Chalk Labs
Need help deploying workflow?
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/cxh0312-workflow
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: productivity, agent-building
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. Checked Oct 25, 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/workflow
What's inside
- Skill name
workflow- Description
- 统一任务入口 — 自动分级、路由、状态跟踪。调用 /agent-workflow:workflow <任务描述> 启动
- License
- MIT
- Instructions
- 90 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Workflow — 统一任务入口
收到任务后,执行以下流水线。每一步必须输出结果,不得跳过。
## Step 1: Concrete Signal Gate
检查任务是否包含至少一个 concrete signal:
- 文件路径、函数名、组件名、接口名
- issue、错误日志、复现步骤、测试命令
- 验收标准、影响范围、明确的非目标
**缺信号** → 标记为"信息不足",询问用户补全,不继续分级。
## Step 2: 治理分级
根据以下矩阵判断级别:
| 条件 | 级别 |
|------|------|
| 单 commit + 方案明确(有文件路径/函数名/错误日志)+ 不改接口/存储 + 非调试 | **Patch** |
| 1-5 文件 + 边界清晰 + 无架构变更 | **Change** |
| >5 文件 或 跨模块 或 需求模糊 或 有架构影响 | **Initiative** |
例外:
- >5 文件但单一关注面(样式替换、批量重命名)且无跨模块契约影响 → Change
- 调试类任务允许先走 /investigate 调查,初始标注"临时 Change"
输出格式:
```
治理级别: Patch / Change / Initiative
判定依据: [1-3 条理由]
```
## Step 3: Solo / Team
| 级别 | 执行形态 |
|------|---------|
| Patch | 默认 **solo**,禁止 team |
| Change | 默认 **solo**;仅当存在 2+ 独立子任务、文件所有权不重叠、契约已冻结时可用 team |
| Initiative | 必须评估 team;若不用 team 需说明原因 |
输出:
```
执行形态: solo / team
```
## Step 4: 路由
| 任务类型 | 路由到 |
|----------|--------|
| Patch 实现 | 直接实现 → 定向验证 |
| Change 实现 | OpenSpec Light(proposal + tasks)→ 实现 → QA |
| Initiative 实现 | OpenSpec Full(proposal + design + APPROVED + tasks)→ TDD |
| 架构/设计评审 | /plan-eng-review |
| 调试/排查 | /investigate |
| 安全审计 | /cso |
| 设计咨询 | /design-consultation |
## Step 5: State Gate(Change / Initiative)
Change 且预计 >10 分钟、或 Initiative:创建 `.agent/current-task.json`。
```json
{
"governance": "Patch|Change|Initiative",
"phase": "classified",
"execution_shape": "solo|team",
"next_step": "..."
}
```
## Step 6: 执行
按 Step 4 的路由启动对应流程。Initiative 必须满足门禁(design.md → /plan-eng-review → APPROVED.md → tasks.md)后才开始编码。
## 用户确认规则
以下情况必须确认:
- 需求/目标/偏好不明确
- 多个方案影响架构/成本/数据模型
- 危险操作(rm -rf、DROP、force-push)
- Initiative 的 design review / APPROVED
以下情况自动继续:
- Patch 实现(除 commit 外)
- Change 的 proposal/tasks 创建
- 验证循环(失败后修复重试)From cxh0312/workflow-kit, MIT.
More from cxh0312/workflow-kit
- 0.464score
workflow:orchestration
cxh0312
Decide solo vs team execution, create owner lanes, state files, dependency order, and integration checks for Change/Initiative agent workflows.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:openspec-full
cxh0312
Create full OpenSpec proposal, design, approval record, and tasks for Initiative architectural or high-risk changes.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:openspec-light
cxh0312
Create lightweight OpenSpec proposal and tasks for Change tasks with clear scope and low architectural risk.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:verification
cxh0312
Enforce evidence-backed verification before claiming completion, committing, pushing, or opening a PR.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 4, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cxh0312/workflow-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cxh0312
- 0.464score
workflow:orchestration
cxh0312
Decide solo vs team execution, create owner lanes, state files, dependency order, and integration checks for Change/Initiative agent workflows.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:openspec-full
cxh0312
Create full OpenSpec proposal, design, approval record, and tasks for Initiative architectural or high-risk changes.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:openspec-light
cxh0312
Create lightweight OpenSpec proposal and tasks for Change tasks with clear scope and low architectural risk.
SkillCFreshness: CClaude Code +9 - 0.461score
workflow:verification
cxh0312
Enforce evidence-backed verification before claiming completion, committing, pushing, or opening a PR.
SkillCFreshness: CClaude 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 workflow 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
workflow skill. Agent Mart. https://agentmart.dev/skills/cxh0312-workflow (last updated 2026-10-24)