intent-framed-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Intent Framed Agent

意图框架化Agent

Install

安装

bash

npx skills add pskoett/pskoett-ai-skills

bash

npx skills add pskoett/pskoett-ai-skills/intent-framed-agent

bash

npx skills add pskoett/pskoett-ai-skills

bash

npx skills add pskoett/pskoett-ai-skills/intent-framed-agent

Purpose

用途

This skill turns implicit intent into an explicit, trackable artifact at the moment execution starts. It creates a lightweight intent contract, watches for scope drift while work is in progress, and closes each intent with a short resolution record.

该Skill会在执行开始时将隐含意图转化为明确的、可追踪的成果物。它会创建一个轻量化的意图契约，在工作进行中监控范围偏离情况，并在每个意图结束时生成简短的完成记录。

Scope (Important)

适用范围（重要）

Use this skill for coding tasks only. It is designed for implementation work that changes executable code.

Do not use it for general-agent activities such as:

broad research
planning-only conversations
documentation-only work
operational/admin tasks with no coding implementation

For trivial edits (for example, simple renames or typo fixes), skip the full intent frame.

仅将该Skill用于编码任务。它专为可修改可执行代码的实现工作设计。

请勿将其用于以下通用Agent活动：

广泛的研究工作
仅规划的对话
仅文档编写的工作
无编码实现的操作/管理任务

对于琐碎的编辑（例如简单重命名或拼写错误修复），无需使用完整的意图框架。

Trigger

触发时机

Activate at the planning-to-execution transition for non-trivial coding work.

Common cues:

User says: "go ahead", "implement this", "let's start building"
Agent is about to move from discussion into code changes

在非琐碎编码工作的规划到执行过渡阶段激活。

常见触发信号：

用户说：“开始吧”、“实现这个”、“我们开始开发吧”
Agent即将从讨论阶段转入代码修改

Workflow

工作流程

Phase 1: Intent Capture

阶段1：意图捕获

At execution start, emit:

markdown

undefined

在执行开始时，输出：

markdown

undefined

Intent Frame #N

Outcome: [One sentence. What does done look like?] Approach: [How we will implement it. Key decisions.] Constraints: [Out-of-scope boundaries.] Success criteria: [How we verify completion.] Estimated complexity: [Small / Medium / Large]


Rules:
- Keep each field to 1-2 sentences.
- Ask for confirmation before coding:
  - `Does this capture what we are doing? Anything to adjust before I start?`
- Do not proceed until the user confirms or adjusts.

Outcome: [一句话描述。完成的标准是什么？] Approach: [我们的实现方式。关键决策。] Constraints: [超出范围的边界。] Success criteria: [我们如何验证完成情况？] Estimated complexity: [Small / Medium / Large]


规则：
- 每个字段限制在1-2句话。
- 编码前需请求确认：
  - `Does this capture what we are doing? Anything to adjust before I start?`
- 需等待用户确认或调整后再继续。

Phase 2: Intent Monitor

阶段2：意图监控

During execution, monitor for drift at natural boundaries:

before touching a new area/file
before starting a new logical work unit
when current action feels tangential

Drift examples:

work outside stated scope
approach changes with no explicit pivot
new features/refactors outside constraints
solving a different problem than the stated outcome

When detected, emit:

markdown

undefined

在执行过程中，在自然节点监控范围偏离：

在接触新区域/文件之前
在开始新的逻辑工作单元之前
当前操作看似偏离主题时

范围偏离示例：

超出既定范围的工作
方法变更但未明确说明转向
超出约束条件的新功能/重构
解决的问题与既定目标不符

检测到偏离时，输出：

markdown

undefined

Intent Check #N

This looks like it may be moving outside the stated intent.

Stated outcome: [From active frame] Current action: [What is happening] Question: Is this a deliberate pivot or accidental scope creep?


If pivot is intentional, update the active intent frame and continue. If not,
return to the original scope.

This looks like it may be moving outside the stated intent.

Stated outcome: [来自当前活跃的意图框架] Current action: [当前正在进行的操作] Question: Is this a deliberate pivot or accidental scope creep?


