Back to Details

automate-me

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Automate me

帮我自动化

A guided flow for turning the user's working conventions into a skill agents will follow. The output is one 
-mode
skill tailored to them (e.g. 
jay-mode
, 
priya-mode
).
This skill orchestrates three others: an inline mining pass (see step 1), Cursor's built-in 
create-skill
(authoring), and the unslop skill (prose discipline). It sequences them; it doesn't replace them.
这是一个引导式流程，可将用户的工作习惯转化为Agent会遵循的skill。输出是一个为用户量身定制的
-mode
skill（例如
jay-mode
、
priya-mode
）。
该skill可协调另外三个skill：一个内联挖掘环节（见步骤1）、Cursor内置的
create-skill
（用于创作），以及unslop skill（用于规范文案）。它负责按顺序调用这些skill，而非替代它们。

Flow

流程

0. Check for an existing skill

0. 检查是否存在现有skill

Look for 
*-mode/SKILL.md
matching the user's handle, under the project's 
.cursor/skills/
or 
~/.cursor/skills/
. If one exists, confirm intent with 
AskQuestion
(unless they already said "update my skill" or similar):
  • Update the existing skill (default for repeat runs)
  • Start fresh (rare; ask why before doing it)
Update mode changes the rest of the flow:
  • Step 1 mines only history since the skill was last edited (
    git log -1 --format=%cI <path>
    ).
  • Step 2 asks what's changed or missing, not what to capture from zero.
  • Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted; revise ones with new evidence; add new sections only for genuinely new rules.
查找项目的
.cursor/skills/
或
~/.cursor/skills/
目录下，与用户标识符匹配的
*-mode/SKILL.md
文件。如果存在，使用
AskQuestion
确认用户意图（除非用户已经明确表示「更新我的skill」或类似需求）：
  • 更新现有skill（重复运行时的默认选项）
  • 重新创建（罕见操作；执行前询问原因）
更新模式会改变后续流程：
  • 步骤1仅挖掘该skill最后编辑时间之后的历史记录（
    git log -1 --format=%cI <path>
    ）。
  • 步骤2询问用户哪些内容有变化或缺失，而非从零开始捕捉需求。
  • 步骤4直接编辑现有文件。保留用户未提出异议的部分；根据新依据修订相关内容；仅为真正新增的规则添加新章节。

1. Mine their history

1. 挖掘用户历史记录

Locate the active workspace's transcripts before fanning out. The system prompt names the workspace's 
agent-transcripts/
directory. Use only that path. Don't glob across 
~/.cursor/projects/*/
. That crosses workspace boundaries and reads private chats from unrelated projects.
Survey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:
  • Response preferences (length, tone, format, "dumb it down" corrections)
  • Delegation habits (subagents, models, specialized workflows, parallelism)
  • Verification posture (what "done" means; unit tests vs live repro; reviewers)
  • Code and prose discipline (style, principles cited, lint/format tools)
  • Process conventions (worktrees, commits, PRs, review/merge tooling)
  • Meta preferences (fixing skills mid-task, proposing new ones)
Cross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence; lone signals are weak and usually get dropped.
在展开操作前定位当前工作区的对话记录。系统提示会指定工作区的
agent-transcripts/
目录。仅使用该路径，不要跨
~/.cursor/projects/*/
目录查找，这会跨越工作区边界，读取无关项目的私人对话。
在该范围内调查近期Agent对话中的重复模式。在历史记录的多个片段（例如最近2-4周的记录，拆分为3个片段，每个片段包含足够内容）上运行多个并行子Agent。每个片段挖掘子Agent读取父Agent提供的工作区范围内路径下的对话记录，寻找以下信号，并返回其发现的模式的简短结构化列表及依据指向。值得关注的默认信号包括：
  • 响应偏好（长度、语气、格式、「简化表述」类修正）
  • 委托习惯（子Agent、模型、特定工作流、并行处理）
  • 验证立场（「完成」的定义；单元测试与实际复现；审核人员）
  • 代码与文案规范（风格、引用的原则、lint/格式化工具）
  • 流程惯例（工作树、提交记录、PR、审核/合并工具）
  • 元偏好（任务中途修正skill、提出新skill）
在确定信号前需跨片段交叉验证。在2个及以上片段中出现的模式为高可信度；仅在单个片段中出现的信号可信度低，通常会被舍弃。

