菜单
Structural audit skill invoked against plans prior to execution to resolve missing edge 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。
Instructions for triggering external Context7 connections
Lightweight research-plan-implement workflow for small tweaks, isolated bugfixes, copy edits, and low-blast-radius polish in this repo. Use when the change can be understood from 1-3 files and stays inside one subsystem without changing shared data flow.
Implements tree-based attack branching and prompt refinement optimization.
Fetch external library or framework documentation only when local docs are insufficient.
Guidance for JudgeAgent scoring, guardrail synthesis, and anti-hallucination validation work.
Full research-plan-implement workflow for new features, architectural updates, multi-file changes, or any task with non-trivial blast radius in RedThread.
基于 SOC 职业分类
| name | Implementation Gap Check |
| description | Structural audit skill invoked against plans prior to execution to resolve missing edge cases. |
You should execute this skill prior to submitting a complex implementation_plan.md for human review, or when the user explicitly requests an audit.
Evaluate the proposed logic against the foundational models described in docs/AGENT_DECISION_TREE.md:
Generate a gap analysis report in the plan's Open Questions section targeting the user.