如果是有意转向，更新当前活跃的意图框架后继续。如果不是，则回到原始范围。

Phase 3: Intent Resolution

阶段3：意图收尾

When work under the active intent ends, emit:

markdown

undefined

当当前活跃意图的工作结束时，输出：

markdown

undefined

Intent Resolution #N

Outcome: [Fulfilled / Partially fulfilled / Pivoted / Abandoned] What was delivered: [Brief actual output] Pivots: [Any acknowledged changes, or None] Open items: [Remaining in-scope items, or None]


Resolution is preferred but optional if the session ends abruptly.

Outcome: [Fulfilled / Partially fulfilled / Pivoted / Abandoned] What was delivered: [简要的实际输出] Pivots: [所有已确认的变更，若无则填None] Open items: [剩余的范围内事项，若无则填None]


若会话突然结束，收尾步骤为可选，但优先执行。

Multi-Intent Sessions

多意图会话

One session can contain multiple intent frames.

Rules:

Resolve current intent before opening the next.
If user changes direction mid-task, resolve current intent as
```
Abandoned
```
or
```
Pivoted
```
, then open a new frame.
Drift checks always target the currently active frame.
Number frames sequentially within the session (
```
#1
```
,
```
#2
```
, ...).
Constraints do not carry forward unless explicitly restated.

单个会话可包含多个意图框架。

规则：

先解决当前意图，再开启下一个。
若用户在任务中途改变方向，将当前意图标记为
```
Abandoned
```
或
```
Pivoted
```
后解决，再开启新框架。
范围偏离检查始终针对当前活跃的意图框架。
在会话内按顺序为框架编号（
```
#1
```
,
```
#2
```
, ...）。
约束条件不会自动延续，除非明确重新说明。

Entire CLI Integration

Entire CLI 集成

Entire CLI: https://github.com/entireio/cli

When tool access is available, detect Entire at activation:

bash

entire status 2>/dev/null

If it succeeds, mention that intent records will be captured in the session transcript on the checkpoint branch.
If unavailable/failing, continue silently. Do not block execution and do not nag about installation.

Copilot/chat fallback:

If command execution is unavailable, skip detection and continue with the same intent workflow in chat output.

完整CLI：https://github.com/entireio/cli

当具备工具访问权限时，在激活时检测Entire：

bash

entire status 2>/dev/null

若检测成功，告知用户意图记录将被捕获到检查点分支的会话记录中。
若不可用/检测失败，静默继续。不要阻止执行，也不要反复提示安装。

Copilot/聊天回退方案：

若无法执行命令，跳过检测，在聊天输出中继续使用相同的意图工作流程。

Guardrails

约束规则

Keep it lightweight; avoid long prose.
Do not over-trigger on trivial tasks.
Do not interrupt on every small step.
Treat acknowledged pivots as valid.
Preserve exact structured block headers/fields for parseability.

保持轻量化；避免冗长的文字。
不要在琐碎任务上过度触发。
不要在每一个小步骤都打断工作。
将已确认的转向视为有效操作。
保留结构化块的准确标题/字段，以确保可解析性。

Interoperability with Other Skills

与其他Skill的互操作性

Use this skill as the front-door alignment layer for non-trivial coding work:

```
plan-interview
```
(optional, for requirement shaping)
```
intent-framed-agent
```
(execution contract + drift monitoring)
Implementation
```
simplify-and-harden
```
(post-completion quality/security pass)
```
self-improvement
```
(capture recurring patterns and promote durable rules)

This ordering helps reduce scope drift early and improve repeatability across tasks.

将该Skill作为非琐碎编码工作的前置对齐层：

```
plan-interview
```
（可选，用于需求梳理）
```
intent-framed-agent
```
（执行契约 + 偏离监控）
实现开发
```
simplify-and-harden
```
（完成后的质量/安全检查）
```
self-improvement
```
（捕获重复模式并推广持久规则）

该顺序有助于尽早减少范围偏离，并提高跨任务的可重复性。