.claude/skills/test/SKILL.md
Run tests and return a summary. Test logs are contained within the forked context; only the summary is returned to the main context.
npx skillsauth add peintangos/deep-agents-example testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run tests based on arguments and output only a results summary.
all -> Run both primary tests and E2E/integration tests when availableunit -> Run only the fast or primary test commande2e -> Run only the E2E/integration commandRead ralph.toml first if it exists, then CLAUDE.md and docs/architecture.md. Inspect common project files at the repo root only as needed (for example Makefile, justfile, package.json, pyproject.toml, Cargo.toml, go.mod, or other task-runner files).
Identify the best available commands for:
Prefer commands explicitly defined in ralph.toml. If the registry is missing or incomplete, prefer commands explicitly documented in project docs. Only then infer them from the repo's task runner or manifest files.
When ralph.toml exists, use:
test_primary for fast or primary teststest_integration for E2E or broader integration testsCommand selection rules:
unit, run the fast or primary test commande2e, run the E2E or broader integration command onlyall, run all distinct discovered test commandsunit and allIf the requested command category does not exist, report it as SKIPPED.
Run the selected fast or primary test command.
Run the selected E2E or broader integration command.
Output results in the following format. Do not output the full test log.
## Test Results
- Primary Tests: PASS (X passed) / FAIL (X passed / Y failed) / SKIPPED
- E2E / Integration Tests: PASS (X passed) / FAIL (X passed / Y failed) / SKIPPED
### Failure Details (failures only)
- `test name` — error message
data-ai
監査レポートを Zenn 技術記事向けの文体 (だ/である調 + 比較表 + 階層化された見出し) に整えるスキル。`src/reporter.ts` の骨組みを LLM が整形してレポート (`out/*.md`) を仕上げるときに読み込む。
testing
OSS リポジトリの既知脆弱性 (OSV / GHSA) を照合し、重大度と影響範囲を分類するスキル。セキュリティ監査を実行するときに読み込む。
data-ai
OSS リポジトリのメンテナンス健全性 (リリース頻度・Issue 対応速度・放置 PR) を定量的に評価するスキル。メンテナンス監査を実行するときに読み込む。
tools
OSS リポジトリのメインライセンスを特定し、商用利用制約・依存互換性・NG ライセンスの検出までを行うスキル。ライセンス監査を実行するときに読み込む。