Agent Skillssoftware-mansion/argent › argent-create-flow

argent-create-flow

GitHub

用于创建、录制和编辑可复用的 Argent 流程 YAML 文件,支持回放与修复。适用于重复交互场景及 A/B 测试配置。

packages/skills/skills/argent-create-flow/SKILL.md software-mansion/argent

Trigger Scenarios

录制或重放可重复的设备操作路径 设置性能分析或 A/B 比较 需要重复三次以上的交互操作

Install

npx skills add software-mansion/argent --skill argent-create-flow -g -y
More Options

Non-standard path

npx skills add https://github.com/software-mansion/argent/tree/main/packages/skills/skills/argent-create-flow -g -y

Use without installing

npx skills use software-mansion/argent@argent-create-flow

指定 Agent (Claude Code)

npx skills add software-mansion/argent --skill argent-create-flow -a claude-code -g -y

安装 repo 全部 skill

npx skills add software-mansion/argent --all -g -y

预览 repo 内 skill

npx skills add software-mansion/argent --list

SKILL.md

Frontmatter
{
    "name": "argent-create-flow",
    "description": "Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A\/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks, acceptance-driven regression tests, or screen video, use argent-test-ui-flow, argent-qa-flows, or argent-screen-recording respectively."
}

Create an Argent flow

An Argent flow is a replayable sequence in .argent/flows/<name>.yaml.

For a saved QA test case, ticket, or acceptance criterion, load argent-qa-flows first. It adds deterministic setup, acceptance evidence, and two-pass proof.

Read the relevant reference

  • Before creating or changing a flow, read Live authoring completely.
  • When polishing, composing, or manually reviewing YAML, read Flow YAML. For Vega, read its platform limits before recording remote or keyboard tools.
  • On capture warnings, raw coordinates, unavailable trees, mistimed transitions, overlays, or replay failures, read Reliability and recovery.

Non-negotiable rules

  1. Record the first walkthrough. Start the recorder before the first launch or in-app action. Do not reconstruct a rehearsed path.
  2. Record checks when their states appear. Record await-ui-element live, then convert it during polish. An echo records intent or diagnostic context, not app behavior or a verdict. A screenshot is human evidence, not an executable verdict. For absence, record the same selector as visible, perform the removing action, then record it as hidden.
  3. Use semantic targets. Prefer a strict id, then stable text or an accessibility label. Use scroll-to for off-screen elements. Resolve every raw-point warning immediately through the coordinate fallback gate.
  4. Prove every screen change. Record a destination-only identity check. During polish, follow it with await: { idle: true }. Stillness does not prove identity, and idle can pass with a warning.
  5. Polish only executed behavior. Convert recorded steps without changing their meaning. Record any missing action or structural check live. The only unrecorded insertions are a planned snapshot:, a navigation await: { idle: true }, and the documented Chromium packaging launch:.
  6. Replay the final YAML end to end. A normal flow needs one uninterrupted full pass. argent-qa-flows requires two consecutive passes.

Stable selectors

A stable selector is fixed by app code and survives account, data, time, count, order, and every locale and environment the flow supports. Prefer ids such as settings-screen. Do not gate on values such as Today, Item 4, usernames, counters, or timestamps.

Flow-only selector scopes

During polish, use within, after, and next to disambiguate repeated elements. Read Flow YAML: Relational scopes for their frame-based semantics and failure cases.

Workflow

  1. Choose the flow type:
    • e2e: the first non-echo step is launch:. The flow controls process start.
    • fragment: there is no leading launch. Declare a precise executionPrerequisite.
  2. Follow Live authoring: start, record one verified step at a time, finish, polish, audit, and replay.
  3. Report the file, replay command, result, prerequisite or side effects, and every coordinate or raw-gesture exception.

Proactive recording

Before repeating three or more interactions, tell the user and start a recording. Record that run and replay it afterward. A completed path cannot be recorded retroactively.

Repair

When replay fails, follow Reliability and recovery. Inspect the first divergence, correct the smallest justified unit, audit, and replay the full flow. Stop after two unsuccessful correction cycles. Never weaken a requested check to obtain a pass.

Version History

  • b1abdec Current 2026-08-15 02:58

    将技能文档拆分为参考文件并新增 argent-qa-flows 技能,优化内容加载效率。

  • a6422a3 2026-08-02 20:45

    新增CSS组合器选择器功能,支持基于元素相对位置(within/next/after)及通用选择器进行精准定位与条件判断。

  • a0460ee 2026-07-24 11:27

    新增 pinch 指令,支持针对特定选择器进行缩放手势操作;优化了缩放尺度的有效性检查与边缘安全策略,确保手势执行的几何计算准确性。

  • bc04c3b 2026-07-06 19:58

Same Skill Collection

packages/skills/skills/argent-android-emulator-setup/SKILL.md
packages/skills/skills/argent-device-interact/SKILL.md
packages/skills/skills/argent-ios-simulator-setup/SKILL.md
packages/skills/skills/argent-lens/SKILL.md
packages/skills/skills/argent-metro-debugger/SKILL.md
packages/skills/skills/argent-native-profiler/SKILL.md
packages/skills/skills/argent-react-native-app-workflow/SKILL.md
packages/skills/skills/argent-react-native-optimization/SKILL.md
packages/skills/skills/argent-react-native-profiler/SKILL.md
packages/skills/skills/argent-screen-recording/SKILL.md
packages/skills/skills/argent-screenshot-diff/SKILL.md
packages/skills/skills/argent-test-ui-flow/SKILL.md
packages/skills/skills/argent-tv-interact/SKILL.md
packages/skills/skills/argent-qa-flows/SKILL.md
packages/skills/skills/argent-settings-permissions/SKILL.md

Metadata

Files
0
Version
b1abdec
Hash
c0c258f1
Indexed
2026-07-06 19:58

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-15 18:07
浙ICP备14020137号-1 $お客様$