Agent skills for OpenAI Agents SDK

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

Agent skill for scout-explorer - invoke with $agent-scout-explorer

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

Use when appending structured perf investigation notes and evidence.

Creates, tests, and refines platform-agnostic AI agent skills using a test-driven RED-GREEN-REFACTOR methodology.

Evaluate existing Agent skills found in third-party sources such as GitHub repositories, skill directories, industry reports, articles…

Discovers, composes, evaluates, and evolves multiple agent skills into verified, production-ready custom skill bundles.

Teaches the AI to design like a high-end agency.

Audits and validates AI agent skills against strict structural and pre-release packaging checklists.

Reference for the alpha agent-substrate/substrate project as an alternative ultra-scale control plane that shares snapshot and runtime…

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

Facilitates direct peer-to-peer communication and task handoffs between concurrent Claude Code sessions using built-in cross-session…

Standardizes the design and implementation of multi-agent teams for complex collaborative workflows.

Parallelizes software implementation by orchestrating specialized AI agent teams for concurrent module development.

Orchestrates specialized AI agent teams using an intelligent decision engine to solve complex, multi-dimensional development tasks.

Test AI agent systems including tool use, multi-turn conversations, error recovery, and non-deterministic outputs.

Finds and recalls past AI agent sessions across Cursor, Codex, Claude Code, and other hosts using activity keywords, projects, or session…

Agent 会话可视化 / session timeline: execution maps for Cursor, Codex, Claude Code, Workbuddy, kimi-code threads (ID or name)…

Builds, converts, and deploys pages to a Bricks Builder WordPress site using the agent-to-bricks CLI (`bricks`).

Tracks per-agent token usage and flags waste in parallel dispatch.

Diagnoses AI agent execution traces, tool logs, and failure cascades to pinpoint root causes with visual Mermaid flowcharts and evidence…