Transforms vague or high-impact product/engineering changes into scoped, verifiable acceptance criteria. Useful for clarifying features, de-risking security/data/migration/integration changes, or preparing handoff artifacts for another agent.
How this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:intent-driven-developmentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
产出有用的验收标准,而不是把规格变成仪式。先检查可用上下文,暴露真实歧义,并选择适合工作本身及其风险的验证方法。
产出有用的验收标准,而不是把规格变成仪式。先检查可用上下文,暴露真实歧义,并选择适合工作本身及其风险的验证方法。
/intent-driven-development 显式调用不要在琐碎编辑、直接的单行修复、活跃调试会话、代码审查请求,或验收条件已清楚的实现请求上激活。
[revised],更新 scope 或验证方法,递增修订号,并只重新呈现变更的标准Quick Capture — “Add CSV export to the dashboard”
Goal: Authenticated users can download dashboard data as a CSV file.
In scope: Export of currently filtered rows; filename includes date.
Out of scope: Scheduled exports, email delivery, Excel format.
Assumptions: Max row count is under 10k; no PII in exported fields.
AC-001: Export generates file with correct headers
- Scenario: authenticated user, at least one data row visible
- Action: click "Export CSV"
- Expected: browser downloads file with columns [id, name, created_at]
- Must not: expose internal fields or rows belonging to other users
- Verification: automated integration test + manual schema spot-check
- Priority: Required
Full Acceptance Brief 触发 — “Migrate user auth to OAuth”
Auth 变更 + 外部依赖 + 已有 session 数据 → Full Brief,含 Risk Review 表、session invalidation 策略的 blocking decisions,以及显式 rollback AC。
现有 spec 审查 — 用户粘贴 PRD
技能审查它是否缺少 scope 边界、不可验证的要求(“the system shall be fast”)和静默假设,然后返回修正或补充的标准,无需重新开始 discovery。
[revised]、说明约束、调整 scope 或验证方法),递增修订号,并只把变更后的标准重新呈现给用户后再继续。只有当修订改变 blocking decision 或实质降低安全或正确性保证时,才要求显式确认。使用最小有用输出。
用于清晰但非平凡的变更,风险低或中。产出:
除非存在运行规则中的 blocking 风险,或用户特别要求先出规格,否则不要为批准而延迟实现。
用于含糊、跨系统、安全敏感、改数据、迁移、compliance 或高成本变更,或用户要求 handoff artifact。产出下方完整模板,并在有风险的实现前对未解决的 blocking decisions 请求确认。
当用户已提供 PRD、issue、plan 或验收标准时:
提取或询问:
避免问关于无关风险的通用问题。
当本地或关联 artifact 可用时,只检查所需部分:
把已发现事实与用户提供的假设分开记录。如果上下文无法检查,说明什么是未知的并提聚焦问题。
Repository 揭示技术事实——系统今天如何表现、它的约定和 contracts。它不揭示产品或业务约束:业务规则、compliance 与监管义务、合同 SLA、定价、data-retention policy、优先级和目标用户。绝不从代码或命名重建它们。只从用户或权威产品 artifact 捕获它们,并在那之前列为待确认假设。
说明:
使用 AC-001、AC-002 等。每条标准必须描述可观察行为和恰当验证方法;标准和测试不必一一对应。
对每条适用标准包含:
不要使用 “correctly”、“securely”、“fast”、“intuitive” 或 “robust” 等词,除非定义了可观察证据或记录为人工审查判断。
考虑这些类别,但只纳入适用的:
| 类别 | 何时纳入 | 典型证据 |
|---|---|---|
| Happy path | 新增或变更的用户可见行为 | 成功 workflow 或状态转移 |
| Validation | 变更接受输入 | 拒绝畸形或边界值且不发生 mutation |
| Authorization/privacy | 数据或操作有访问边界 | 拒绝访问且不泄漏敏感信息 |
| Persistence/migration | 存储数据或 schemas 变更 | 向后读取、迁移、rollback 或备份行为 |
| Compatibility | 公共 API、文件、事件或客户端可能破坏 | 现有 contract 或 fixture 仍有效 |
| Failure recovery | 存在网络、服务或异步失败 | 无部分状态,或有清晰 retry/degraded 行为 |
| Idempotency/concurrency | 重复或同时写入可能发生 | 无重复副作用或无效终态 |
| Performance | 某个用户或服务阈值重要 | 定义测量条件和阈值 |
| UX/accessibility | 有人与结果交互 | 键盘、反馈、错误恢复、视觉/人工审查 |
对 Full Acceptance Brief 使用此模板。Quick Capture 时省略无关 sections。
# Acceptance Brief: <Change Name>
**Status:** Draft | Approved | Implemented | Verified
**Revision:** <number>
**Prepared for:** <user/team/agent, when known>
**Approval required before risky work:** Yes | No - <reason>
## Revision Log
| Rev | Date | Changed criteria | Reason |
| --- | --- | --- | --- |
| 1 | <date> | — | Initial draft |
