ai-sdlc-delivery-spec-synthesis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

ai-sdlc-delivery-spec-synthesis: Delivery Spec Synthesis

ai-sdlc-delivery-spec-synthesis：交付规范合成

Internal AI SDLC skill, not client-facing by default. Every rule below is important to follow. None of it can be skipped. Before producing the final artifact, confirm required inputs, target audience, missing facts, output format, and constraints when they are unclear. Do not invent missing information. Ask concise clarification questions when required inputs are absent.

内部AI SDLC技能，默认不面向客户。以下每条规则都必须严格遵守，不得跳过任何一条。在生成最终成果前，若所需输入、目标受众、缺失信息、输出格式和约束条件不明确，请先确认这些内容。不得编造缺失的信息。当必要输入缺失时，请提出简洁的澄清问题。

0. Skill Card

0. 技能卡片

Skill name:
```
ai-sdlc-delivery-spec-synthesis
```
Primary audience: BA
Supporting audience: Dev, QA, PM, Delivery
Audience tags: BA, Dev, QA, PM
SDLC stage: Delivery specification
Purpose: Convert the clarified package and story set into a structured delivery specification.
Output: Structured delivery specification for engineering and cross-functional planning

技能名称：
```
ai-sdlc-delivery-spec-synthesis
```
主要受众：BA（业务分析师）
支持受众：Dev（开发人员）、QA（测试人员）、PM（产品经理）、交付团队
受众标签：BA, Dev, QA, PM
SDLC阶段：交付规范
用途：将已明确的需求包和故事集转换为结构化的交付规范。
输出：供工程团队和跨职能团队规划使用的结构化交付规范

0.1 Required Inputs

0.1 必要输入

Approved or clarified stories and delivery context.
Business rules, acceptance criteria, and dependencies.
Known implementation constraints or system boundaries.

已批准或明确的需求故事和交付上下文。
业务规则、验收标准和依赖关系。
已知的实施约束或系统边界。

0.2 Clarification Rules

0.2 澄清规则

Ask concise questions before finalizing when role, artifact, requirements, scope, audience, or constraints are unclear.
If optional information is missing, mark it as
```
TBD
```
,
```
Not provided
```
, or
```
Assumption
```
instead of inventing it.
Separate confirmed facts from assumptions and open questions.
Do not proceed to downstream synthesis when a required upstream artifact or decision is missing.

当角色、成果、需求、范围、受众或约束条件不明确时，在最终确定前提出简洁的问题。
若可选信息缺失，标记为
```
TBD
```
（待确定）、
```
Not provided
```
（未提供）或
```
Assumption
```
（假设），不得编造。
将已确认的事实与假设、未解决问题分开。
当必要的上游成果或决策缺失时，不得进行下游合成工作。

0.2.1 Flow Mode Flags

0.2.1 流程模式标志

Support two explicit execution flags:
```
--quick-flow
```
and
```
--full-flow
```
.
If both flags are supplied,
```
--full-flow
```
takes precedence because it is the stricter mode.
```
--quick-flow
```
: move fast, make high-quality progress with available context, avoid clarification questions unless continuing would create material product, security, compliance, data-loss, or irreversible implementation risk.
In
```
--quick-flow
```
, use documented assumptions, recommended defaults, existing repository patterns, and the nearest available artifact evidence; record important assumptions and decisions in
```
decision-log.md
```
.
In
```
--quick-flow
```
, run only focused checks that are directly relevant, cheap, and likely to catch regressions for the requested work; report any skipped broader checks as residual risk.
```
--full-flow
```
: ask concise clarification questions when inputs, scope, ownership, acceptance criteria, or decisions are unclear; do not silently assume material requirements.
In
```
--full-flow
```
, verify upstream and downstream artifacts, decision-log entries, traceability links, acceptance criteria, and validation evidence before finalizing.
In
```
--full-flow
```
, run or recommend the skill-appropriate gates, reviews, scripts, and validation commands needed for end-to-end confidence; document any blocked verification explicitly.
When neither flag is supplied, follow the skill default rules and choose the least risky behavior for the request size and domain.

