frontend-development
Skill292 starsChanged 21 days agoApache-2.0View on GitHub
实现或审查 1flowbase web/ 页面、交互、schema UI、样式与接口消费。按 DESIGN.md 和当前源码定位 owner；需求决策用 problem-framing，正式验收用 qa-evaluation。
13 other projects use a version of this.
Adopted by
Most recently taken up by
- lubusIN/frappe-skillstheir own version, first seen Nov 4, 2026
- its-ash/skillstheir own version, first seen Nov 1, 2026
- liushikuan63/Qoder-Optimizationtheir own version, first seen Nov 1, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- typv/nest-turbo-startertheir own version, first seen Oct 8, 2026
- ambient-code/platformtheir own version, first seen Oct 8, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- All-Hands-AI/OpenHands★ 93ksame name
- OpenHands/OpenHands★ 93ksame name
- typv/nest-turbo-starter★ 224same name
- ambient-code/platform★ 131same name
- avibebuilder/claude-prime★ 119same name
- lubusIN/frappe-skills★ 68same name
- aws-solutions/konductor★ 11same name
- Ampli-Group/agentic-mobile-blueprint★ 4same name
- liushikuan63/Qoder-Optimization★ 2same name
- dhslegen/digital-delivery-team★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api/AGENTS.mdAGENTS.md
- .memory/AGENTS.mdAGENTS.md
- web/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- backend-developmentSkill
- github-solution-researchSkill
- mcp-configuration-developmentSkill
- problem-framingSkill
- qa-evaluationSkill
- test-driven-developmentSkill
The file
Files
Frontend Development
Outcome and Entry
把已确认的用户流程落到现有前端结构，保留设计与业务真值。进入 web/ 先读 web/AGENTS.md 及改动目录的局部规则；复用已确认目标、授权和 AC，不重复对齐或另开 issue。
行为验证使用 test-driven-development 的风险策略；缺失业务语义或扩大目标、权限、contract 时回到 problem-framing，局部实现选择继续执行。
Design Truth and Architecture
DESIGN.md 是前端设计真值；先理解第 1–2 节的真值关系和视觉层，再按任务定位章节。精确 token 值和实际组件能力查它指向的源码，不从偶然页面样式反推全局设计。skill 只说明如何定位、应用和验证，不维护第二份 recipe / 状态色 / 断点规范。
设计约束：DESIGN.md → theme / token → shared UI → feature 局部实现
业务真值：backend DTO → api-client → feature api → UI
结构归属：app-shell / routes → features/* → shared/*（仅真实共享）- Shell 复用 Ant Design 与现有共享组件；Canvas / Inspector 使用现有 Editor UI，不另建视觉体系。
- 业务数据、权限、状态原因、排序 / 筛选 / 聚合由后端提供；前端拥有展示、交互与客户端草稿，不推断缺失业务真值。
- 接口字段沿用后端 DTO 原名；导航与按钮可见性不构成 API 授权。
- 单 feature 请求编排留在 feature api，跨 feature 真实复用才提到 shared/api；schema 关系为
shared/schema-ui → feature schema → node definitions → renderer / consumer。
Read by Task
只读取命中任务与直接风险的行；设计与源码冲突时说明偏离，不能以同步为由修改产品语义。
| 任务信号 | 最短入口 |
| 工作区、页面 recipe、L1 详情、状态或响应式 | workspace-rules → DESIGN.md 对应章节 |
| 目录落点、API 编排、schema / node 分层 | placement-rules |
| 入口层级、同类对象行为、反馈位置 | interaction-architecture-gate |
| DTO、权限消费、取消、流式状态 | consumer-contracts → 受影响源码 |
| i18n key / value、owner、unused key | i18n-rules |
| 样式、第三方 slot、共享组件覆写 | visual-baseline；运行态再读 browser-verification |
| 报表、ECharts、JS Block chart | chart-reporting |
| 新公共 props、抽象、重复防御或转发层 | design-rules；具体坏味道查 anti-patterns |
| 实现完成、直接风险自查 | review-checklist |
| 修改本 skill 或检查合法例外 | pressure-scenarios |
Execution and Handoff
- 先确认主路径、详情规则、反馈位置与 owner，再落组件与样式；缺后端 DTO / 聚合时联动
backend-development，不添加前端兼容推断。 - 测试资源沿用仓库包装器与
.1flowbase.verify.local.json，不写死并发；执行成本、停止与证据复用见test-driven-development。 - 完成开发后使用
qa-evaluation；交付保留页面 / 组件 / API 消费链、关键决策与证据指针，已有 AC 逐点映射，不复制代码或重述 diff。 - 当前结果与直接风险证据充分即停止；缺证据明确标为未验证，不自动升级全仓 lint / build / 浏览器回归。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.