菜单
This skill should be used when the user asks to "save to file", "download", "export", "store in file", or any request that involves getting data from Qlerify and saving it locally. Bypasses AI processing and is ~100x faster than MCP tools for large data exports.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/Qlerify/qlerify-plugins --skill download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。
Create, extend, validate, and improve Qlerify workflow diagrams and domain models, including domain events, roles, read models, commands, policies, aggregates, entities, value objects, attributes, given-when-then scenarios, bounded contexts, and invariants. Use when the task involves event storming, event modeling, domain-driven design (DDD), specification-driven development (SDD), model-driven development (MDD), software modeling, domain modeling, process modeling, legacy modernization, reverse-engineering code into a model, generating code from a model, or any direct use of the Qlerify modeling tools.
Generate production-ready code from a Qlerify domain model. Use when the user asks to "generate code from the model", "implement the workflow", "scaffold from Qlerify", "build the aggregate", "code up the domain model", "create the app from the model", or after a workflow has been modeled or extracted and the next step is producing runnable code on a target tech stack. Pairs with the workflow-creation skill (which produces the model) and the sync skill (which keeps model and code aligned over time).
Keep a codebase and its Qlerify domain model in agreement, in both directions. Use when the user asks to "sync domain model", "update Qlerify", "push changes to Qlerify", "sync schemas/entities/domain events", or after implementing features that add or change entities, API endpoints, commands, domain events, database schemas, migrations, or Prisma/GraphQL types — sync applies that code drift into the Qlerify model. Also use when the Qlerify model has been edited (new entities, changed commands, new acceptance criteria) and the code needs to catch up — sync detects the model-side drift and hands off to the code-generation skill. For brownfield/legacy codebases with unclear boundaries, isolate one aggregate at a time first (the workflow-creation skill's Phase 0 covers aggregate extraction).
正在显示 SKILL.md
基于 SOC 职业分类
| name | download |
| description | This skill should be used when the user asks to "save to file", "download", "export", "store in file", or any request that involves getting data from Qlerify and saving it locally. Bypasses AI processing and is ~100x faster than MCP tools for large data exports. |
| allowed-tools | Bash, Read, Glob |
CRITICAL: When saving ANY Qlerify data to a file, use curl + jq instead of MCP tools. MCP responses pass through
AI context which takes minutes for large data. Shell pipes take seconds.
cat ~/.claude.json 2>/dev/null | jq -r '.mcpServers.qlerify // empty'
Extract the url and headers.x-api-key.
curl -s "$MCP_URL" \
-H "x-api-key: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "TOOL_NAME",
"arguments": { ...ARGS... }
}
}' | jq -r '.result.content[0].text | fromjson' > output.json
curl -s "$MCP_URL" -H -H \
-d \
| jq -r > workflow.json
curl -s "$MCP_URL" -H "x-api-key: $API_KEY" -H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"generate_openapi_spec","arguments":{"workflowId":"...","projectId":"...","boundedContext":"..."}}}' \
| jq -r '.result.content[0].text' > swagger.yaml
curl -s "$MCP_URL" -H "x-api-key: $API_KEY" -H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_workflow","arguments":{"workflowId":"...","projectId":"..."}}}' \
| jq -r '.result.content[0].text | fromjson | .specification.schemas.entities' > entities.json
curl -s "$MCP_URL" -H "x-api-key: $API_KEY" -H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_workflow","arguments":{"workflowId":"...","projectId":"..."}}}' \
| jq -r '.result.content[0].text | fromjson | .specification.domainEvents' > events.json
| Data size | Method | Example |
|---|---|---|
| Small (< 50 lines) | MCP tool | list_workflows |
| Large (> 50 lines) | curl + jq | get_workflow, generate_openapi_spec |
| Any "save to file" | curl + jq | Always, regardless of size |
Use MCP tools for small lookups:
list_workflows → get workflow ID and project IDThen use curl for the actual data fetch.