define-frontend-spec
在全局层面定义 frontend 工程约定与质量标准。在启动新 frontend 项目、frontend-spec.md 缺失或过时、或需要确立组件模式、accessibility 标准或 performance budget 时使用。产出 docs/frontend-spec.md，作为 frontend…
Skill by wanggang316
Chalk Labs
Need help deploying define-frontend-spec?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/wanggang316-define-frontend-spec
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, finance
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/define-frontend-spec
What's inside
- Skill name
define-frontend-spec- Description
- 在全局层面定义 frontend 工程约定与质量标准。在启动新 frontend 项目、frontend-spec.md 缺失或过时、或需要确立组件模式、accessibility 标准或 performance budget 时使用。产出 docs/frontend-spec.md，作为 frontend 工程规则的唯一事实来源。
- License
- unknown
- Instructions
- 366 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- accessibility-checklist.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from wanggang316/harness-stack
- 0.584score
fdd-planning
wanggang316
FDD 主流程 step 1（规划与拆解）。覆盖两段——plan（与用户弄清需求、经 investigator 调查代码库、定出 milestone、写出 plan.md 并呈现）与 features（把 milestone 拆成 features.json 并过 coverage 闸）。中间的 contract…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
fdd-execution
wanggang316
FDD 主流程 step 2——执行循环。串行驱动 feature 构建：next-feature → 派 implementer → handoff 决策树 → complete。每个 feature 由交接决策树把关（核验 implementer 自验留下的证据）。静态验证 → 代码审查 → user-test…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
fdd-validate
wanggang316
FDD 的验证流水线——里程碑 / 最终批量闸。一条线性、成本递增的三级 gate：静态验证（scrutiny-validator 硬门禁 test/lint/type-check + 逐 feature scrutiny）→ 代码审查（code-reviewer，逐 feature）→…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
fdd-validation-contract
wanggang316
为一个 plan 撰写 validation contract——把 definition of done 落成一组可测试、用户可观测的 assertion（VAL-<AREA>-NNN），带 persona 与声明的 Evidence。它是 fdd step 1（规划）里的 contract 阶段。契约通过逐…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
define-architecture
wanggang316
在全局层面定义系统 architecture。在启动新项目、architecture.md 缺失或过时、或系统结构发生重大变化时使用。产出 docs/architecture.md，作为系统的结构地图。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
design
wanggang316
为某个具体实现决策撰写一份 design doc（docs/design-docs/）。独立、由人触发——不属于主 build 流程。当一个解法足够含糊、技术路线应在动工前先论证清楚时使用；涵盖 feature design、技术性重构、架构决策与迁移。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
fdd
wanggang316
构建新特性的主流程编排器。契约优先的多 agent 架构——捕获一个 plan，定义可测试的断言，拆解为多个 feature，再用全新上下文的 implementer/reviewer/validator subagent 驱动一个里程碑设闸的执行循环。当一处改动触及多个文件、有多条验收标准、或跨越多个…
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
document
wanggang316
维护项目长期知识。用于已确认的行为、架构边界、术语、决策或操作方式发生变化，或把已验证的调查结论整理为可复用知识。
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
domain-modeling
wanggang316
构建并打磨项目的领域模型：在设计讨论中澄清术语、压测概念边界，并记录当场确定的定义和决策。
SkillAFreshness: A★ 1Claude Code +9 - 0.577score
skill-create
wanggang316
在 harness-stack 仓库里新增、拆分或调整 skill 时使用——决定调用方式、落位与注册、按约定写作、并实测插件能加载它。只管 harness-stack 自身约定，不教通用的 skill 写作方法。
SkillAFreshness: A★ 1Claude Code +9 - 0.577score
env-init
wanggang316
为并行开发初始化每个 worktree 独立隔离的 runtime 环境。在创建新 worktree、dev server 因 port 或 database 冲突、或首次为某个项目搭建多 worktree 并行开发时使用。
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
docs-init
wanggang316
对项目的文档结构与基础文档做一次性初始化。从 assets/ 的模板生成 docs/ 目录树、AGENTS.md、CLAUDE.md、README.md 以及基础文档。
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 16, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/wanggang316/harness-stack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from wanggang316
- 0.584score
fdd-planning
wanggang316
FDD 主流程 step 1（规划与拆解）。覆盖两段——plan（与用户弄清需求、经 investigator 调查代码库、定出 milestone、写出 plan.md 并呈现）与 features（把 milestone 拆成 features.json 并过 coverage 闸）。中间的 contract…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
fdd-execution
wanggang316
FDD 主流程 step 2——执行循环。串行驱动 feature 构建：next-feature → 派 implementer → handoff 决策树 → complete。每个 feature 由交接决策树把关（核验 implementer 自验留下的证据）。静态验证 → 代码审查 → user-test…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
fdd-validation-contract
wanggang316
为一个 plan 撰写 validation contract——把 definition of done 落成一组可测试、用户可观测的 assertion（VAL-<AREA>-NNN），带 persona 与声明的 Evidence。它是 fdd step 1（规划）里的 contract 阶段。契约通过逐…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
fdd-validate
wanggang316
FDD 的验证流水线——里程碑 / 最终批量闸。一条线性、成本递增的三级 gate：静态验证（scrutiny-validator 硬门禁 test/lint/type-check + 逐 feature scrutiny）→ 代码审查（code-reviewer，逐 feature）→…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
define-architecture
wanggang316
在全局层面定义系统 architecture。在启动新项目、architecture.md 缺失或过时、或系统结构发生重大变化时使用。产出 docs/architecture.md，作为系统的结构地图。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
design
wanggang316
为某个具体实现决策撰写一份 design doc（docs/design-docs/）。独立、由人触发——不属于主 build 流程。当一个解法足够含糊、技术路线应在动工前先论证清楚时使用；涵盖 feature design、技术性重构、架构决策与迁移。
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get define-frontend-spec running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
define-frontend-spec skill. Agent Mart. https://agentmart.dev/skills/wanggang316-define-frontend-spec (last updated 2026-10-24)