支持两种明确的执行标志：
```
--quick-flow
```
和
```
--full-flow
```
。
若同时提供两个标志，
```
--full-flow
```
优先，因为它是更严格的模式。
```
--quick-flow
```
：快速推进，利用现有上下文取得高质量进展，除非继续执行会导致重大产品、安全、合规、数据丢失或不可逆的实施风险，否则避免提出澄清问题。
在
```
--quick-flow
```
模式下，使用已记录的假设、推荐默认值、现有仓库模式和最接近的可用成果证据；将重要假设和决策记录在
```
decision-log.md
```
中。
在
```
--quick-flow
```
模式下，仅运行与请求工作直接相关、成本低且可能发现回归问题的针对性检查；将任何跳过的更广泛检查报告为残余风险。
```
--full-flow
```
：当输入、范围、所有权、验收标准或决策不明确时，提出简洁的澄清问题；不得默认重要需求。
在
```
--full-flow
```
模式下，在最终确定前验证上下游成果、决策日志条目、可追溯链接、验收标准和验证证据。
在
```
--full-flow
```
模式下，运行或推荐技能对应的关卡、评审、脚本和验证命令，以确保端到端的可信度；明确记录任何受阻的验证工作。
当未提供任何标志时，遵循技能默认规则，并根据请求规模和领域选择风险最低的行为。

0.3 Output Rules

0.3 输出规则

Keep output structured with headings and bullets.
Make findings, gaps, risks, and blockers explicit.
Tie recommendations to evidence from the provided artifact,
```
specs-refiniment/<feature-name>/<file.md>
```
workspace, or user context.
Include role ownership when the output creates follow-up work for BA, QA, Dev, PM, or Delivery.
Return progress, completion, validation, and handoff summaries directly in the Codex response.

Before the final response, emit the

ai-sdlc-handoff/v1

contract with

result

blockers

next_required

, and

next_optional

; every action includes

reason

command

, and

expected_artifact

Do not create
```
summary.txt
```
,
```
*-summary.txt
```
, or another standalone summary file unless the user explicitly requests one.
Keep durable writes limited to the canonical lifecycle artifacts, decision log, human-readable index, and
```
_ai_sdlc
```
machine files.
Let shared helpers migrate legacy paths on the next write; never overwrite or manually merge divergent legacy and canonical files.

保持输出结构清晰，使用标题和项目符号。
明确指出发现的问题、差距、风险和阻塞点。
将建议与提供的成果、
```
specs-refiniment/<feature-name>/<file.md>
```
工作区或用户上下文的证据关联起来。
当输出为BA、QA、Dev、PM或交付团队产生后续工作时，需明确角色负责人。
直接在Codex响应中返回进度、完成情况、验证和交接摘要。

在最终响应前，输出包含

result

、

blockers

、

next_required

和

next_optional

的

ai-sdlc-handoff/v1

契约；每个操作需包含

reason

、

command

和

expected_artifact

。

除非用户明确要求，否则不得创建
```
summary.txt
```
、
```
*-summary.txt
```
或其他独立的摘要文件。
仅将持久化写入限制在标准生命周期成果、决策日志、人类可读索引和
```
_ai_sdlc
```
机器文件中。
让共享助手在下次写入时迁移旧路径；不得覆盖或手动合并不一致的旧文件和标准文件。

0.4 Artifact Routing

0.4 成果路由

Maintain a feature decision log whenever this skill records, resolves, changes, or depends on a product, delivery, QA, security, validation, branching, implementation, or rollout decision.
For PM, BA, QA, Delivery, discovery, planning, refinement, and readiness work, write decisions to
```
specs-refiniment/<feature-name>/decision-log.md
```
.
For developer implementation SDD work, write decisions to
```
specs/<feature-name>/decision-log.md
```
.
Each decision-log entry must include date, decision, context or evidence, options considered when relevant, owner, status, and links to affected artifacts, tasks, tests, or validation evidence.