## Goal
<One observable outcome sentence.>
## Scope
**In scope**
- <behavior included>
**Out of scope**
- <adjacent work excluded>
## Context
**Discovered facts** (technical, verified from repository or artifact)
- <how the system behaves today, conventions, contracts>
**Product/business constraints** (supplied by user or product artifact, never inferred from code)
- <business rule, compliance/SLA obligation, retention policy, priority, target user — or "none supplied yet">
**Assumptions**
- <unverified claim to confirm or validate>
**Dependencies and constraints**
- <external service, local convention, compatibility obligation, environment limit>
## Risk Review
| Risk area | Applies? | Required handling |
| --- | --- | --- |
| Security/privacy | Yes/No | <redaction, authorization, review, etc.> |
| Persistent data/migration | Yes/No | <compatibility, backup, rollback, etc.> |
| External effects/cost | Yes/No | <sandbox/test environment/authorization> |
| Compatibility/API | Yes/No | <contract to preserve or version> |
| UX/accessibility | Yes/No | <manual or automated evidence> |
## Acceptance Criteria
### AC-001: <observable behavior>
- **Scenario:** <starting condition>
- **Action:** <single trigger>
- **Expected:** <observable result>
- **Must not:** <prohibited side effect, if applicable>
- **Verification:** <method and intended evidence>
- **Environment/safety:** <constraints, if applicable>
- **Priority:** Required | Important | Optional
## Blocking Decisions
- [ ] <only decisions that prevent safe or correct progress>
## Verification Plan
| Criterion | Verification evidence | Status |
| --- | --- | --- |
| AC-001 | <test/check/review command or evidence type> | Pending |
用这些判断技能是否真的产出了可验证 brief,而不是 planning prose。
失败的验收标准
AC-001: The export works correctly and is secure.
失败——“works correctly” 和 “secure” 不可观察,没有 scenario、trigger、expected result 或 verification method,也没有说明什么绝不能发生。读者无法判断实现是否满足了它。
通过的验收标准
AC-001: Export generates file with correct headers
- Scenario: authenticated user, at least one data row visible
- Action: click "Export CSV"
- Expected: browser downloads file with columns [id, name, created_at]
- Must not: expose internal fields or rows belonging to other users
- Verification: automated integration test + manual schema spot-check
- Priority: Required
通过——一个具体可观察结果、一个禁止副作用,以及一个命名验证方法。两个人会就是否满足达成一致。
失败的 context 条目
Discovered facts: Users on the free tier are limited to 100 exports per month.
失败——按 tier 限制是业务规则。它不能作为从代码推断的 discovered facts 出现;它属于 Product/business constraints,由用户提供,或列为待确认假设。
只有当每个答案是 “yes” 时 brief 才通过。任何 “no” 意味着返回前修订。
返回 brief 前检查:
当另一个 planning 或实现工作流可用时,把验收 brief 或标准 ID 传给它。当没有专用工作流时,直接把 brief 作为实现参考提供。不要假设任何命名 skill 或工具已安装。
npx claudepluginhub aaione/everything-claude-code-zhTransforms ambiguous or high-impact product/engineering changes into scoped, verifiable acceptance criteria before or alongside implementation. Use to de-risk features, migrations, security changes, or agent handoffs.
Creates or updates functional specifications from natural language feature descriptions by analyzing codebase impact, generating context, and writing structured spec documents.
Generates engineering specs for non-trivial features, changes, or refactors before planning or coding. Covers goals, non-goals, constraints, acceptance criteria, and open questions.