{"name":"mcorbett51090-prompt-engineering-plugins-prompt-engineering","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"mcorbett51090-prompt-engineering-plugins-prompt-engineering","source":{"source":"git-subdir","url":"https://github.com/mcorbett51090/ravenclaude","path":"plugins/prompt-engineering"},"description":"Prompt & context engineering team — 3 agents (prompt-architect, prompt-implementation-engineer, prompt-reliability-engineer) that own the layer between the model and the app: prompt & context strategy (task decomposition, pattern selection across few-shot / CoT / decomposition / role, system-vs-user structure), the output-format contract (JSON mode, tool/function-calling schemas, few-shot curation, token budgeting), and prompt reliability (eval sets & regression, prompt versioning/CI, prompt-injection & jailbreak defense at the prompt layer). Provider-neutral. 4 skills, a 2-doc knowledge bank with 4 Mermaid decision trees + a dated 2026 reference, 5 best-practices, 2 templates. Seams: which model → ai-coding-model-guidance / claude-api; retrieval → ai-rag-engineering; eval at scale → llm-evaluation-engineering; adversarial testing → ai-red-teaming; the app → claude-app-engineering / backend-engineering. Requires ravenclaude-core@>=0.7.0.","version":"0.1.0","strict":true,"keywords":["prompt-engineering","context-engineering","llm","few-shot","chain-of-thought","structured-output","json-mode","tool-use","function-calling","prompt-injection","jailbreak-defense","prompt-eval","prompt-versioning","guardrails","token-budget"],"category":"development"}]}