Use this exact decision-log structure:

markdown

# Decision Log

| ID | Date | Status | Owner | Decision | Context/Evidence | Options Considered | Affected Artifacts | Validation/Trace Links |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| DEC-001 | YYYY-MM-DD | proposed / accepted / superseded / rejected | role or name | concise decision | source facts, artifact links, or evidence | option A; option B; recommended default | affected docs, tasks, code, tests, or rollout notes | requirement IDs, test IDs, validation commands, PRs, commits, or tickets |

When writing or updating files, place PM, BA, QA, Delivery, discovery, planning, refinement, and readiness artifacts at
```
specs-refiniment/<feature-name>/<file.md>
```
.
Use the path pattern
```
specs-refiniment/<feature-name>/<file.md>
```
; choose a stable feature slug when known, otherwise use
```
tbd-<short-topic>
```
for
```
<feature-name>
```
.
Do not write this skill's output into
```
specs/
```
; that folder is reserved for developer implementation SDD artifacts.
If the user explicitly asks to convert a refined artifact into developer implementation work, hand off to
```
$ai-sdlc-sdd
```
.

每当本技能记录、解决、更改或依赖产品、交付、QA、安全、验证、分支、实施或发布决策时，维护功能决策日志。
对于PM、BA、QA、交付团队的探索、规划、细化和准备工作，将决策写入
```
specs-refiniment/<feature-name>/decision-log.md
```
。
对于开发人员的实施SDD（软件设计文档）工作，将决策写入
```
specs/<feature-name>/decision-log.md
```
。
每个决策日志条目必须包含日期、决策内容、上下文或证据、相关备选方案（如有）、负责人、状态以及受影响成果、任务、测试或验证证据的链接。

使用以下精确的决策日志结构：

markdown

# Decision Log

| ID | Date | Status | Owner | Decision | Context/Evidence | Options Considered | Affected Artifacts | Validation/Trace Links |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| DEC-001 | YYYY-MM-DD | proposed / accepted / superseded / rejected | role or name | concise decision | source facts, artifact links, or evidence | option A; option B; recommended default | affected docs, tasks, code, tests, or rollout notes | requirement IDs, test IDs, validation commands, PRs, commits, or tickets |

写入或更新文件时，将PM、BA、QA、交付团队的探索、规划、细化和准备成果放在
```
specs-refiniment/<feature-name>/<file.md>
```
路径下。
使用路径模式
```
specs-refiniment/<feature-name>/<file.md>
```
；若已知稳定的功能别名则使用，否则
```
<feature-name>
```
使用
```
tbd-<short-topic>
```
。
不得将本技能的输出写入
```
specs/
```
文件夹；该文件夹专为开发人员的实施SDD成果保留。
若用户明确要求将已细化的成果转换为开发人员的实施工作，则移交至
```
$ai-sdlc-sdd
```
技能。

0.5 Feature State Machine

0.5 功能状态机

Maintain feature lifecycle state in TOON at

specs-refiniment/<feature-name>/_ai_sdlc/state.toon

for refinement work and

specs/<feature-name>/_ai_sdlc/state.toon

for implementation work.

Before executing this skill for a feature, check the state machine with

python3 skills/_shared/state_machine.py check --feature <feature-name> --skill <this-skill-name> --workspace <refinement|implementation> --quick-flow|--full-flow

When this skill starts durable work, mark it in progress with
```
begin
```
; when the skill's required artifact or review is complete, mark it done with
```
complete
```
and include
```
--artifacts <path>
```
plus
```
--decision-ref DEC-###
```
when a decision was involved.
In
```
--full-flow
```
, do not proceed when predecessor stages are incomplete, another lifecycle skill is active, or the state file reports a blocker.
In
```
--quick-flow
```
, a predecessor skip is allowed only when continuing is low risk and the command includes
```
--assumption "..."
```
or
```
--decision-ref DEC-###
```
; record the same assumption or decision in
```
decision-log.md
```
.

Use

python3 skills/_shared/state_machine.py status --feature <feature-name> --workspace <refinement|implementation> --format toon

to emit compact LLM-readable state before choosing the next skill.

The state machine is feature-scoped: do not reuse a
```
state.toon
```
across unrelated feature folders.