2. Ask the user directly

2. 直接询问用户

Mining misses intent that hasn't come up yet. Use the 
AskQuestion
tool (structured multi-choice) rather than asking the user to type from scratch. Lower cognitive load, higher hit rate.
Shape: one or two questions with 4-6 options each, 
allow_multiple: true
for category questions. Start broad ("Which areas matter most?"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.
Don't dump 20 questions. Two structured rounds plus one open question is usually enough.
挖掘可能会遗漏尚未出现的用户意图。使用
AskQuestion
工具（结构化选择题）而非让用户从头输入，这样可降低认知负荷，提高响应准确率。
形式：1-2个问题，每个问题提供4-6个选项，分类问题设置
allow_multiple: true
（允许多选）。先从宽泛问题入手（「哪些领域对你最重要？」），再针对用户选择的领域提出具体选项。结构化问答环节结束后，用一个开放式问题捕捉选项未覆盖的内容。
不要一次性抛出20个问题。通常两轮结构化问答加一个开放式问题就足够。

3. Cluster findings

3. 整合发现的内容

Group the combined signals into sections. Common ones (use only what applies):
  • Response style: length, tone, format.
  • Autonomy: how much to do without asking; MCP tool use.
  • Understand first: which skills to reach for when scoping or investigating a change.
  • Subagents: default, parallelism, model-to-task, specialized workflows.
  • Prose / code discipline: principles, lint tools, style guides.
  • Review and verify: repro posture, verification skills, live-testing tools.
  • Process: git worktrees, commits, PRs, review/merge tooling.
  • Skills: skill-authoring habits, fix-the-skill-first, proposing new skills.
The poteto-mode skill shows the shape. Read it for granularity. Don't copy its content; the user's rules are not the same as poteto-mode's.
将收集到的信号分组为不同章节。常见章节（仅使用适用的部分）：
  • 响应风格：长度、语气、格式。
  • 自主性：无需询问即可执行的操作范围；MCP工具的使用。
  • 先理解需求：梳理或调查变更时应调用哪些skill。
  • 子Agent：默认设置、并行处理、模型与任务匹配、特定工作流。
  • 文案/代码规范：原则、lint工具、风格指南。
  • 审核与验证：复现立场、验证skill、实时测试工具。
  • 流程：git工作树、提交记录、PR、审核/合并工具。
  • Skill相关：Skill创作习惯、优先修正Skill、提出新Skill。
poteto-mode skill展示了章节的结构。可参考其粒度，但不要复制内容；用户的规则与poteto-mode的规则不同。

4. Draft the skill

4. 起草Skill

Use Cursor's built-in 
create-skill
skill to author the skill. Placement:
  • Path: 
    .cursor/skills/<handle>-mode/SKILL.md
    in the project (or 
    ~/.cursor/skills/<handle>-mode/
    if the user prefers a personal skill).
  • Handle: the user's first name or chosen identifier.
  • Frontmatter 
    description
    : trigger on their name + 
    /<handle>-mode
    + "work in their style", not on generic keywords like "write code" or "review PR".
  • Frontmatter formatting: follow 
    create-skill
    's YAML rules. Keep 
    description
    as one YAML scalar; quote it or use 
    description: >-
    with indented continuation lines when punctuation or wrapping requires it.
  • Frontmatter 
    disable-model-invocation: true
    by default. Mode skills are heavy and opinionated; they should only apply when the user explicitly invokes them (by name or slash command), not auto-trigger on description matching. Opt out only if the user explicitly wants their mode to apply on every turn.
使用Cursor内置的
create-skill
skill来创作Skill。存放位置：
  • 路径：项目中的
    .cursor/skills/<handle>-mode/SKILL.md
    （如果用户偏好个人Skill，则存放在
    ~/.cursor/skills/<handle>-mode/
    ）。
  • 标识符：用户的名字或自定义标识。
  • 前置元数据
    description
    ：触发条件为用户名称 + 
    /<handle>-mode
    + 「按我的风格工作」，而非「编写代码」或「审核PR」等通用关键词。
  • 前置元数据格式：遵循
    create-skill
    的YAML规则。将
    description
    设为单个YAML标量；当包含标点或需要换行时，使用引号包裹，或采用
    description: >-
    加缩进换行的形式。
  • 前置元数据默认设置
    disable-model-invocation: true
    。Mode Skill内容详实且带有主观倾向，仅应在用户显式调用（通过名称或斜杠命令）时生效，不应通过描述匹配自动触发。仅当用户明确希望其Mode在每次交互时都生效时，才关闭该设置。

