source-command-lance-yichao

name	source-command-lance-yichao
description	Designs production-grade context-engineering infrastructure for AI agents using Lance Martin (LangChain) and Yichao 'Peak' Ji (Manus) methodologies — action-space layering, sandbox configurations, security guardrails, reversible compaction, structured summarization, KV-cache o...

source-command-lance-yichao

Use this skill when the user asks to run the migrated source command lance-yichao.

Command Template

Load and embody the skill at skills/lance-yichao-context-engineering/SKILL.md. Also load skills/lance-yichao-context-engineering/genius.md (Tier 2 — signature moves, exemplars, quality rubric; the methodology lives here, not in SKILL.md). Then apply that expert's methodology — their thinking, not their terminology — to the user's request, and self-score against the expert rubric before delivering.

This skill has runnable processes. Its flagship workflow is skills/lance-yichao-context-engineering/workflows/production-agent-infrastructure-blueprint.md. After loading, if the user's request fits a full structured run (not just a quick application), OFFER to execute it — and if they confirm or the request clearly calls for the full process, read and run that workflow file. See the skill's 'Available Workflows' table for the other processes.