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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/tractorjuice/arckit-kimi --skill arckit-gcloud-search命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | arckit-gcloud-search |
| description | Find G-Cloud services on UK Digital Marketplace with live search and comparison |
You are helping an enterprise architect find and compare G-Cloud services on the UK Digital Marketplace.
$ARGUMENTS
G-Cloud is the UK Digital Marketplace framework for procuring off-the-shelf cloud services:
This command:
IMPORTANT: Check prerequisites before proceeding:
a. Project with Requirements (MUST exist):
projects/[project]/ARC-*-REQ-v*.mdb. Architecture Principles (RECOMMENDED):
projects/000-global/ARC-000-PRIN-*.md existsNote: Before generating, scan
projects/for existing project directories. For each project, list allARC-*.mdartifacts, checkexternal/for reference documents, and check000-global/for cross-project policies. If no external docs exist but they would improve output, ask the user.
Scan requirements to identify what cloud services are needed:
Look for:
Service categories to identify:
Determine:
CRITICAL - Auto-Populate Document Control Fields:
Before completing the document, populate ALL document control fields in the header:
Construct Document ID:
ARC-{PROJECT_ID}-GCLD-v{VERSION} (e.g., ARC-001-GCLD-v1.0)Populate Required Fields:
Auto-populated fields (populate these automatically):
[PROJECT_ID] → Extract from project path (e.g., "001" from "projects/001-project-name")[VERSION] → "1.0" (or increment if previous version exists)[DATE] / [YYYY-MM-DD] → Current date in YYYY-MM-DD format[DOCUMENT_TYPE_NAME] → "G-Cloud Service Requirements"ARC-[PROJECT_ID]-GCLD-v[VERSION] → Construct using format above[COMMAND] → "arckit.gcloud-search"User-provided fields (extract from project metadata or user input):
[PROJECT_NAME] → Full project name from project metadata or user input[OWNER_NAME_AND_ROLE] → Document owner (prompt user if not in metadata)_partials/RENDERING.md fixes the ladder from the artefact's own regime; ${default_classification} applies only where that regime falls through to user config.Calculated fields:
[YYYY-MM-DD] for Next Review Date → Current date + 30 daysPending fields (leave as [PENDING] until manually updated):
[REVIEWER_NAME] → [PENDING][APPROVER_NAME] → [PENDING][DISTRIBUTION_LIST] → Default to "Project Team, Architecture Team" or [PENDING]Populate Revision History:
| 1.0 | {DATE} | ArcKit AI | Initial creation from `/skill:arckit-gcloud-search` command | [PENDING] | [PENDING] |
Populate Generation Metadata Footer:
The footer should be populated with:
**Generated by**: ArcKit `/skill:arckit-gcloud-search` command
**Generated on**: {DATE} {TIME} GMT
**ArcKit Version**: {ARCKIT_VERSION}
**Project**: {PROJECT_NAME} (Project {PROJECT_ID})
**AI Model**: [Use actual model name, e.g., "Claude Sonnet 5 (session default)"]
**Generation Context**: [Brief note about source documents used]
Read the template (user override takes precedence):
.arckit/templates-custom/gcloud-requirements-template.md.arckit/templates/gcloud-requirements-template.md.arckit/templates/gcloud-requirements-template.md.arckit/templates/_partials/RENDERING.md and resolve the <!-- DOC-CONTROL-HEADER --> marker in the template before writing. Do not hand-write the Document Control table: the partial RENDERING.md selects is the only source of the 14 standard fields and of the classification ladder.The template owns the document structure. Populate it — do not invent a parallel one.
Create directory: projects/[project]/procurement/
Fill Sections 1-5 from the analysis in Step 3:
ARC-000-PRIN-*.md where it exists; integration context from the INT-xxx requirements.Sections 6-9 are filled in Steps 5-7 below, once the search has run.
IMPORTANT: Now perform live marketplace search to find actual services.
For each service category identified:
Create search query:
site:digitalmarketplace.service.gov.uk g-cloud [service category] [key requirements]
Examples:
site:digitalmarketplace.service.gov.uk g-cloud cloud hosting kubernetessite:digitalmarketplace.service.gov.uk g-cloud monitoring prometheus grafanasite:digitalmarketplace.service.gov.uk g-cloud email delivery serviceInclude in query:
Use WebSearch tool to search Digital Marketplace.
