菜单
Use when changing ACC prefs (talk style, learning, automations, memory path). Not for code tasks.
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
Use when a plan or concrete tasks exist and user said build/go/implement. Not to invent scope or claim done without verify.
Use when goal/spec is clear and you need ordered tasks before writing code. Not while still clarifying.
Use when about to claim done/works/fixed, or user asks test/check/prove. Run evidence; not for pure planning chat.
Use when another installed plugin/skill may do the job better, or to route specialists. ACC stays workflow owner.
Use when user wants an explicit recorded decision or blocker saved to artifacts. Not silent monitoring.
Use when request is too vague to plan or build. Not when goal and constraints are already clear.
| name | settings |
| description | Use when changing ACC prefs (talk style, learning, automations, memory path). Not for code tasks. |
Script root: ACC_PLUGIN_ROOT from SessionStart (hooks inject). PLUGIN_ROOT is hooks-only.
Use $settings to inspect or change user preferences.
Reply rule:
normal, caveman-lite, caveman-stricttrigger-auto.codex/anyone-can-code/memory/notes, user-changeablenone, obsidian, or future acc-viewer unavailableask, project, user, or shared.codex/anyone-can-code/settings/preferences.jsonCommunication mode changes surfaced communication only. It does not control hidden reasoning.
When showing or changing communication mode, dry-run tone with the live helper:
python3 "<ACC_PLUGIN_ROOT>/scripts/comm_contract.py" caveman-strict "Feature implemented successfully."
That script is product path (not tests).
When this skill's job is finished: