بنقرة واحدة
redsub-validate
Run lint, type check, and unit tests with evidence.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Run lint, type check, and unit tests with evidence.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Enforced release pipeline. Save → Validate → Review → Version → Merge → Tag → Push.
Initial plugin setup. Register plugins, permissions, create CLAUDE.md.
Diagnose and auto-repair plugin integrity.
Collaborative design through Socratic dialogue. Turn rough ideas into validated designs.
Deployment workflow for dev/prod environments.
Execute implementation plan task-by-task with subagent dispatch and 2-stage review.
| name | redsub-validate |
| description | Run lint, type check, and unit tests with evidence. |
Determine the project's validation commands:
package.json scripts and infer:
lint, lint:fix)check, typecheck)test, test:unit)pnpm-lock.yaml → pnpm, yarn.lock → yarn, default → npm)Run sequentially. Stop on first failure.
<package-manager> run <lint-script>
<package-manager> run <check-script>
<package-manager> run <test-script>
If the test script doesn't include a --run flag for watch-mode frameworks (e.g., vitest), append -- --run.
When a canonical source exists (config, constants, types), verify consumers stay in sync:
No claims without evidence. Follow this exact sequence:
Forbidden before verification: "should", "probably", "seems to", or satisfaction expressions ("Great!", "Done!", "Perfect!").
On success:
Validation passed (with evidence):
- lint: pass (0 errors, 0 warnings)
- type check: pass (0 errors)
- unit test: pass (N tests, 0 failures)
On failure:
Validation failed:
- [step]: [error details]
- Fix: [suggestion]