Agent skill · Testing & QA

t-web-demo-run-all

Discover all non-live Demo E2E tests and run them one file at a time in the main session, diagnosing and fixing failures inline, restarting the environment after backend code changes and rebuilding demo data between files, until every file is resolved or exhausts its retry budget. Supports an optional scan mode that pre-runs all files without repairing, clusters failures by shared root cause, and fixes each unique cluster once before re-verifying affected files.

timzaak55★ · 1 repos on radarProfile →
claude-codecan modify filesApache-2.0
Install
npx skills add timzaak/web-dev-skills --skill t-web-demo-run-all --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 9 KB
Bundled scripts: none
Allowed tools: -Read-Glob-Grep-Bash-Write-Agent
Path: skills/t-web-demo-run-all/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 55
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 批量运行 Demo 测试（主会话逐文件驱动） 运行时边界统一参考：`${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md` 单文件运行与修复闭环统一参考：`${CLAUDE_PLUGIN_ROOT}/protocols/web-demo-run-repair-contract.md` ## 目标 - 自动发现除 `live/`、`fixtures/`、`templates/`、`verification/` 和文件名含 `test-` 之外的全部 Demo 测试。 - **由当前主会话逐个文件驱动**，每一步都是可观察、可中断的短 Bash / Agent 调用。 - 单文件失败时复用 `/t-tools:t-web-demo-run` 的修复流程：整文件跑 → 失败时拆用例 → 每用例诊断 → 分发修复 → 补测 → 重跑，每文件最多 6 次尝试。 - 当次修复实际产生后端代码变动时，在当前 Demo 验证前重建环境。 - 文件之间重建 Demo 环境和数据容器，避免前一文件产生的业务数据影响后续测试。 - 每文件达到上限仍失败则标记 `FAILED` 并继续下一个文件，不阻塞整批。 - 持续写盘批次状态，支持 `continue` 从未完成文件的断点恢复。 - 产出 Markdown + JSON 汇总报告。 ## 为什么不再 fork 嵌套 `claude -p` 旧版本对每个文件 spawn 一个嵌套 Claude CLI 子进程并串行等待，叠加多轮 diagnose→fix→retest 和长超时，会长时间阻塞发起调用的会话。本 skill 改为**主会话直接驱动循环**：每条命令都是独立、可见的 Bash/Agent 调用，可以随时 Ctrl-C 后用 `/t-tools:t-web-demo-run-all continue` 从断点恢复。 ## 使用方式 ```bash /t-tools:t-web-demo-run-all # 从头运行全部非 live 文件 ``` ```bash /t-tools:t-web-demo-run-all continue # 从最近运行中批次的未完成断点继续 ``` ```bash /t-tools:t-web-demo-run-all scan # 先预扫描聚类，再按唯一根因修复（见"扫描模式"） ``` ## 两种模式 默认逐文件模式（无参数 / `continue`）：发现 → 逐文件跑 → 失败就当场修复 → 文件间数据隔离 → 收尾。每个文件独立诊断修复，互不参照。 扫描模式（`scan`）：先纯 Bash 预跑全部文件**不修复**，按归一化错误指纹聚类失败，再对每个 unique cluster 只修一次（用 representativ

What's inside
Steps it walks through
  1. 目标
  2. 为什么不再 fork 嵌套 claude -p
  3. 使用方式
  4. 两种模式
  5. 执行流程（默认逐文件模式）
  6. A. 发现阶段（一次性，脚本辅助）
  7. B. 主循环：对 discoveredfiles[resumeindex:] 逐个文件
  8. C. 收尾
  9. 恢复机制
  10. 批次状态契约
  11. 汇总报告
  12. 失败处理
  13. 执行流程（扫描模式）
  14. S1. 发现阶段
Commands it runs
uv run scripts/web-demo-run-all.py discover [--filter-file <path>]
uv run scripts/web-demo-run-all.py discover continue
uv run scripts/web-demo-run-all.py checkpoint --json <json_report> --index <zero_based_index>
uv run scripts/web-demo-test-runner.py "<rel_path>" --run-id "<batch_run_id>-<file_key>-initial" --mode fast
uv run scripts/demo-stop.py --quiet && uv run scripts/demo-start.py
uv run scripts/web-demo-run-all.py finalize --json <json_report>
uv run scripts/web-demo-run-all.py scan --json <json_report> [--scan-run-id <id>]
uv run scripts/web-demo-test-runner.py "<rel_path>" --run-id "<scan_run_id>-<file_key>-scan" --mode fast
uv run scripts/web-demo-run-all.py cluster --json <json_report>
More from web-dev-skills
All skills →
t-demo-run-allDiscover all non-live Demo E2E tests and run them one file at a time in the main session…Testing & QAt-demo-runRun a single demo E2E test file, diagnose failures, dispatch fixes to agents, and re-run until pass.Testing & QAt-decisionDecide whether a feature should enter the t-tools workflow before tech research or PRD.Workflow & Productivityt-docGenerate project tutorial documentation that reads like a human wrote it, not like AI output. Scans…Backend & APIt-design-checkEvaluate technical design documents for implementability, completeness, and consistency with a…Design & Presentationt-demo-acceptValidate demo tests cover user stories, compile and pass, and output structured acceptance reports.Other
About this skill
What does the t-web-demo-run-all skill do?

Discover all non-live Demo E2E tests and run them one file at a time in the main session, diagnosing and fixing failures inline, restarting the environment after backend code changes and rebuilding demo data between files, until every file is resolved or exhausts its retry budget. Supports an optional scan mode that pre-runs all files without repairing, clusters failures by shared root cause, and fixes each unique cluster once before re-verifying affected files.

How do I install it?

Run `npx skills add timzaak/web-dev-skills --skill t-web-demo-run-all --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From timzaak/web-dev-skills, a repository with 55 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.