Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Run Tests

ASecurity

Use when the user wants to run tests for the TodoCalendar project - runs all or specific test schemes via the project's test script

15 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsbash

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add sudopark/TodoCalendar --skill run-tests --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run Tests?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Run Tests
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sudopark-run-tests/badge)](https://www.skillsdirectory.com/skills/sudopark-run-tests)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: run-tests
description: Use when the user wants to run tests for the TodoCalendar project - runs all or specific test schemes via the project's test script
---

# Run Tests — TodoCalendar

`scripts/run-all-tests.sh`를 실행하여 프로젝트 테스트를 돌린다.

## Usage

```bash
# 전체 테스트
./scripts/run-all-tests.sh

# 특정 스킴만
./scripts/run-all-tests.sh Domain Repository

# destination 오버라이드
DESTINATION='platform=iOS Simulator,name=iPhone 16,OS=18.0' ./scripts/run-all-tests.sh
```

## 시뮬레이터

`DESTINATION` 을 안 주면 `scripts/ensure-test-simulator.sh` 가 **iPhone 16 / iOS 18.0** 을
확보해 UDID 로 넘긴다 — 없으면 만든다. CI(`pr_test.yml`)도 같은 스크립트를 부르므로
로컬과 CI 의 실행 기기가 갈리지 않는다.

기기·OS 를 바꿔야 하면 그 스크립트 한 곳만 고친다. 촬영 기준(snapshot-check §3 — iPhone 17
/ iOS 26.2)과는 별개다 — 스냅샷은 시뮬 상태에 의존해 전용기를 따로 쓴다.

## Available Schemes

`Extensions` / `Domain` / `Repository` / `AuthService` / `CommonPresentation` / `BillingScenes` / `CalendarPresentation` / `CalendarScenes` / `EventDetailScene` / `EventListScenes` / `SettingScene` / `MemberScenes` / `AIAgentScene` / `WidgetScenes` / `TodoCalendarApp` / `TodoCalendarAppWidget` / `TodoCalendarAppShare`

이 목록이 문서 쪽 스킴 목록의 **정본**이다 (CLAUDE.md §3에서 이관). 신규 스킴 등록 절차는 add-framework 스킬.

## Instructions

1. 프로젝트 루트(`/Users/sudo.park/Documents/codebase/TodoCalendar`)에서 실행
2. 인자 없이 실행하면 17개 스킴 전체 순차 실행
3. 실패 시 `FAILED` 스킴 목록과 상위 에러 라인 출력
4. 빌드 실패(`BUILD FAILED`)도 FAILED로 판정됨

## Invoke

```bash
cd /Users/sudo.park/Documents/codebase/TodoCalendar && ./scripts/run-all-tests.sh
```

## 종료 기록 — skill_end

**유저가 이 스킬을 직접 호출한 독립 런에서만** 남긴다. 결과 판정(PASS 스킴 / FAILED 스킴 + 상위 에러 라인)을 보고한 직후 `log-record.py skill_end --name run-tests` (명령·compliance 규칙은 CLAUDE.md §1). 실패가 났어도 판정을 보고했으면 이 스킬의 절차는 끝난 것이다 — 후속 수정은 troubleshoot·implement 소관이다.

**다른 스킬 안에서 도구로 호출된 경우는 기록하지 않는다** — implement 완료 판정의 스킴 실행, 페어 wrap-up의 검증 등. 런을 마무리하는 전이는 호출한 스킬 쪽이고 종료 레코드도 거기서 남는다. 여기서 또 남기면 한 런에 종료가 두 겹으로 쌓여 호출 스킬의 준수 신호와 섞인다.

종속 호출로 뜨는 구조적 누락률은 `usage-thresholds.json`의 `missing_rate_exempt_skills`로 처리한다 — 누락률 숫자를 근거로 위 기록 범위를 넓히지 않는다.

Attribution

sudoparksudopark
View sourceMore from sudopark →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →