メニュー
Inject VCP security and architecture standards into context. Run this at session start or after context compaction so the AI internalizes rules while writing code.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build stage — per-unit implementation with fresh context and mechanical backpressure
PK Stage — multi-AI competitive debate with iterative consensus. Sends a topic to all configured AI participants simultaneously, synthesizes the best approach, then iterates until consensus or max rounds.
Code review stage — multi-AI semantic drift detection with AC tracing
Dev Buddy web configuration portal for managing presets and pipeline config
Decomposition stage — break features into small, independently testable units of work
Discovery stage — multi-AI codebase and running app exploration
| name | vcp-context |
| description | Inject VCP security and architecture standards into context. Run this at session start or after context compaction so the AI internalizes rules while writing code. |
| user-invocable | true |
| allowed-tools | Read, Glob, Bash |
| argument-hint |
This skill is a thin slash-command launcher. The authoritative workflow lives in the VCP MCP prompt vcp_context and resource vcp://prompts/vcp-context.
vcp_context with the caller-supplied host, current project path, and raw command arguments.get_prompt({ command: "vcp-context", host, project_path, arguments }) and follow the returned prompt text.detect_installation, validate_plugin_root, or resolve_config. Use those tools for deterministic work.Do not reimplement the workflow in this file; update the MCP prompt instead.