菜单
Guidelines for ensuring architectural changes are validated against core use cases.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Guidelines for creating, reviewing, and improving agent skills.
Guidelines for validation, staging, amending, and commit messages.
Guidelines for dependency injection patterns.
Orchestrates efficient read and write interactions with the engram unified memory store via MCP tools. Provides deterministic workflows for decomposing observations into atomic memories, composing four-dimensional queries (context, similarity, relationship, time) for maximum retrieval accuracy, managing agent-managed focus context, and linking memories into associative webs at write time. Ensures memories are discoverable, precisely ranked, and structurally connected across sessions.
Guidelines for dual-use architecture (CLI and Go Library), dependency separation, and extensible registry patterns.
Guidelines for configuring the pi.hitl CEL-based permission sandbox via permissions.yaml files.
| name | agent-validation |
| description | Guidelines for ensuring architectural changes are validated against core use cases. |
All designs must be evaluated against practical, real-world constraints to ensure Dux remains focused on delivering functional "agents."
When formulating an implementation_plan.md or making a significant architectural design decision, you MUST include a checklist explicitly validating the impact of those changes against the following 5 core example agents:
docs/tutorials/ within the same pull request/effort. Currently, the tutorials detail "Current Limitations/Known Gaps"; when these gaps are closed, the documentation must reflect the newfound capabilities.