菜单
Run tests with context-efficient output. Hides passing test output, shows ONLY failures. Use when running tests, checking if tests pass, or verifying changes. Also detects flaky tests.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jamesaphoenix/tx --skill test-quiet命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Turn a design spec into an explicit tx task graph with `tx decompose`, then refine the graph using normal tx task and dependency primitives.
Generate a detailed design document via `tx doc add design`. Covers architecture, interfaces, data model, invariants, failure modes, verification, and testing strategy. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Reads companion PRD automatically to map EARS requirements to invariants. Output lands in specs/design/<name>.md.
Generate a system overview spec via `tx doc add overview`. Produces an architectural overview covering problem, scope, components, data flows, and non-goals. References plan via file path instead of embedding. Plan lives in ~/.claude/plans/<name>.md. Output lands in specs/<name>.md with tx-managed frontmatter.
正在显示 SKILL.md
基于 SOC 职业分类
| name | test-quiet |
| description | Run tests with context-efficient output. Hides passing test output, shows ONLY failures. Use when running tests, checking if tests pass, or verifying changes. Also detects flaky tests. |
| allowed-tools | Bash(*) |
Runs vitest with minimal context consumption. Passing tests show as a single ✓ line. Failing tests show the test name + first line of error. This saves 90%+ of context tokens vs raw vitest output.
Based on HumanLayer's backpressure pattern: swallow passing output, dump failures.
ALWAYS use this skill instead of running vitest directly. Raw vitest output wastes context.
.claude/skills/test-quiet/scripts/run.sh
.claude/skills/test-quiet/scripts/run.sh test/integration/core.test.ts
.claude/skills/test-quiet/scripts/run.sh test/integration/
Re-runs failing tests multiple times to distinguish flaky from consistent failures:
.claude/skills/test-quiet/scripts/run.sh --flaky
.claude/skills/test-quiet/scripts/run.sh --flaky --runs 5
| Flag | Description |
|---|---|
--flaky | Re-run failing tests to detect flakiness |
--runs N | Number of re-runs for flaky detection (default: 3) |
[path] | Test file or directory (default: test/integration/) |
tx test-quiet — hide passing, show failures
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✓ test/integration/core.test.ts (82 tests)
✓ test/integration/cycle-scan.test.ts (15 tests)
✗ test/integration/cli-graph.test.ts (0 passed, 51 failed)
FAIL: CLI graph:link creates an anchor...
SyntaxError: JSON Parse error: Unexpected EOF
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1/3 files failed — 51/148 tests failed, 0 skipped (5s)
--flaky shows flaky tests: investigate timer/async issues (see test-diagnostics skill)