在TOON中维护功能生命周期状态：细化工作的状态存于
```
specs-refiniment/<feature-name>/_ai_sdlc/state.toon
```
，实施工作的状态存于
```
specs/<feature-name>/_ai_sdlc/state.toon
```
。

在为某个功能执行本技能前，使用

python3 skills/_shared/state_machine.py check --feature <feature-name> --skill <this-skill-name> --workspace <refinement|implementation> --quick-flow|--full-flow

检查状态机。

当本技能开始持久化工作时，使用
```
begin
```
标记为进行中；当技能所需成果或评审完成时，使用
```
complete
```
标记为完成，并在涉及决策时添加
```
--artifacts <path>
```
和
```
--decision-ref DEC-###
```
。
在
```
--full-flow
```
模式下，当前置阶段未完成、其他生命周期技能正在运行或状态文件报告阻塞时，不得继续执行。
在
```
--quick-flow
```
模式下，仅当继续执行风险低且命令包含
```
--assumption "..."
```
或
```
--decision-ref DEC-###
```
时，才允许跳过前置阶段；需在
```
decision-log.md
```
中记录相同的假设或决策。

使用

python3 skills/_shared/state_machine.py status --feature <feature-name> --workspace <refinement|implementation> --format toon

输出紧凑的LLM可读状态，再选择下一个技能。

状态机以功能为范围：不得在不相关的功能文件夹间复用
```
state.toon
```
。

0.6 Artifact Metadata And Metatags

0.6 成果元数据与元标签

Every Markdown artifact generated or updated by this skill must start with an
```
artifact_metadata
```
YAML frontmatter block before the first visible heading.

Use schema

ai-sdlc-artifact-metadata/v1

and keep these fields current:

feature

artifact

path

workspace

skill

flow_mode

state_file

decision_log

status

owner

created_at

updated_at

trace_ids

related_artifacts

validation

, and

metatags

```
metatags
```
must include at minimum
```
ai-sdlc
```
, the workspace (
```
refinement
```
or
```
implementation
```
), this skill name, the artifact type or filename stem, and a lifecycle/status tag such as
```
draft
```
,
```
review
```
,
```
approved
```
, or
```
validated
```
.
When
```
--quick-flow
```
is active, set
```
flow_mode: quick
```
, keep assumptions visible in the body, and add tags for major defaults or unresolved risk only when they help retrieval.
When
```
--full-flow
```
is active, set
```
flow_mode: full
```
, keep blockers and validation evidence reflected in
```
status
```
,
```
validation
```
,
```
trace_ids
```
, and
```
related_artifacts
```
.
Update metadata whenever the artifact path, status, owner, trace links, validation evidence, related artifacts, or decision references change.
Metadata is an index for routing, retrieval, and traceability; it does not replace the artifact body,
```
decision-log.md
```
, or
```
state.toon
```
.

本技能生成或更新的每个Markdown成果，必须在第一个可见标题前包含
```
artifact_metadata
```
YAML前置块。

使用

ai-sdlc-artifact-metadata/v1

schema，并保持以下字段最新：

feature

、

artifact

、

path

、

workspace

、

skill

、

flow_mode

、

state_file

、

decision_log

、

status

、

owner

、

created_at

、

updated_at

、

trace_ids

、

related_artifacts

、

validation

和

metatags

。

```
metatags
```
必须至少包含
```
ai-sdlc
```
、工作区（
```
refinement
```
或
```
implementation
```
）、本技能名称、成果类型或文件名主干，以及生命周期/状态标签（如
```
draft
```
、
```
review
```
、
```
approved
```
或
```
validated
```
）。
当
```
--quick-flow
```
激活时，设置
```
flow_mode: quick
```
，在正文中显示假设，仅当有助于检索时才添加主要默认值或未解决风险的标签。
当
```
--full-flow
```
激活时，设置
```
flow_mode: full
```
，在
```
status
```
、
```
validation
```
、
```
trace_ids
```
和
```
related_artifacts
```
中反映阻塞点和验证证据。
当成果路径、状态、负责人、追溯链接、验证证据、相关成果或决策引用发生变化时，更新元数据。
元数据用于路由、检索和可追溯性；它不能替代成果正文、
```
decision-log.md
```
或
```
state.toon
```
。

0.7 Specs Index

0.7 规范索引

Before searching across feature folders, inspect the compact LLM index first:
```
specs-refiniment/_ai_sdlc/specs-index.toon
```
for refinement work or
```
specs/_ai_sdlc/specs-index.toon
```
for implementation work.
Use the human-readable index at
```
specs-refiniment/specs-index.md
```
or
```
specs/specs-index.md
```
when reporting feature coverage, artifact inventory, or handoff status to people.

