x-update-architecture
Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.
- License 许可
- MIT
- 最近更新
- 2026-10-27
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- x-update-architecture
- description
- Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.
- allowed-tools
- Read, Write, Edit, Bash, Grep, Glob
- argument-hint
- [STORY-ID or architecture-plan-path]
- context-budget
- light
- user-invocable
- true
- requires-capabilities
- []
02 资源文件 1
- 参考文档README.md1.7 KB
03 SKILL.md 正文
Global Output Policy
- Language: English ONLY.
- Tone: Technical, Direct, and Concise.
- Efficiency: Remove all conversational fillers and greetings to save tokens.
Skill: Service Architecture Document Updater
Purpose
Incrementally updates the service architecture document (steering/service-architecture.md) with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content.
Triggers
/x-update-architecture [STORY-ID]— update architecture doc from the architecture plan for the given story/x-update-architecture [architecture-plan-path]— update architecture doc from the specified plan file- After a feature is implemented and an architecture plan exists
- When Phase 3 (Documentation) of
x-implement-storyis executing - SKIP when no architecture plan exists for the feature
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
STORY-ID |
String | Yes (or path) | Story identifier to locate the architecture plan |
architecture-plan-path |
String | Yes (or ID) | Direct path to the architecture plan file |
Workflow
Step 1 — Read Inputs
- Read the architecture plan at the path provided as argument
- Read the current service architecture doc at
steering/service-architecture.md - If
service-architecture.mddoes NOT exist, read the template fromresources/templates/_TEMPLATE-SERVICE-ARCHITECTURE.mdand create the initial document by replacing{{ placeholders }}with project identity values
Step 2 — Identify Changes
- Compare the architecture plan sections against the current service architecture doc
- For each section, identify: new components, new integrations, new flows, new ADRs, changed NFRs, new observability or resilience configurations
- Build a diff list of changes per section
Step 3 — Apply Incremental Updates (RULE-008 — Content Preservation)
For each changed section, INSERT new content at the appropriate location. NEVER remove or rewrite existing content.
| # | Section Heading | Update Action |
|---|---|---|
| 1 | 1. Overview | Append new interfaces or technology changes |
| 2 | 2. C4 Diagrams | Add new nodes and edges to existing Mermaid diagrams |
| 3 | 3. Integrations | Append new rows to the integration table |
| 4 | 4. Data Model | Add new entities and relationships to the ER diagram |
| 5 | 5. Critical Flows | Add new sequence diagrams as new subsections |
| 6 | 6. NFRs | Update targets only if changed; never remove rows |
| 7 | 7. Architectural Decisions | Append new ADR references to the table |
| 8 | 8. Observability | Add new metrics, alerts, or dashboard entries |
| 9 | 9. Resilience | Add new circuit breaker, retry, or fallback configurations |
| 10 | 10. Change History | Append a new changelog entry with date, story ID, and summary |
Content Preservation Rules
- NEVER remove existing content from any section
- NEVER rewrite a section — only insert or append
- If a component was refactored: mark old as deprecated, add new
- If a flow changed: add new version, mark previous as "v1"
- Merge conflicts: preserve both versions
Change History Entry Format
| Date | Author | Description |
|---|---|---|
| YYYY-MM-DD | AI (story-XXXX-YYYY) | Sections affected: [list]. Summary: [brief description] |
Step 4 — Update Change History
ALWAYS append a new row to Section 10 (Change History). Include: today's date, story ID, list of sections modified, brief summary.
Step 5 — Save
- Write the updated document to
steering/service-architecture.md - Report: sections updated, changes applied, new entries added
Document Creation from Scratch
If steering/service-architecture.md does NOT exist:
- Read the template from
resources/templates/_TEMPLATE-SERVICE-ARCHITECTURE.md - Replace
{{ placeholders }}with project identity values - Populate sections from the architecture plan data
- Add an initial Change History entry
Template Fallback
If resources/templates/_TEMPLATE-SERVICE-ARCHITECTURE.md is not found, create a minimal service architecture document with 10 numbered sections and populate from the architecture plan. Log a warning: "Template not found; using inline fallback structure."
