菜单
This skill should be used when the user asks to 'prepare release', 'create PR', 'generate documentation', 'run release gates', or needs guidance on Phase 9 release. Also trigger on 'sdd release', 'blocking gates', 'security scan', 'release gate', or 'export work items'.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Decision framework for designing production agentic systems on GitHub platform and Azure AI Foundry. Covers model routing tiers (mini to frontier), prompt caching and semantic caching, short and long term memory, context curation and RAG, tools and MCP, identity and guardrails, evaluation, observability (OpenTelemetry GenAI), and cost control. Use when architecting an AI agent or multi-agent system, choosing a model router, deciding a caching or memory strategy, planning context windows, or reviewing an agent design for reliability, security, and cost. Pairs with azure-managed-redis-cache, foundry-agent-blueprint, azure-api-center, apim-ai-gateway, and azure-architecture-diagrams.
Front model and tool backends with Azure API Management as an AI gateway: token rate limiting (token-per-minute and quota), multi-backend load balancing and circuit breaker across model deployments, semantic caching, token metric emission for cost attribution, managed identity to backends, and content safety integration. Use when designing the runtime gateway for an agentic platform, enforcing token budgets, load balancing across model endpoints, adding a semantic cache at the gateway, or governing tool API calls. Routes to the installed azure-aigateway skill for policy detail. Pairs with azure-api-center (governance), azure-managed-redis-cache (cache backend), and agentic-architecture-patterns.
Validate an architecture document (the {app}_Architecture.md produced by the Senior Cloud Architect agent) against a hard Definition of Done: required sections, the five required diagrams, well-formed Mermaid, the seven explanation parts per diagram, and the repository copy conventions. Use when producing, reviewing, or finishing an architecture document, or whenever you need to confirm a Mermaid-based architecture deliverable is complete and will render before presenting it.
Govern APIs and agent tools at enterprise scale with Azure API Center: a central catalog of APIs, versions, definitions (OpenAPI), environments, and deployments, plus registration of agent tools and MCP servers for discovery and reuse. Use when designing API governance for an agentic platform, building a tool or MCP registry for agents, enforcing API standards with the API Center linter, or making backend APIs discoverable to agent builders. Pairs with apim-ai-gateway (runtime gateway), foundry-agent-blueprint (tool consumption), and agentic-architecture-patterns (tools and MCP).
Produce complete, professional architecture diagrams that use the official Azure, Microsoft, and GitHub (Octicons) icon sets, output as editable draw.io (.drawio) files and exported SVG. Covers the official icon catalogs and their terms of use, the draw.io mxGraph file format, layout and connector conventions, and a bundled draw.io MCP server (Python FastMCP) that creates and edits .drawio diagrams programmatically (add nodes with official icons, connect edges, group, and lay out). Use whenever the deliverable includes an architecture diagram, a system context, a component or deployment diagram, or any cloud diagram that must use official vendor icons. Pairs with ai-native-engineer and agentic-architecture-patterns, and complements svg-professional for hand-crafted SVG.
Design and provision Azure Managed Redis as the cache, semantic cache, vector store, session store, and agent memory backend for AI-native systems. Covers SKU selection (Balanced, MemoryOptimized, ComputeOptimized, FlashOptimized), the fact that Redis Enterprise is retired for new creations, vector search and RedisVL for semantic caching and long term memory, session and short term state, tenant isolation, managed identity (Entra) access, private networking, and a Bicep sample. Use when an agent design needs caching, a semantic cache, a vector memory store, or session state on Redis. Pairs with agentic-architecture-patterns and apim-ai-gateway.
| name | release-engineer |
| description | This skill should be used when the user asks to 'prepare release', 'create PR', 'generate documentation', 'run release gates', or needs guidance on Phase 9 release. Also trigger on 'sdd release', 'blocking gates', 'security scan', 'release gate', or 'export work items'. |
Phase 9 executes final release gates, creates deployment artifacts, generates user documentation, and publishes work items. It is the final verification before production deployment.
Before Phase 9 begins, verify these mandatory conditions:
Missing prerequisites block release. Run /specky:check-gates to validate.
Two sequential blocking gates must pass before release:
Execute security scanning:
./scripts/security-scan.sh --full
Checks performed:
Pass criteria:
Fail items block release completely.
Execute final release checklist:
./scripts/release-gate.sh --version=X.Y.Z
Verifies:
Pass criteria:
Either gate failure blocks release. Manual override requires CISO approval (security) or engineering director approval (release).
