一键导入
ans
/ans — conversational answer-only mode toggle. NEVER edit files or run shell. /ans end to exit. NOT for stopping mid-task to ask (just answer inline).
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。
菜单
/ans — conversational answer-only mode toggle. NEVER edit files or run shell. /ans end to exit. NOT for stopping mid-task to ask (just answer inline).
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
Development wisdom and workflow rules. NOT for project-specific conventions (those live in CLAUDE.md, edit via wisdom).
The `BUGS.md` open-issues queue — entry format, lifecycle, pruning to diary. NOT for the record-don't-fix policy (that's CLAUDE.md Bug Triage Protocol), NOT for resolved-bug history (use /diary), NOT for feature backlog (use TODO.md/specs).
Terminal demo GIF + MP4 recordings for READMEs and social (asciinema + agg + ffmpeg). NOT for general Makefile targets (use software) or GUI screenshots (use visual).
Go development. NOT for non-Go code (use rs, py, ts, tsx, or sh).
Humanize text: strip AI-isms and add real voice. NOT for drafting new copy (use writing).
Python development. NOT for shell scripting (use sh) or non-Python code.
| name | ans |
| description | /ans — conversational answer-only mode toggle. NEVER edit files or run shell. /ans end to exit. NOT for stopping mid-task to ask (just answer inline). |
| when_to_use | just answer, don't change anything, explain only, read-only mode, no edits, answer from context, stop touching files |
| user-invocable | true |
Toggle. /ans enters, /ans end exits.
Announce in one line: Answer-only mode ON. / Answer-only mode OFF.
ALLOW Edit/Write for diary and auxiliary docs only: .diary/*.md, MEMORY.md, BUGS.md, TODO.md, *.md specs/architecture/readme/changelog.
NEVER use Edit/Write for code files (.py, .ts, .js, .go, .rs, .toml, .yaml, .json, etc.); NEVER use NotebookEdit, Bash, TaskCreate, TaskUpdate.
ALWAYS use Read, Glob, Grep, WebFetch, WebSearch freely.
ALWAYS allow Agent — read-only research only; instruct subagents not to write files or run code.
ALWAYS ground answers in the context where /ans was invoked — the current file, topic, or recent diff. NEVER wander into unrelated areas unless explicitly asked.
Prefer reading nearby files over broad searches.