For each major service type needed (up to 3 service types):
For each service found:
Fill Sections 6-8 of the template from what the search returned:
Search-result evidence is external content, so follow the citation instructions in .arckit/references/citation-instructions.md: place inline citation markers next to claims drawn from a supplier's service page and register each source in the template's External References section.
If WebSearch finds 5+ good matches:
If WebSearch finds 3-4 matches:
If WebSearch finds 1-2 matches:
If WebSearch finds 0 matches:
Fill the rest of the template, then write the file:
CRITICAL: Use the Write tool to save the completed document to
projects/[project]/procurement/ARC-{PROJECT_ID}-GCLD-v1.0.md. Writing it inline
risks the 32K output-token limit; the Write tool also creates parent directories.
Before writing, read .arckit/references/quality-checklist.md and verify all Common Checks plus the GCLD per-type checks pass. Fix any failures before proceeding.
Before finalizing, validate output:
Output to user:
✅ Generated G-Cloud service search for [PROJECT_NAME]
Framework: G-Cloud
Document: projects/[project]/procurement/ARC-{PROJECT_ID}-GCLD-v1.0.md
Requirements Summary:
- ✅ Requirements extracted from ARC-*-REQ-*.md
- [✅/⚠️] Architecture principles referenced
- ✅ Service category identified: [Category]
Marketplace Search Results:
- ✅ Executed WebSearch for: [search query 1]
- [✅] Executed WebSearch for: [search query 2] (if multiple)
- ✅ Found [X] matching services
- ✅ Shortlisted top [X] services for comparison
Recommended Service:
🏆 [Service Name] by [Supplier Name]
- Match Score: [X/Y] MUST + [X/Y] SHOULD requirements
- Link: [URL]
Alternative Services:
2. [Service Name] by [Supplier] - [URL]
3. [Service Name] by [Supplier] - [URL]
Next Steps:
1. Review document: projects/[project]/procurement/ARC-{PROJECT_ID}-GCLD-v1.0.md
2. Visit recommended service page: [Link]
3. Contact supplier for detailed information
4. Validate integration requirements (INT-xxx)
5. Complete due diligence checklist (Section 9.2)
6. Award contract via Digital Marketplace
Important: All shortlisted services should be validated against MUST requirements before selection.
For Cloud Hosting:
site:digitalmarketplace.service.gov.uk g-cloud cloud hosting kubernetes dockersite:digitalmarketplace.service.gov.uk g-cloud iaas virtual machines linuxsite:digitalmarketplace.service.gov.uk g-cloud paas cloud platform managedFor SaaS Platforms:
site:digitalmarketplace.service.gov.uk g-cloud monitoring observability prometheussite:digitalmarketplace.service.gov.uk g-cloud email delivery service smtpsite:digitalmarketplace.service.gov.uk g-cloud ci cd pipeline automationsite:digitalmarketplace.service.gov.uk g-cloud analytics data warehouseFor Specialized Services:
site:digitalmarketplace.service.gov.uk g-cloud cdn content delivery networksite:digitalmarketplace.service.gov.uk g-cloud backup disaster recoverysite:digitalmarketplace.service.gov.uk g-cloud security scanning vulnerabilityIf requirements suggest custom development rather than cloud services:
⚠️ FRAMEWORK MISMATCH DETECTED
Your requirements suggest custom development (FR-xxx functional requirements for building features).
G-Cloud is for buying off-the-shelf cloud services, not custom development.
✅ Use /skill:arckit-dos instead - Digital Outcomes and Specialists
DOS is the correct framework for:
- Custom software development
- Building new systems
- Hiring developers/specialists
- Project outcomes that require custom implementation
Only use /skill:arckit-gcloud-search if you need:
- Cloud hosting or infrastructure (IaaS/PaaS)
- Off-the-shelf SaaS platforms
- Managed cloud services
< or > (e.g., < 3 seconds, > 99.9% uptime) to prevent markdown renderers from interpreting them as HTML tags or emoji