tk-wizard

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

User-Run Wizard

用户执行向导

Guide
host-session
procedures that users must perform themselves. Internally, strictly track steps, value sources/destinations, secrecy, and safety boundaries, but do not dump them to the user like an approval document.
Keep the conversation natural and the state strict.
Initially describe the full journey in only 1–3 sentences, then naturally guide the user through one action they must take now. Do not repeatedly confirm already completed steps. 사용자가 action이나 비가역 confirmation을 선택해야 하면 host별 native structured question surface를 우선 사용합니다 (Claude Code: AskUserQuestion; Codex: request_user_input; Hermes: clarify). unavailable하면 같은 안내를 plain chat으로 fallback하고 secret 자체를 tool input으로 수집하지 않습니다.
引导用户必须亲自完成的
host-session
流程。内部需严格追踪步骤、值的来源/去向、保密性及安全边界,但不得像审批文档一样将这些信息直接展示给用户。
保持对话自然,状态管控严格。
最初仅用1-3句话描述完整流程,然后自然引导用户完成当前必须执行的一项操作。无需反复确认已完成的步骤。 当用户需要选择操作或不可逆确认时,优先使用对应host的原生结构化提问界面(Claude Code:AskUserQuestion;Codex:request_user_input;Hermes:clarify)。若无法使用,则退化为普通聊天形式进行引导,且不将secret本身作为工具输入收集。

Scope

适用范围

Applicable examples:
  • provisioning
    and
    dashboard
    setup
  • Issuing and placing
    credential
    /
    secret
    values
  • login
    , MFA, OTP, CAPTCHA,
    passkey
  • permission
    /
    keychain
    /
    device
    pairing
  • Human-only steps during
    migration
    /
    cutover
Routine code/CLI tasks the
agent
can safely execute, product decisions, and
acceptance
verification
are outside this skill's scope.
适用场景示例:
  • provisioning
    dashboard
    设置
  • credential
    /
    secret
    值的发放与配置
  • login
    、MFA、OTP、CAPTCHA、
    passkey
    相关操作
  • permission
    /
    keychain
    /
    device
    pairing
    配对
  • migration
    /
    cutover
    过程中仅能由人工完成的步骤
agent
可安全执行的常规代码/CLI任务、产品决策及
acceptance
verification
验收验证不在本技能的适用范围内。

Research and Planning

调研与规划

upstream provenance
또는
adaptation
판단이 필요할 때만 upstream 증류를 읽고, 일반
wizard
실행에서는 읽지 않습니다.
First read the
repository
and current
host
evidence
to build this internal state:
  • Full journey and sequence
  • Each value's
    source
    /
    destination
  • secret
    /
    public
    classification
  • Already completed steps
  • Steps the user must perform
  • Irreversible steps
  • Verifiable
    completion
    signal
Do not invent unknown UI, buttons, URLs, or commands. Where evidence is unavailable, describe only that point as
Unverifiable
.
For example, tell the user:
text
대략 키 발급 → 로컬 저장 → 연결 확인 세 단계면 끝납니다.
키 값은 대화에 남기지 않을게요. 먼저 발급 화면까지 들어가 주세요.
Guide the next step only after observing the previous step's
completion
.
仅当需要判断
upstream provenance
上游来源或
adaptation
适配性时,才阅读上游提炼,常规
wizard
向导执行无需阅读。
首先读取
repository
仓库及当前
host
主机的
evidence
证据,构建以下内部状态:
  • 完整流程与步骤顺序
  • 每个值的
    source
    来源/
    destination
    去向
  • secret
    机密/
    public
    公开的分类
  • 已完成的步骤
  • 用户必须执行的步骤
  • 不可逆步骤
  • 可验证的
    completion
    完成
    signal
    信号
不得虚构未知的UI、按钮、URL或命令。当证据缺失时,仅将该环节标注为
Unverifiable
无法验证。
例如,告知用户:
text
大致分为密钥发放 → 本地存储 → 连接验证三个步骤即可完成。
我不会在对话中留存密钥值,请先进入发放页面。
仅在观察到上一步的
completion
完成状态后,再引导下一步操作。