After this skill creates or materially updates an artifact, refresh the matching workspace index with

python3 skills/_shared/ai_sdlc_specs_index.py --workspace <refinement|implementation> --quick-flow|--full-flow

In
```
--quick-flow
```
, rely on
```
specs-index.toon
```
to choose the smallest relevant artifact set before opening files.
In
```
--full-flow
```
, verify the updated artifact appears in both
```
specs-index.toon
```
and
```
specs-index.md
```
before final handoff.
The specs index summarizes artifact metadata and state; it does not replace reading the selected source artifacts when details, approvals, or validation evidence matter.

在跨功能文件夹搜索前，先查看紧凑的LLM索引：细化工作的索引为
```
specs-refiniment/_ai_sdlc/specs-index.toon
```
，实施工作的索引为
```
specs/_ai_sdlc/specs-index.toon
```
。
向人员报告功能覆盖范围、成果清单或交接状态时，使用人类可读索引
```
specs-refiniment/specs-index.md
```
或
```
specs/specs-index.md
```
。

本技能创建或大幅更新成果后，使用

python3 skills/_shared/ai_sdlc_specs_index.py --workspace <refinement|implementation> --quick-flow|--full-flow

刷新匹配的工作区索引。

在
```
--quick-flow
```
模式下，依靠
```
specs-index.toon
```
选择最小的相关成果集，再打开文件。
在
```
--full-flow
```
模式下，在最终交接前验证更新后的成果是否同时出现在
```
specs-index.toon
```
和
```
specs-index.md
```
中。
规范索引汇总成果元数据和状态；当细节、审批或验证证据很重要时，它不能替代阅读选定的源成果。

0.8 Complete Refinement Cascade

0.8 完整细化流程

Trigger the complete cascade only when the user explicitly asks for a full, complete, or end-to-end spec refinement or asks for every refinement artifact. A normal
```
--full-flow
```
call for one skill remains single-stage.
Before the first durable write, run
```
python3 skills/_shared/refinement_status.py --feature <feature-name> --gate full --format toon
```
and start with the earliest reported
```
next_skill
```
, including stages earlier than this skill.
Execute the existing refinement skills in lifecycle order with
```
--full-flow
```
: discovery, PRFAQ, delivery-package gap review, requirements readiness, goal/capability mapping, backlog gap review, backlog decomposition, story decomposition, release slicing, BA context, delivery spec, QA plan, QA gap review, test strategy, test cases, test suite, QA readiness, and delivery handoff.
Produce all 18 canonical Markdown artifacts.
```
release-slicing.md
```
is mandatory for a complete cascade; when release slicing is not applicable, write an explicit evidence-backed N/A artifact and complete the stage instead of skipping it.
After every stage, finalize its artifact, record required decisions, mark the stage
```
done
```
, and refresh the refinement indexes before selecting the next skill.
Do not declare the cascade complete until
```
python3 skills/_shared/refinement_status.py --feature <feature-name> --gate full --format markdown
```
exits successfully with
```
18/18
```
. If it fails, continue with the reported next skill or return the concrete blocker and remaining inventory in Codex.
Surface checkpoint and final summaries in Codex only; never persist a cascade summary as a text file.

仅当用户明确要求完整、全面或端到端的规范细化，或要求所有细化成果时，才触发完整流程。普通的
```
--full-flow
```
调用仅执行单个阶段。
在第一次持久化写入前，运行
```
python3 skills/_shared/refinement_status.py --feature <feature-name> --gate full --format toon
```
，从报告的最早
```
next_skill
```
开始执行，包括早于本技能的阶段。
按生命周期顺序使用
```
--full-flow
```
执行现有的细化技能：探索、PRFAQ、交付包差距评审、需求就绪、目标/能力映射、待办事项差距评审、待办事项分解、故事分解、发布切片、BA上下文、交付规范、QA计划、QA差距评审、测试策略、测试用例、测试套件、QA就绪和交付交接。
生成所有18个标准Markdown成果。
```
release-slicing.md
```
是完整流程的必填项；若发布切片不适用，需编写明确的有证据支持的N/A成果并完成该阶段，不得跳过。
每个阶段完成后，最终确定其成果、记录必要决策、标记阶段为
```
done
```
，并在选择下一个技能前刷新细化索引。
仅当
```
python3 skills/_shared/refinement_status.py --feature <feature-name> --gate full --format markdown
```
成功退出且显示
```
18/18
```
时，才宣布流程完成。若失败，继续执行报告的下一个技能，或在Codex中返回具体阻塞点和剩余任务清单。
仅在Codex中显示检查点和最终摘要；不得将流程摘要保存为文本文件。

