Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

test-for-openclaw

Sterne2

Forks0

Aktualisiert28. April 2026 um 07:28

Require evidence before declaring coding work done in OpenClaw. Use when the request sounds like "verify this works", "what tests should we add", "prove this is safe", "is this ready", or any implementation, fix, refactor, review, or deploy task where the right level of proof is ambiguous or easy to under-scope.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

LeoYeAI

LeoYeAI/openclaw-coding-skills

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Softwarequalitätssicherungsanalysten und -testerInformatik- und Mathematikberufe·SOC 15-1253

Datei-Explorer

2 Dateien

SKILL.md

readonly

Mehr aus diesem Repository

gleiches Repository

build-for-openclaw

LeoYeAI/openclaw-coding-skills

Execute implementation work in small, reviewable slices inside OpenClaw. Use when the request is to "implement this", "make the code change", "add this behavior", "wire this up", or "patch this without rewriting everything", especially when the change should stay narrow and be verified immediately.

2026-04-282

debug-for-openclaw

LeoYeAI/openclaw-coding-skills

Triage and resolve failures inside an OpenClaw workspace with a disciplined debugging loop. Use when the request sounds like "help me debug this", "this test is failing", "the build broke", "this works sometimes and I do not know why", or when logs suggest a problem but not the cause.

2026-04-282

deploy-for-openclaw

LeoYeAI/openclaw-coding-skills

Prepare and execute deployment-oriented work in an OpenClaw workspace with explicit release safety, environment awareness, and rollback thinking. Use when the request sounds like "deploy this", "prepare this for production", "update config and ship it", "what is the rollback plan", "check release readiness", or when a change could affect production behavior or operator workflow.

2026-04-282

docs-for-openclaw

LeoYeAI/openclaw-coding-skills

Update technical documentation, operational notes, prompts, or decision records in an OpenClaw workspace with the same rigor used for code. Use when the request sounds like "update the docs", "write this down", "capture this decision", "document the setup", or when behavior changes and future agents need durable written context instead of tribal knowledge.

2026-04-282

frontend-for-openclaw

LeoYeAI/openclaw-coding-skills

Build or modify user-facing interfaces inside an OpenClaw workspace with strong interaction, responsiveness, and verification discipline. Use when the request sounds like "build this UI", "fix this page", "this interaction is broken", "make this responsive", "update this component", or any browser-facing change users will directly see, click, type into, or depend on visually.

2026-04-282

openclaw-dev-workflow

LeoYeAI/openclaw-coding-skills

Enforce a production-grade development workflow for OpenClaw coding work. Use when the request is broad or end-to-end, such as "build this feature", "fix this properly", "handle this coding task", "implement this across the codebase", or "help me ship this safely", especially when work spans multiple files and needs planning, verification, and clean closeout.

2026-04-282

name	test-for-openclaw
description	Require evidence before declaring coding work done in OpenClaw. Use when the request sounds like "verify this works", "what tests should we add", "prove this is safe", "is this ready", or any implementation, fix, refactor, review, or deploy task where the right level of proof is ambiguous or easy to under-scope.

Test For OpenClaw

Completion requires proof.

Process

Identify the real behavior at risk.
Choose the cheapest credible form of evidence.
Run verification as close as possible to the changed surface.
Record what passed, what was not run, and why.
Refuse to overclaim when evidence is partial.

Acceptable Evidence

targeted automated tests
lint or typecheck on affected code
browser-based flow verification for UI changes
reproduction before and after for bug fixes
diff inspection for prompt or documentation-only work

Reference Files

Read references/evidence-ladder.md when you need to choose the minimum credible proof for a change.

Bad Evidence

confidence without execution
"looks right"
passing unrelated tests
assumptions about triviality