Secrets and Authentication

机密信息与身份验证

Never
echo
a
secret
or store it in
chat
, Markdown,
log
, or
eval
. When necessary, use only
hidden
/
ephemeral
input
at execution time.
Do not prompt users to paste OTP,
password
,
token
,
session
value
, or
recovery
code
into the conversation. Do not retain even non-secret
identifier
values unless needed for the task.
If a
helper
is needed, create it as a one-time
user-run
helper
and preserve these semantics:
  • Separate normal input from
    secret
    input
  • Do not
    persist
    secret
    values by default
  • Clearly show the
    destination
  • Do not silently overwrite existing values
  • Statically validate with
    bash -n
    and, when possible,
    shellcheck
  • Explain how to delete or retain it afterward
绝不可
echo
输出
secret
机密信息,也不得将其存储在
chat
聊天记录、Markdown、
log
日志或
eval
执行环境中。必要时,仅在执行阶段使用
hidden
隐藏/
ephemeral
临时输入框。
不得提示用户将OTP、
password
密码、
token
令牌、
session
会话
value
值或
recovery
恢复
code
码粘贴到对话中。除非任务必需,否则即使是非机密的
identifier
标识值也不得留存。
若需要辅助工具,需创建一次性的
user-run
用户执行
helper
辅助工具,并遵循以下规则:
  • 将普通输入与
    secret
    机密输入分离
  • 默认不
    persist
    持久化存储
    secret
    机密值
  • 清晰展示
    destination
    去向
  • 不得静默覆盖现有值
  • 使用
    bash -n
    进行静态验证,尽可能同时使用
    shellcheck
    检查
  • 事后说明如何删除或保留该工具

🔴 CHECKPOINT · 🛑 STOP · Safety Confirmation

🔴 检查点 · 🛑 终止 · 安全确认

Treat irreversible, production-affecting, or unverifiable steps below as hard stops; ordinary reversible steps remain frictionless.
Do not ask for approval at every ordinary
reversible
step. Require explicit confirmation only for actions that change the user's decision, are difficult to reverse, or affect
production
.
Example:
text
여기서 기존 production key를 폐기하면 현재 서비스에 영향이 생길 수 있어요.
새 key 연결이 정상인지 먼저 확인한 뒤 폐기하는 걸 권장합니다.
새 key 확인 후 기존 key를 폐기할까요?
If no safe verification path exists, do not rush execution; explain the state as
Blocked
or
Unverifiable
.
将不可逆、影响生产环境或无法验证的步骤视为强制终止节点;普通可逆步骤则保持流畅无需中断。
无需对每个普通的
reversible
可逆步骤请求批准。仅当操作会改变用户决策、难以撤销或影响
production
生产环境时,才要求明确确认。
示例:
text
在此处废弃现有生产密钥可能会影响当前服务。
建议先确认新密钥连接正常后再进行废弃操作。
确认新密钥正常后,是否要废弃旧密钥?
若不存在安全的验证路径,请勿急于执行;需将状态说明为
Blocked
受阻或
Unverifiable
无法验证。

Completion

完成阶段

At the end, briefly explain what the user completed and how it was verified. Do not expose a
stage
table
,
secret
inventory
, internal state machine, or long
receipt
by default.
Use exactly one actual state from
Status: Pass | Pending | Blocked | Unverifiable | Fail
as the
terminal
token
.
结束时,简要说明用户完成的内容及验证方式。默认不得暴露
stage
阶段
table
表格、
secret
机密
inventory
清单、内部状态机或冗长的
receipt
回执。
需使用
Status: Pass | Pending | Blocked | Unverifiable | Fail
中的某一实际状态作为
terminal
终结
token
标识。