Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

lmd-finishing-a-development-branch

Sterne4

Forks0

Aktualisiert16. Juli 2026 um 15:48

Guides branch completion by verifying tests, detecting the workspace environment, presenting exactly 4 (or 3 for detached HEAD) integration options, then executing the choice with provenance-based worktree cleanup. Use when implementation is complete and you must decide how to integrate the work — merge, PR, keep, or discard.

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

dasTholo

dasTholo/lean-md

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

Datei-Explorer

2 Dateien

SKILL.md

readonly

name	lmd-finishing-a-development-branch
description	Guides branch completion by verifying tests, detecting the workspace environment, presenting exactly 4 (or 3 for detached HEAD) integration options, then executing the choice with provenance-based worktree cleanup. Use when implementation is complete and you must decide how to integrate the work — merge, PR, keep, or discard.

lmd-finishing-a-development-branch (delegation stub)

Body renders one phase at a time — never read it from disk. Rendering, diagnosis and fallback: see the lmd-rendering-skills skill.

Interactive, inline (main agent) — no subagent dispatch, no companions. Verifies tests, then branches the render by the human's chosen integration option.

Phases

pre-context → verify-tests → detect-env → present-options → then ONE option phase: merge-local | create-pr | keep-as-is | discard.

Each option phase is terminal (records the close via ctx_session); there is no follow-on skill.

Mehr aus diesem Repository

gleiches Repository

lmd-brainstorm

dasTholo/lean-md

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Use when starting creative work that will produce a versioned design spec.

2026-07-164

lmd-rendering-skills

dasTholo/lean-md

Use when you need to render an lmd-* skill phase or companion, or when a render call fails and you must decide whether the gateway is broken or the call was misaddressed.

2026-07-164

lmd-test-driven-development

dasTholo/lean-md

Use when implementing any feature or bugfix, before writing implementation code

2026-07-164

lmd-writing-skills

dasTholo/lean-md

Use when creating new skills, editing existing skills, or verifying skills work before deployment

2026-07-164

lmd-dispatching-parallel-agents

dasTholo/lean-md

Fans out one focused subagent per independent problem domain (disjoint files, no shared state), then conflict-scans and integrates. Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

2026-07-164

lmd-executing-plans

dasTholo/lean-md

Executes a .lmd.md plan in this session — the main agent runs each task itself, pauses at batch checkpoints for human review, and closes at a whole-branch final gate. No companions. Use when executing an implementation plan inline with human review checkpoints.

2026-07-164

name	lmd-finishing-a-development-branch
description	Guides branch completion by verifying tests, detecting the workspace environment, presenting exactly 4 (or 3 for detached HEAD) integration options, then executing the choice with provenance-based worktree cleanup. Use when implementation is complete and you must decide how to integrate the work — merge, PR, keep, or discard.

lmd-finishing-a-development-branch (delegation stub)

Body renders one phase at a time — never read it from disk. Rendering, diagnosis and fallback: see the lmd-rendering-skills skill.

Interactive, inline (main agent) — no subagent dispatch, no companions. Verifies tests, then branches the render by the human's chosen integration option.

Phases

pre-context → verify-tests → detect-env → present-options → then ONE option phase: merge-local | create-pr | keep-as-is | discard.

Each option phase is terminal (records the close via ctx_session); there is no follow-on skill.