Agent building

Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex).

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects).

HTTP fallback bridge for coordinator when MCP transport is unavailable

Validate and score a bounded, self-attested offline payment-assurance run record against the unpublished alpha challenge contract.

Council Dashboard: Open the live council launch board either inline in Codex or as the standalone browser workbench.

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable…

Use when collaborating with humans to produce publication-grade complex diagrams in editable PPT, especially for system architecture, dataflow, and…

Use when collaborating with humans to turn Markdown, DOCX, and structured visual assets into polished Word deliverables with explicit Chinese/English…

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation.

Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets.

Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging.

Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management.

Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation.

Run delivery when AI coding and ops agents take tickets.

Multi-agent board meeting protocol running a structured 6-phase deliberation with isolated C-suite contributions to prevent groupthink.

OpenAI Codex CLI and cross-platform skill authoring.

Context management engine for AI coding agents.

Manage parallel development with Git worktrees: creation with port allocation, environment sync, branch isolation, and cleanup.

Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports.

Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics.

Browser-based QA combining Chrome MCP control with Python analysis tools.

Multi-agent source security audit with a coverage ledger, independently verified findings, and machine-checked records.

Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously.

Prompt engineering and LLM evaluation.