Skip to content
Agentmart
Submit a tool

dev

Skill by Brothelmdzz

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying dev?

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.

Book a call

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/brothelmdzz-dev

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.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
dev
Description
None
License
MIT
Instructions
166 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
  • name: missing
  • description: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /dev — 开发流水线编排器

## 启动声明(必读 · 不可跳过)

收到 `/dev` 调用后,**第一条回复必须严格按以下格式开头**:

> Using `dev-harness:dev` skill — running Step 0 (并行 3 条检测) now.

然后**在同一条回复内立即并行调用**下面"启动"段的 3 条 Bash 命令。

**禁止行为**:

- 只回复"收到,按 dev-harness 流程启动..."然后停下等下一轮
- 用抽象总结("我会先检测环境")代替实际 Bash 执行
- 只列出要做什么而不真正调用工具

**Why**:用户输入 `/dev` 是开始动作,不是请求解说。把"意图声明"绑死到"立即执行",是 harness engineering 的核心防摆烂手段(参考 superpowers `executing-plans` skill 的 "Announce at start" 同源设计)。

## 约束

- 每完成一个阶段/Phase,必须 `harness.py update` — 续跑的唯一依据
- 不在阶段间停下等用户 — 更新状态后直接继续
- Skill 解析走三层(L1 项目 > L2 用户 > L3 内置)
- 同一 Phase/阶段失败 3 次必须停下报告用户

## 脚本路径

所有脚本通过 `${CLAUDE_PLUGIN_ROOT}` 定位:

```bash
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" <cmd>
bash "${CLAUDE_PLUGIN_ROOT}/scripts/detect-stack.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/skill-resolver.py" <stage>
```

---

## 启动

并行执行环境检测:

```bash
cat .claude/harness-state.json 2>/dev/null || echo "NO_STATE"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/detect-stack.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/skill-resolver.py" --all
```

- **有 harness-state.json** → 读取 `current_stage`,续接该阶段
- **无状态** → 询问用户任务名称和类型,判断路线,初始化:

```bash
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" init "任务名" --route C
```

## Skill 解析

对当前阶段运行三层解析:

```bash
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/skill-resolver.py" <stage_name>
```

- L1/L2 命中 → 调用 `/skill-name`
- L3 命中 → 读取插件内置 SKILL.md 执行

## Pipeline 推进

每个阶段:

```bash
# 开始
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" update <stage> IN_PROGRESS

# 执行 Skill(根据解析结果)

# 完成
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" update <stage> DONE

# 直接继续下一个阶段,不停下
```

---

## 各阶段

### research(路线 B)
产出: `.claude/researches/*.md`

### prd(路线 A/B)
需要多轮对话。产出: `.claude/project-design/*-prd.md`

### plan(路线 A/B/C)

产出: `.claude/plans/*.md`。**等待策略读 `pipeline.yml` 或 `dev-config.yml` 的 `plan.fallback`**:

- `fallback: wait`(默认)— plan 写完停下,明确告诉用户"请 review,说'通过'后我会继续"。等审批
- `fallback: auto-approve` — plan 写完立即 `harness.py update plan DONE` 并进入 implement,不等用户。**告诉用户已自动通过**但不要等回复
- `fallback: skip` — 跳过整个 plan 阶段(D 路线/修 typo 类极简任务)

无配置时默认 `wait`。**禁止**在 `wait` 模式下用任何形式自作主张进入 implement。

### implement
读取 `.claude/plans/` 下的计划文档,逐 Phase 执行。

每个 Phase:
1. 按 plan 变更清单修改文件
2. 运行门禁(detect-stack.sh 检测 build/test 命令)
3. 门禁通过 → `harness.py update implement IN_PROGRESS --phase N --gate build=pass`
4. 继续下一个 Phase

Phase > 3 时,可用 background Agent(`isolation: "worktree"`) 并行执行无依赖的 Phase。

门禁命令来源(优先级):
1. `.claude/dev-config.yml` 的 `gates` 段
2. `detect-stack.sh` 自动检测

### post-implement 并行组(audit + docs + test)

implement 完成后,用 background Agent 同时启动三路:

From Brothelmdzz/dev-harness, MIT.

More from Brothelmdzz/dev-harness

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
May 11, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Brothelmdzz

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 dev 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dev?

CallGet help
Cite this page

dev skill. Agent Mart. https://agentmart.dev/skills/brothelmdzz-dev (last updated 2026-10-24)