages.

Transforms vague problems into structured, agent-solvable problem briefs and evaluates their automation feasibility.

MUST USE when user wants to research/search/look up/find anything on the internet — e.g. "research this topic", "do a deep dive on X"…

Give your AI agent eyes to see the entire internet. 17 platforms via CLI, MCP, curl, and Python scripts.

Look up which agent or team owns a kind of work in this repository.

The contract for the sdlc-agent-result-persist CLI — its modes, its flags, the paths it composes, the line grammar of the round log it…

Detailed review process, v2 validation checklist, and scoring methodology for agent definition reviews

Worker that runs parallel external agent reviews (Codex + Gemini) on Story/Tasks.

Use this skill when an agent is about to follow, publish, or delegate a runbook and needs a local readiness check first.

Enforces deterministic code-level safety boundaries, idempotency, human-in-the-loop approvals, and concurrency isolation in AI agent…

Use this skill before an agent asks for approval to send, publish, delete, write to an external system, or otherwise create side effects.

Use when: (1) Starting a long-running experiment that may span multiple sessions/disconnects, (2) Resuming work after a break and needing…