一键导入
openspec-feature-list
Generate openspec/changes/<id>/feature_list.json by parsing openspec/changes/<id>/tasks.md (one feature per unique [#R<n>] checkbox task).
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。
菜单
Generate openspec/changes/<id>/feature_list.json by parsing openspec/changes/<id>/tasks.md (one feature per unique [#R<n>] checkbox task).
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
| name | openspec-feature-list |
| description | Generate openspec/changes/<id>/feature_list.json by parsing openspec/changes/<id>/tasks.md (one feature per unique [#R<n>] checkbox task). |
| metadata | {"short-description":"Generate feature_list.json from OpenSpec tasks.md"} |
Follow these instructions when this skill is invoked to generate or update openspec/changes/<change-id>/feature_list.json by parsing openspec/changes/<change-id>/tasks.md.
Do not add scripts or code files. Do not modify openspec/changes/<change-id>/tasks.md. Do not run any git commands.
$openspec-feature-list <change-id><change-id> is missing, ask the user for it once, then proceed.change-id = user-provided argument.tasks.md = openspec/changes/<change-id>/tasks.mdopenspec/changes/<change-id>/feature_list.jsontasks.mdtasks.md does not exist, stop and report an error. Do not create output.tasks.md into task blocks (checkbox-only)- [ ] ...- [x] ... (case-insensitive x is allowed)[#R<n>] (example: [#R12]).
[#R<n>] MUST be unique across the entire tasks.md.
- bullet and indentation):
ACCEPT: ...TEST: ...ref key: "R<n>" from [#R<n>] (example: [#R12] => key "R12").task_id:
1.1), store it."?".description:
task_id (if present).[#R1], [@F_login], [#REQ-...], [#SCN-...], and any other trailing [...] tokens).accept: the text after ACCEPT: in the block (trim).test: the text after TEST: in the block (trim).steps:
TEST starts with Manual: (case-insensitive), treat it as manual steps:
1) or 1..TEST as runnable command(s):
&& chains into separate commands.Run: <command>.category (simple heuristic from description, case-insensitive):
docs if contains: doc, docs, readme, changelogmaintenance if contains: refactor, cleanup, lint, reformatperformance if contains: perf, performance, benchmarktesting if contains: test, pytest, jest, unit, integrationfunctionalpasses: default false (see preservation rule below).feature_list.json already exists, preserve passes for matching ref keys.passes unless the user explicitly asks to reset (example: "reset passes").passes=false.openspec/changes/<change-id>/feature_list.json.indent=2 and a trailing newline.change_id = <change-id>generated_at = UTC ISO-8601 timestamp with Z suffix (example: 2026-01-06T02:30:00Z){
"change_id": "<change-id>",
"generated_at": "<UTC ISO-8601 Z timestamp>",
"features": {
"R1": {
"category": "functional",
"description": "New chat button creates a fresh conversation",
"task_id": "1.1",
"accept": "<ACCEPT value>",
"test": "<TEST value>",
"steps": [
"Navigate to main interface",
"Click the 'New Chat' button",
"Verify a new conversation is created",
"Check that chat area shows welcome state",
"Verify conversation appears in sidebar"
],
"passes": false
}
}
}
change-id, number of features generated, and output path.Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).
Use this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI) needs AI models via @cloudbase/js-sdk. Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. Models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field. MUST run two-step preflight before code — see body. Keywords: 页面, Web, 前端, React, Vue, Next, Nuxt, SPA, AI chat UI, generateText, streamText, createModel, hunyuan-exp, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the data wrapper model field. API differs from JS/Node SDK — streamText needs data wrapper, generateText returns raw response. MUST run two-step preflight before code — see body. Keywords: Mini Program AI, wx.cloud.extend.AI, 小程序成长计划, ai_miniprogram_inspire_plan, Token Credits 资源包, generateText, streamText, createModel, hunyuan-exp, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).
CloudBase Node SDK auth guide for server-side identity, user lookup, and custom login tickets. This skill should be used when Node.js code must read caller identity, inspect end users, or bridge an existing user system into CloudBase; not when configuring providers or building client login UI.
CloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.