5. Iterate on prose

5. 优化文案

Apply the unslop skill and 
create-skill
's writing guidelines to every line. Both apply to any agent-read prose, not just skills.
Show the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly; a mode skill is not a manual.
对每一行内容应用unslop skill和
create-skill
的写作指南。这些规则适用于所有Agent可读的文案，而非仅Skill。
向用户展示草稿并收集反馈。通常需要多次迭代。果断删减内容；Mode Skill不是操作手册。

6. Land it

6. 落地Skill

Work in a worktree off main. Commit and open a PR so the user can review it. Don't push to main directly.
在主分支外的工作树中进行操作。提交并创建PR供用户审核，不要直接推送到主分支。

Guardrails

注意事项

  • Don't overfit to one conversation. A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.
  • Don't be clever. Restating other skills' contents, inventing metaphors, or writing "poetic" prose for an agent reader is cost without benefit. Keep it operational.
  • Reference, don't inline. Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.
  • Keep sections minimal. Only add a section if the user has a specific, non-default rule there. "Communicate clearly" is not a section. "Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel." is.
  • Name conventions generic. Use "the user" or "the human" in imperatives, not the author's first name. Others may read or adopt the skill.
  • Don't force symmetry. If a user has no process rules worth writing down, skip the Process section entirely. Sparse is fine; bloated is not.
  • 不要过度拟合单次对话。用户某次提到的偏好若在另一次对话中被否定，则属于干扰信息。需多次出现后才可将其编入规则。
  • 不要自作聪明。复述其他Skill的内容、创造隐喻、或为Agent读者撰写「富有诗意」的文案都是无用功。保持内容具备可操作性。
  • 引用而非嵌入。用户依赖的其他Skill应通过路径引用，而非粘贴内容。用户在其他地方维护的原则文档也同理。
  • 保持章节精简。仅当用户有特定的非默认规则时才添加章节。「清晰沟通」不属于有效章节；「使用短段落。对比选项时使用表格。仅当条目真正平行时才使用项目符号。」才是有效章节。
  • 命名惯例通用化。在命令式语句中使用「用户」或「人类」，而非作者的名字。其他人可能会阅读或采用该Skill。
  • 无需追求对称。如果用户没有值得记录的流程规则，可完全跳过「流程」章节。内容精简没问题，冗余才是大忌。

Evaluation

评估

A 
-mode
skill is subjective output. A 
create-skill
-style test/iterate benchmark loop isn't useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.
Run a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.
-mode
Skill是主观性输出。
create-skill
风格的测试/迭代基准循环在此处无用。只需与用户确认感受：内容是否符合他们的风格？是否遗漏了什么？确认后即可发布。
仅当实际使用中发现Skill的触发准确率存在问题时，才需要进行描述优化循环。

When not to use

不适用场景

  • User wants a task-specific skill (not working conventions): 
    create-skill
    alone, no mining required.
  • User wants to capture one narrow workflow (e.g. "how I write commit messages"): that's a regular skill, not a mode skill.
  • 用户需要任务特定的Skill（而非工作习惯）：仅使用
    create-skill
    ，无需挖掘。
  • 用户希望捕捉某一特定工作流（例如「我如何编写提交信息」）：这属于常规Skill，而非Mode Skill。

Reference files

参考文件

  • The poteto-mode skill: example of the output shape.
  • The unslop skill: prose discipline for every line.
  • Cursor's built-in 
    create-skill
    skill: skill authoring process and writing guidelines.
  • poteto-mode skill：输出结构示例。
  • unslop skill：逐行文案规范。
  • Cursor内置的
    create-skill
    skill：Skill创作流程与写作指南。