Auto-generate deployment documentation from DESIGN.md and SPECIFICATION.md:
Generate from SPECIFICATION.md user-facing requirements:
Format: Markdown → PDF/HTML via doc pipeline
Generate from DESIGN.md API contracts:
Format: OpenAPI spec → Swagger UI / Redoc
From DESIGN.md deployment topology:
Format: Markdown
From DESIGN.md and operational NFRs:
Create GitHub/GitLab PR with generated release description:
## Release v1.2.3
**Release Type:** [Major | Minor | Patch]
**Date:** [YYYY-MM-DD]
### Summary
[Auto-generated from SPECIFICATION.md summary]
### Features
- [REQ-FEAT-001] Feature description
- [REQ-FEAT-002] Feature description
### Fixes
- [REQ-BUG-001] Bug description
- [REQ-BUG-002] Bug description
### Breaking Changes
[If major version]
- [BREAKING-001] Description
- Migration guide: [link]
### Checklist
- [ ] All tests pass
- [ ] Documentation updated
- [ ] Security scan clean
- [ ] Changelog complete
- [ ] Version bumped correctly
- [ ] Release notes reviewed
**Artifacts:**
- Binary/image: [link]
- Documentation: [link]
- Changelog: [link]
Approvals:
- [x] Code review
- [x] Security review
- [x] Product review
Set PR to merge following the Gitflow-SDD branching strategy:
spec/NNN-* branch → target develop (after Phase 8 verification)develop → target stage (after integration review)stage → target main (after all blocking gates pass)Require 2+ approvals. Never merge a spec branch directly to main or stage.
Export implementation tracking to project management tool:
Generate from TASKS.md and implementation history:
Work Item Type: Release
Title: Release v1.2.3
Status: Ready for Release
Completion: 100%
Linked Tasks (completed):
- TASK-001: Feature A implementation (100%)
- TASK-002: Feature B implementation (100%)
- TASK-003: Bug C fix (100%)
Related PRs:
- PR-#451: Implement feature A
- PR-#452: Implement feature B
- PR-#453: Fix bug C
Metrics:
- Tasks completed: 20 of 20
- Lines of code: [count]
- Test coverage: 87%
- Cycle time: 14 days
Artifacts:
- Release binary: [link]
- Release notes: [link]
- Deployment guide: [link]
Export to Jira, Linear, Azure DevOps, or Asana via REST API.
Generate from commit history, SPECIFICATION.md, and VERIFICATION.md:
# Changelog - v1.2.3
**Released:** 2026-04-13
## [1.2.3] - 2026-04-13
### Added
- REQ-FEAT-001: User dashboard with real-time metrics
- REQ-FEAT-002: Bulk operations via CSV import
- REQ-FEAT-003: Advanced search with filters
### Fixed
- REQ-BUG-001: Login timeout on slow networks
- REQ-BUG-002: Export function truncating long values
### Changed
- REQ-ENHANCEMENT-001: Improved search performance by 40%
- REQ-ENHANCEMENT-002: Redesigned settings UI
### Deprecated
- Old reporting API (use Analytics API instead)
- CSV export format v1 (migrate to v2)
### Removed
- Legacy authentication method (deprecated in v1.1.0)
### Security
- Fixed XSS vulnerability in rich text editor
- Updated dependencies with security patches
### Performance
- Reduced API response time by 35% (REQ-NFR-001)
- Optimized database queries for large datasets
## [1.2.2] - 2026-03-30
[previous release notes...]
/specky:release --version=X.Y.Z # Full release workflow
/specky:release --security-scan # Run security gate only
/specky:release --generate-docs # Generate docs only
/specky:release --create-pr --no-merge # Create PR, don't merge
/specky:release --export-items # Export to project mgmt
If post-release issues detected:
/specky:rollback --version=X.Y.Z| Tool | Purpose |
|---|---|
sdd_create_pr | Generate PR payload with spec summary and correct branch target |
sdd_generate_all_docs | Parallel generation of all documentation types |
sdd_generate_docs | Generate user documentation from SPECIFICATION.md |
sdd_generate_api_docs | Generate API reference from DESIGN.md |
sdd_generate_runbook | Generate operational runbook from DESIGN.md |
sdd_generate_onboarding | Generate developer onboarding guide |
sdd_export_work_items | Export tasks to GitHub Issues / Azure DevOps / Jira |
@release-engineer — Phase 9 agent that runs blocking gates and calls these tools. Load this skill as first step.