Subagent Prompt
Launch a single general-purpose subagent:
You are a Documentation Engineer performing an incremental update of the service architecture document for {{PROJECT_NAME}}.
Step 1 — Read inputs:
- Read the architecture plan at the path provided as argument
- Read the current service architecture doc at
steering/service-architecture.md- If
service-architecture.mddoes NOT exist, read the template fromresources/templates/_TEMPLATE-SERVICE-ARCHITECTURE.mdand create the initial document by replacing{{ placeholders }}with project identity valuesStep 2 — Identify changes:
- Compare the architecture plan sections against the current service architecture doc
- For each section, identify: new components, new integrations, new flows, new ADRs, changed NFRs, new observability or resilience configurations
- Build a diff list of changes per section
Step 3 — Apply incremental updates (RULE-008):
- For each changed section, INSERT new content at the appropriate location
- NEVER remove or rewrite existing content
- For C4 diagrams: add new Mermaid nodes and edges within existing graph blocks
- For tables: append new rows
- For sequence diagrams: add new subsections with new diagrams
- For ADR references: append new rows to the ADR table
Step 4 — Update Change History:
- ALWAYS append a new row to Section 10 (Change History)
- Include: today's date, story ID, list of sections modified, brief summary
Step 5 — Save:
- Write the updated document to
steering/service-architecture.md- Report: sections updated, changes applied, new entries added
Conventions:
- All content in English (RULE-012)
- Mermaid syntax for all diagrams
- Incremental updates only — never full rewrite (RULE-008)
Error Handling
| Scenario | Action |
|---|---|
| Architecture plan not found | Skip with log: "No architecture plan found; skipping architecture doc update" |
| Service architecture doc not found | Create from template (see Document Creation from Scratch) |
| Template not found | Use inline fallback structure, log warning |
| Section heading mismatch | Match by numeric prefix, warn if heading text differs |
| Merge conflict in Mermaid diagram | Preserve both versions, add comment marking conflict |
Integration Notes
| Skill | Relationship | Context |
|---|---|---|
x-implement-story |
called-by | Invoked during Phase 3 (Documentation) to update architecture doc |
x-plan-architecture |
reads | Generates the input architecture plans consumed by this skill |
x-generate-adr |
calls | May trigger ADR generation for new architectural decisions |
architecture |
reads | References architecture principles and patterns KP |
Knowledge Pack References
| Pack | Files | Purpose |
|---|---|---|
| architecture | knowledge/architecture.md |
Architecture principles and patterns |
04 同仓库更多 Skills
x-parallel-eval
Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-task-plan / x-story-plan, applies the parallelism-heuristics knowledge pack (hard / regen / soft categories + hotspot overrides), and emits a collision matrix + serialization recommendation in Markdown (default) or JSON.
parallelism-heuristics
Canonical catalog of file-collision heuristics for parallel task, story, and epic execution. Defines the File Footprint block format, the three Conflict Categories (hard / regen / soft), a hotspot list of high-contention paths, and the degrade-with-warning policy. Consumed by x-task-plan, x-story-plan, x-epic-map, x-parallel-eval, and x-dev-*-implement.
x-watch-pr-ci
Polls a PR's CI checks and Copilot review status, blocking until checks complete or timeout. Returns one of 8 stable exit codes (SUCCESS=0, CI_PENDING_PROCEED=10, CI_FAILED=20, TIMEOUT=30, PR_ALREADY_MERGED=40, NO_CI_CONFIGURED=50, PR_CLOSED=60, PR_NOT_FOUND=70). Writes a versioned state-file for session resume.
x-validate-docs
Documentation freshness gate: validates 6 dimensions (readme, api-specs, grpc-proto, adr, skill-docs, system-architecture) against code changes in a PR. Stack-aware — only validates targets declared/auto-detected from ProjectConfig.documentation.targets. Returns exit non-zero on staleness; produces structured report.
x-update-system-architecture
Incrementally updates docs/architecture/system.md after an epic completes. Appends new entries to the Decision Log (§11) using x-internal-write-report --append (dedup by ## ID: marker) and surgically inserts component/integration changes into sections 1-10 via Edit. Idempotent: re-running with the same epic produces a byte-identical system.md.
x-update-architecture
Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.