Stats
Actions
Tags
From transformers
Defines core principles for Transformers agents: human-in-the-loop, honesty, impact analysis, and scope discipline.
How this skill is triggered — by the user, by Claude, or both
Slash command
/transformers:core-principlesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
@${CLAUDE_PLUGIN_ROOT}/knowledge/core-principles.md
@${CLAUDE_PLUGIN_ROOT}/knowledge/core-principles.md
npx claudepluginhub shankarkakumani/transformers --plugin transformersAnalyzes project requirements and recommends optimal Anthropic architectures using Skills, Agents, Prompts, and SDK primitives for scalable AI systems.
Working with AI coding agents — User Sovereignty, agreement-as-signal, Karpathy/Willison framing, per-model overlays, and the rule to measure your prompt nudges.
Provides patterns and principles for building reliable autonomous agents: agent loops (ReAct, Plan-Execute), goal decomposition, reflection, and production guardrails. Useful when designing constrained, domain-specific agents.