Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

commandagent-uat

Sterne0

Forks0

Aktualisiert18. Juni 2026 um 06:59

Plan and record CommandAgent UAT checks for CLI, REPL, slash-command, release, provider, or manual terminal behavior. Use when changes need user-acceptance validation beyond unit tests.

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

Kewton

Kewton/CommandAgent

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

SKILL.md

readonly

name	commandagent-uat
description	Plan and record CommandAgent UAT checks for CLI, REPL, slash-command, release, provider, or manual terminal behavior. Use when changes need user-acceptance validation beyond unit tests.

CommandAgent UAT

Use this skill after one or more changes are ready for acceptance validation.

Output

Write the report under workspace/management/runs/<run_id>/uat-report.md unless the user requests another path.

Include:

change or issue scope
acceptance scenarios
automated checks and results
manual CLI, REPL, TTY, release, or provider steps when relevant
expected results
evidence to collect on failure
pass/fail status
follow-up fix prompt when UAT fails

CommandAgent Checks

Use CommandAgent-specific surfaces:

commandagent --help
commandagent --version
provider-free CLI paths
interactive commandagent> REPL behavior
/plan-run and /ultra-plan-run when planning behavior changed
.commandagent/ sessions, plans, repairs, and logs when state behavior changed

Do not run live provider checks unless the user explicitly asks.

Mehr aus diesem Repository

gleiches Repository

commandagent-create-pr

Kewton/CommandAgent

Create a CommandAgent pull request from the current committed branch. Use when the user asks Codex to publish local work, open a PR, or prepare a branch for review in this repository.

2026-06-180

commandagent-issue-worker

Kewton/CommandAgent

Implement one assigned CommandAgent issue or task in a dedicated git worktree. Use when Codex is working from orchestration notes, issue acceptance criteria, or a feature branch and needs a scoped implementation workflow for this repository.

2026-06-180

commandagent-orchestrate

Kewton/CommandAgent

Plan CommandAgent issue orchestration through a dry-run manifest before any worktree, CommandMate, PR, merge, or UAT action. Use when the user asks to orchestrate multiple issues or plan parallel issue work.

2026-06-180

commandagent-release-post

Kewton/CommandAgent

Draft copy-ready release announcement text for a CommandAgent release. Use when the user asks for a release post, social post, announcement, or changelog-based summary.

2026-06-180

commandagent-release

Kewton/CommandAgent

Prepare or verify a CommandAgent release using the repository release process. Use when the user asks for a release, version tag, release PR, or GitHub Release for CommandAgent.

2026-06-180

commandagent-worktree-cleanup

Kewton/CommandAgent

Safely remove merged or obsolete CommandAgent git worktrees. Use when the user asks to clean up issue worktrees, feature worktrees, or all merged worktrees for this repository.

2026-06-180

name	commandagent-uat
description	Plan and record CommandAgent UAT checks for CLI, REPL, slash-command, release, provider, or manual terminal behavior. Use when changes need user-acceptance validation beyond unit tests.

CommandAgent UAT

Use this skill after one or more changes are ready for acceptance validation.

Output

Write the report under workspace/management/runs/<run_id>/uat-report.md unless the user requests another path.

Include:

change or issue scope
acceptance scenarios
automated checks and results
manual CLI, REPL, TTY, release, or provider steps when relevant
expected results
evidence to collect on failure
pass/fail status
follow-up fix prompt when UAT fails

CommandAgent Checks

Use CommandAgent-specific surfaces:

commandagent --help
commandagent --version
provider-free CLI paths
interactive commandagent> REPL behavior
/plan-run and /ultra-plan-run when planning behavior changed
.commandagent/ sessions, plans, repairs, and logs when state behavior changed

Do not run live provider checks unless the user explicitly asks.