spec-kit-analyze

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Spec Kit Analyze

Spec Kit 分析

Run a non-destructive cross-artifact quality audit before implementation.

在实施前执行无破坏性的跨文档质量审计。

When to Use

适用场景

```
tasks.md
```
exists and you want a pre-implementation consistency check across spec/plan/tasks.
You suspect coverage gaps, requirement drift, ambiguous language, or contradictory artifacts.
You need a constitution-alignment gate without editing artifacts yet.

已存在
```
tasks.md
```
，且你希望在实施前对spec/plan/tasks进行一致性检查。
你怀疑存在覆盖缺口、需求偏离、表述模糊或文档矛盾的情况。
你需要一个规范对齐检查环节，且暂时不修改文档。

When Not to Use

不适用场景

Any prerequisite artifact is missing (
```
spec-kit-specify
```
,
```
spec-kit-plan
```
, or
```
spec-kit-tasks
```
first).
You need targeted remediation edits now (
```
spec-kit-reconcile
```
).
You are executing implementation work (
```
spec-kit-implement
```
).

缺少任何前置文档（需先执行
```
spec-kit-specify
```
、
```
spec-kit-plan
```
或
```
spec-kit-tasks
```
）。
你现在需要针对性的修正编辑（使用
```
spec-kit-reconcile
```
）。
你正在执行实施工作（使用
```
spec-kit-implement
```
）。

Router Fit

流程适配

Primary route from
```
spec-kit
```
after
```
spec-kit-tasks
```
.
Read-only quality gate before
```
spec-kit-implement
```
.
Default handoff to
```
spec-kit-reconcile
```
when findings require coordinated artifact updates.

是
```
spec-kit
```
在
```
spec-kit-tasks
```
之后的主要流程节点。
是
```
spec-kit-implement
```
之前的只读质量检查环节。
当发现问题需要协调更新文档时，默认流转到
```
spec-kit-reconcile
```
。

Critical Constraints

关键约束

Strictly read-only: do not modify files.
Treat
```
memory/constitution.md
```
as authoritative; any MUST-level conflict is
```
CRITICAL
```
.

严格只读：不得修改文件。
将
```
memory/constitution.md
```
视为权威文件；任何违反MUST级要求的冲突均为
```
CRITICAL
```
（严重）级别。

Preconditions

前置条件

Run from repository root (or a subdirectory inside it).
Active feature context resolves to one feature directory with
```
spec.md
```
,
```
plan.md
```
, and
```
tasks.md
```
.

从仓库根目录（或其子目录）运行。
当前功能上下文指向包含
```
spec.md
```
、
```
plan.md
```
和
```
tasks.md
```
的单个功能目录。

Workflow

工作流程

Resolve artifact paths and enforce prerequisite gate:

Run

scripts/check-prerequisites.sh --json --require-tasks --include-tasks

exactly once.

Parse:
- ```
FEATURE_DIR
```
- ```
AVAILABLE_DOCS
```

Derive:

```
SPEC = FEATURE_DIR/spec.md
```
```
PLAN = FEATURE_DIR/plan.md
```
```
TASKS = FEATURE_DIR/tasks.md
```

If any required artifact is missing, stop and route to the owning sibling skill.

Load focused sections from:
- ```
spec.md
```
  : requirements, stories, acceptance criteria, edge cases.
- ```
plan.md
```
  : architecture/stack decisions, phases, constraints.
- ```
tasks.md
```
  : task IDs, phase grouping,
```
[P]
```
  markers, referenced paths.
- ```
memory/constitution.md
```
  : principle names and normative MUST/SHOULD statements.
Build internal maps:
- Requirement inventory (functional + non-functional) with stable keys.
- Story/action inventory with acceptance-test intent.
- Task-to-requirement/story coverage mapping.
- Constitution obligations relevant to spec/plan/tasks scope.
Detect and classify issues:
- Duplication: overlapping or near-duplicate requirements.
- Ambiguity/placeholders: vague quality terms, TODO/TKTK/placeholder tokens.
- Underspecification: requirements lacking measurable outcomes or clear objects.
- Constitution conflicts: violations against MUST principles (
```
CRITICAL
```
  ).
- Coverage gaps: requirements without tasks and tasks without mapped requirement/story.
- Cross-artifact inconsistency: terminology drift, entity mismatch, ordering contradictions.
- Cap findings at 50 rows; summarize overflow counts by category.
Assign severity and output a compact report with stable IDs, coverage table, and metrics.
- ```
CRITICAL
```
  : constitution MUST violations, missing core coverage that blocks baseline behavior.
- ```
HIGH
```
  : conflicting/duplicate requirements, untestable or high-risk ambiguity.
- ```
MEDIUM
```
  : terminology drift, non-functional coverage gaps, underspecified edge cases.
- ```
LOW
```
  : wording/style cleanup without execution impact.
Recommend next actions:
- If
```
CRITICAL
```
  /
```
HIGH
```
  findings require cross-artifact edits, block
```
spec-kit-implement
```
  and route to
```
spec-kit-reconcile
```
  with a concise gap summary.
- If only one artifact needs focused updates, route to its owner skill (
```
spec-kit-specify
```
  ,
```
spec-kit-plan
```
  , or
```
spec-kit-tasks
```
  ).
- Otherwise provide prioritized improvements and whether implementation can proceed.
Offer follow-up only:
- Ask whether to run
```
spec-kit-reconcile
```
  using top findings as the gap report.
- Do not apply any edits in this skill.