References

参考资料

Use
```
scripts/delivery_spec_scaffold.py
```
when deterministic scaffolding, planning, or formatting is useful for this workflow; pass the same
```
--quick-flow
```
or
```
--full-flow
```
flag that was supplied to the skill.
Read
```
references/spec-structures.md
```
when the task needs the detailed structure, checklist, or examples for this skill.

当此工作流需要确定性脚手架、规划或格式化时，使用
```
scripts/delivery_spec_scaffold.py
```
；传递与技能相同的
```
--quick-flow
```
或
```
--full-flow
```
标志。
当任务需要本技能的详细结构、检查清单或示例时，阅读
```
references/spec-structures.md
```
。

Script Usage

脚本使用

In default and full flow, always run this skill's primary analysis script with
```
--format toon --budget-tokens 24000
```
before drafting; explicit inputs are priority evidence but do not replace the rest of the feature package.
Read this skill's reference file before writing sections. Use its detailed tables and quality bar, not only the compact scaffold headings.
Run the primary script with
```
--emit-template
```
in the active flow mode to obtain the exact shared context headings and required stage table columns before section writes.
Make every default/full artifact self-contained by completing all ten shared feature-context sections plus the stage-specific profile sections. Quick flow may use the compact stage-only draft.
Follow every
```
next_reads
```
entry before finalization and list every consumed source in
```
Source Coverage
```
; do not claim whole-feature context from a partial source set.
Keep the final artifact within
```
--max-artifact-tokens 24000
```
; condense repetition instead of dropping feature dimensions or source traceability.
Run
```
scripts/delivery_spec_scaffold.py
```
before drafting or updating this skill's artifact when inputs are longer than a few bullets, when traceability matters, or when a flow flag is supplied. For agent analysis, pass
```
--format toon
```
, read
```
anchors
```
first, and open only
```
next_reads
```
; without that flag the script keeps its human-readable Markdown output.

Quick flow analysis:

python3 skills/ai-sdlc-delivery-spec-synthesis/scripts/delivery_spec_scaffold.py --feature <feature-name> --quick-flow <input.md>...

Full flow analysis:

python3 skills/ai-sdlc-delivery-spec-synthesis/scripts/delivery_spec_scaffold.py --feature <feature-name> --full-flow <input.md>...

To write content, pass one canonical heading with
```
--section "<section>"
```
; provide only that section body on stdin, without H1, H2, frontmatter, or a temporary content file.
Repeat
```
--section
```
for each required section, then run the same script with
```
--finalize
```
to validate the artifact and refresh metadata and specs indexes.
The AI must not write or directly edit the routed Markdown artifact; the script owns scaffold creation, section placement, and durable file writes.
Use
```
--decision-row
```
with one nine-cell Markdown table row on stdin when a decision-log entry is required.

Legacy

--emit-template

--emit-decision-log-entry

, and

--write

remain available for compatibility.

Use
```
--quick-flow
```
for first-pass synthesis with assumptions; use
```
--full-flow
```
before readiness, handoff, signoff, or any decision-sensitive output.

