Agent Skills › mvschwarz/openrig › development-team

development-team

GitHub

协调开发小队将需求转化为软件,涵盖构建、验证、QA及设计。指导解析项目上下文,执行TDD与缺陷修复,管理独立审查及手递流程,确保产出质量并处理阻塞问题。

skills/_canonical/pods/development-team/SKILL.md mvschwarz/openrig

Trigger Scenarios

开始或交接实现、QA或设计工作 需要协调开发、测试与设计角色协作

Install

npx skills add mvschwarz/openrig --skill development-team -g -y
More Options

Non-standard path

npx skills add https://github.com/mvschwarz/openrig/tree/main/skills/_canonical/pods/development-team -g -y

Use without installing

npx skills use mvschwarz/openrig@development-team

指定 Agent (Claude Code)

npx skills add mvschwarz/openrig --skill development-team -a claude-code -g -y

安装 repo 全部 skill

npx skills add mvschwarz/openrig --all -g -y

预览 repo 内 skill

npx skills add mvschwarz/openrig --list

SKILL.md

Frontmatter
{
    "name": "development-team",
    "description": "Use when a development pod begins or hands off implementation, QA, or design work."
}

Development Team

The pod turns the assigned user outcome into working software. Builders, QA and designers are capabilities; neighboring roles may be held by one seat unless independence was explicitly selected.

Start from the work

Run rig whoami --json, then resolve project.yaml -> mission.yaml -> active slice.yaml -> selected component or wave map -> addressed context. The complete lookup and precedence rule is docs/reference/product-journey-sdlc.md#resolve-the-selected-path (installed: $OPENRIG_HOME/reference/product-journey-sdlc.md#resolve-the-selected-path). Read the selected addresses and source needed for this task; skills available in your profile are capabilities, not a mandatory reading list. No composition means light Part A. Role names and idle seats add no gates. Explicit rigor and authored wave boundaries retain their named checks.

Build and verify

Clarify consequential uncertainty, inspect the existing seam, then complete one coherent outcome. Reproduce a defect before repairing it; use tests that distinguish the failure and verify through the public surface. Keep chunks as large as the outcome and file territory permit. TDD is a feedback loop, not a two-seat protocol.

The builder reports the exact candidate, changed behavior, commands and observed results, with remaining uncertainty. No universal pre-edit proposal, QA approval or post-edit gate is implied. When one is explicitly selected, honor its boundary and send the relevant evidence directly to its owner.

QA and design

QA compares the delivered behavior with the actual contract. Read the diff and exercise the result; avoid tests that merely repeat the implementation. On a tiny change the builder may hold QA. Independent QA excludes the author when selected. A wave receives independent review at its authored boundary, not per slice.

Design clarifies user flows and ambiguous behavior when the outcome needs it. Browser and dogfood skills load for a relevant UI journey, not every task. During assigned dogfood, fix-and-retest only within the granted scope; a read-only assignment stays read-only. If a tester becomes an author, preserve that attribution when independent evaluation is required.

Blockers and return

Use systematic-debugging for an unexpected failure and verification-before-completion before claiming success. A permission prompt is a concrete blocker; report the command and consequence instead of labeling it progress. A missing decision goes to the owner who can settle it.

Return the candidate and evidence through the selected handoff. Do not create obligations just to keep an idle QA, guard or reviewer occupied. Quality is a working product with honest evidence, not the number of transfers.

Version History

  • dc2221e Current 2026-10-18 15:37

Same Skill Collection

.agents/skills/developing-openrig/SKILL.md
.claude/skills/developing-openrig/SKILL.md
skills/_canonical/core/agent-starters/SKILL.md
skills/_canonical/core/agent-startup-and-context-ingestion/SKILL.md
skills/_canonical/core/cross-host-rig-commands/SKILL.md
skills/_canonical/core/human-in-the-loop/SKILL.md
skills/_canonical/core/messaging-the-human/SKILL.md
skills/_canonical/core/openrig-architect/SKILL.md
skills/_canonical/core/openrig-cmux/SKILL.md
skills/_canonical/core/openrig-software-factory/SKILL.md
skills/_canonical/core/openrig-upgrade/SKILL.md
skills/_canonical/core/rig-bundles-and-shareable-artifacts/SKILL.md
skills/_canonical/core/session-source-fork/SKILL.md
skills/_canonical/core/specification-system/SKILL.md
skills/_canonical/core/topology-mutation-and-seat-management/SKILL.md
skills/_canonical/core/watchdog/SKILL.md
skills/_canonical/pm/backlog-capture/SKILL.md
skills/_canonical/pm/context-builder/SKILL.md
skills/_canonical/pm/exec-summary/SKILL.md
skills/_canonical/pm/office-hours/SKILL.md
skills/_canonical/pm/plan-review/SKILL.md
skills/_canonical/pm/requirements-writer/SKILL.md
skills/_canonical/pm/ui-mockup/SKILL.md
skills/_canonical/pods/orchestration-team/SKILL.md
skills/_canonical/pods/review-team/SKILL.md
skills/_canonical/process/agent-browser/SKILL.md
skills/_canonical/process/dogfood/SKILL.md
skills/_canonical/process/frontend-design/SKILL.md
skills/_canonical/process/systematic-debugging/SKILL.md
skills/_canonical/process/test-driven-development/SKILL.md
skills/_canonical/process/verification-before-completion/SKILL.md
packages/daemon/assets/skills/rigs/SKILL.md
skills/_canonical/core/openrig-herdr/SKILL.md
skills/_canonical/core/openrig-skills/SKILL.md
skills/_canonical/core/rig-lifecycle/SKILL.md
skills/_canonical/pods/oversight-team/SKILL.md
skills/_canonical/process/context-engineering/SKILL.md
skills/rigs/SKILL.md

Metadata

Files
0
Version
dc2221e
Hash
3d712a94
Indexed
2026-10-18 15:37

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-19 04:24
浙ICP备14020137号-1