解析文档路径并执行前置检查：
- 准确执行一次
```
scripts/check-prerequisites.sh --json --require-tasks --include-tasks
```
  脚本。
- 解析以下内容：
  - ```
  FEATURE_DIR
```
- ```
AVAILABLE_DOCS
```
- 推导路径：
  - ```
  SPEC = FEATURE_DIR/spec.md
```
- ```
PLAN = FEATURE_DIR/plan.md
```
  - ```
  TASKS = FEATURE_DIR/tasks.md
```
- 如果缺少任何必需文档，停止流程并流转到对应的关联工具。
加载以下文档的重点内容：
- ```
spec.md
```
  ：需求、用户故事、验收标准、边缘案例。
- ```
plan.md
```
  ：架构/技术栈决策、阶段划分、约束条件。
- ```
tasks.md
```
  ：任务ID、阶段分组、
```
[P]
```
  标记、引用路径。
- ```
memory/constitution.md
```
  ：原则名称及规范性的MUST/SHOULD声明。
构建内部映射表：
- 需求清单（功能性+非功能性）及稳定键值。
- 用户故事/动作清单及验收测试意图。
- 任务到需求/用户故事的覆盖映射。
- 与spec/plan/tasks范围相关的规范约束。
检测并分类问题：
- 重复：重叠或近乎重复的需求。
- 歧义/占位符：模糊的质量术语、TODO/TKTK/占位符标记。
- 规格不足：缺少可衡量结果或明确对象的需求。
- 规范冲突：违反MUST级原则（标记为
```
CRITICAL
```
  ）。
- 覆盖缺口：未对应任务的需求，以及未映射到需求/用户故事的任务。
- 跨文档不一致：术语偏差、实体不匹配、顺序矛盾。
- 最多显示50条问题；超出部分按类别汇总数量。
分配问题严重程度，并输出包含稳定ID、覆盖表和指标的简洁报告：
- ```
CRITICAL
```
  （严重）：违反MUST级规范、缺失阻碍基线功能的核心覆盖。
- ```
HIGH
```
  （高）：需求冲突/重复、不可测试或高风险的歧义。
- ```
MEDIUM
```
  （中）：术语偏差、非功能性需求覆盖缺口、规格不足的边缘案例。
- ```
LOW
```
  （低）：不影响执行的措辞/风格优化。
推荐后续操作：
- 如果
```
CRITICAL
```
  /
```
HIGH
```
  级问题需要跨文档编辑，阻止
```
spec-kit-implement
```
  流程，并流转到
```
spec-kit-reconcile
```
  ，同时提供简洁的缺口摘要。
- 如果仅需更新单个文档，流转到对应的工具（
```
spec-kit-specify
```
  、
```
spec-kit-plan
```
  或
```
spec-kit-tasks
```
  ）。
- 否则提供优先级排序的改进建议，以及是否可以继续实施。
仅提供后续操作选项：
- 询问是否使用发现的主要问题作为缺口报告，运行
```
spec-kit-reconcile
```
  。
- 本工具不执行任何编辑操作。

Output

输出

Markdown report only (no file writes) containing:
- Findings table:
```
ID | Category | Severity | Location(s) | Summary | Recommendation
```
- Requirement coverage table:
```
Requirement Key | Has Task? | Task IDs | Notes
```
- Constitution alignment issues (if any)
- Unmapped tasks (if any)
- Metrics:
  - Total requirements
  - Total tasks
  - Coverage percentage
  - Ambiguity count
  - Duplication count
  - Critical issues count
- Next-step routing recommendation

仅输出Markdown报告（不写入文件），包含：
- 问题表：
```
ID | 类别 | 严重程度 | 位置 | 摘要 | 建议
```
- 需求覆盖表：
```
需求键值 | 是否有对应任务 | 任务ID | 备注
```
- 规范对齐问题（若有）
- 未映射任务（若有）
- 指标：
  - 总需求数
  - 总任务数
  - 覆盖百分比
  - 歧义问题数
  - 重复问题数
  - 严重问题数
- 后续流程流转建议

References

参考资料

```
references/command-analyze.md
```
```
scripts/check-prerequisites.sh
```

https://github.com/github/spec-kit/blob/9111699cd27879e3e6301651a03e502ecb6dd65d/templates/commands/analyze.md

```
references/command-analyze.md
```
```
scripts/check-prerequisites.sh
```

https://github.com/github/spec-kit/blob/9111699cd27879e3e6301651a03e502ecb6dd65d/templates/commands/analyze.md