在默认和完整流程中，起草前始终使用
```
--format toon --budget-tokens 24000
```
运行本技能的主分析脚本；明确输入是优先证据，但不能替代整个功能包。
编写章节前阅读本技能的参考文件。使用其详细表格和质量标准，而不仅仅是紧凑的脚手架标题。
在当前流程模式下运行主脚本并添加
```
--emit-template
```
，以获取精确的共享上下文标题和所需阶段表格列，再进行章节编写。
每个默认/完整成果必须包含所有十个共享功能上下文章节以及阶段特定的配置文件章节，确保自包含。快速流程可使用紧凑的仅阶段草稿。
最终确定前遵循每个
```
next_reads
```
条目，并在
```
Source Coverage
```
中列出所有使用的源；不得从部分源集声称拥有完整功能上下文。
保持最终成果在
```
--max-artifact-tokens 24000
```
限制内；压缩重复内容，而非删除功能维度或源可追溯性。
当输入超过几个项目符号、可追溯性很重要或提供了流程标志时，起草或更新本技能的成果前运行
```
scripts/delivery_spec_scaffold.py
```
。对于Agent分析，传递
```
--format toon
```
，先读取
```
anchors
```
，再打开仅
```
next_reads
```
；若不使用该标志，脚本将保持人类可读的Markdown输出。

快速流程分析：

python3 skills/ai-sdlc-delivery-spec-synthesis/scripts/delivery_spec_scaffold.py --feature <feature-name> --quick-flow <input.md>...

完整流程分析：

python3 skills/ai-sdlc-delivery-spec-synthesis/scripts/delivery_spec_scaffold.py --feature <feature-name> --full-flow <input.md>...

要编写内容，使用
```
--section "<section>"
```
传递一个标准标题；仅在标准输入中提供该章节的正文，无需H1、H2、前置块或临时内容文件。
对每个所需章节重复
```
--section
```
，然后使用
```
--finalize
```
运行相同的脚本，以验证成果并刷新元数据和规范索引。
AI不得直接写入或编辑路由的Markdown成果；脚本负责脚手架创建、章节放置和持久化文件写入。
当需要决策日志条目时，使用
```
--decision-row
```
并在标准输入中提供一行九单元格的Markdown表格。

为兼容保留旧版

--emit-template

、

--emit-decision-log-entry

和

--write

选项。

使用
```
--quick-flow
```
进行带假设的首次合成；在就绪、交接、签字或任何决策敏感输出前使用
```
--full-flow
```
。

Purpose

用途

Convert the clarified package and story set into a structured delivery specification.

将已明确的需求包和故事集转换为结构化的交付规范。

Use When

使用场景

The gap review is complete.
The story set is mature enough to serve as a reliable input.
The team needs a delivery-oriented spec, not just narrative discovery.

差距评审已完成。
故事集足够成熟，可作为可靠输入。
团队需要面向交付的规范，而非仅叙事性探索文档。

Do Not Use When

禁止使用场景

Stories are still missing key actor behavior or acceptance logic.
The team only needs a lightweight story list.

故事仍缺少关键参与者行为或验收逻辑。
团队仅需要轻量级的故事列表。

Workflow

工作流程

Start from the validated stories and upstream package.
Synthesize scope, roles, workflows, business rules, data needs, NFRs, and dependencies.
Keep assumptions and open questions explicit instead of smoothing them over.
Organize the document for delivery handoff rather than executive storytelling.

从已验证的故事和上游需求包开始。
合成范围、角色、工作流、业务规则、数据需求、非功能性需求（NFRs）和依赖关系。
明确列出假设和未解决问题，而非掩盖它们。
组织文档以适应交付交接，而非面向管理层的叙事。

Spec Rules

规范规则

Keep the spec consistent with the story set and MVP boundaries.
Do not re-invent requirements that contradict the input package.
Call out unresolved rules, missing owners, and dependency risks directly.
Go deep enough for delivery planning, but do not drift into code design unless the business-level spec genuinely requires it.

保持规范与故事集和MVP边界一致。
不得编造与输入需求包相矛盾的需求。
直接指出未解决的规则、缺失的负责人和依赖风险。
深入到足以支持交付规划的程度，但除非业务级规范确实需要，否则不要陷入代码设计细节。

Structures

结构

Use

references/spec-structures.md

使用

references/spec-structures.md

。

Completion Criteria

完成标准

Scope, actors, and workflows are explicit.
Requirements are traceable to stories and business value.
Dependencies, assumptions, and open questions are visible.
The document is usable as a delivery handoff artifact.

范围、参与者和工作流明确。
需求可追溯到故事和业务价值。
依赖关系、假设和未解决问题清晰可见。
文档可用作交付交接成果。