Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

port-change

Sterne0

Forks0

Aktualisiert10. Juli 2026 um 04:06

Ports the current branch's change to this template's sibling variants (es/en × with-AI/no-AI) — translates the content, adapts or removes the AI layer depending on the target, and leaves each variant with a PR-ready branch. Use this when a template change must be replicated in the other variants (e.g. "port this change to the Spanish template", "replicate this in the variants").

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

brayandiazc

brayandiazc/project-starter-template-en-ai

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

SKILL.md

readonly

name	port-change
description	Ports the current branch's change to this template's sibling variants (es/en × with-AI/no-AI) — translates the content, adapts or removes the AI layer depending on the target, and leaves each variant with a PR-ready branch. Use this when a template change must be replicated in the other variants (e.g. "port this change to the Spanish template", "replicate this in the variants").

Replicate the current branch's change in the family's sibling variants:

🇬🇧 with AI: project-starter-template-en-ai · 🇪🇸 with AI: project-starter-template-es-ai
🇬🇧 no AI: project-starter-template-en · 🇪🇸 no AI: project-starter-template-es

Step 1 — Scope the change

Take the current branch's diff against main (git diff main...HEAD) and classify each file: general documentation, AI layer (.claude/, AGENTS.md, CLAUDE.md, specs/), or neutral tooling (.github/, scripts)?

Step 2 — Choose targets

Ask which variants to port to and where their local copies live (or clone them). Rules per target:

Same language, no AI: strip from the port everything that depends on the AI layer (skills, .claude/ hooks, mentions of agents). If a native equivalent exists (e.g. .githooks/), adapt there.
Other language: translate content and names following the rename map in .github/scripts/check-parity.sh (e.g. instantiate ↔ instanciar, port-change ↔ portar-cambio, update-template ↔ actualizar-plantilla). Placeholders get translated too ([PROJECT_NAME] ↔ [NOMBRE_DEL_PROYECTO]): respect the target's TEMPLATE-USAGE catalog.

Step 3 — Apply in each target

In each variant: create a branch with the same name as the origin one, apply the adapted change, and run its checks (.github/scripts/check-links.sh, check-placeholders.sh, tests if they exist).

Attribution: in the with-AI variants, commits carry the co-authorship trailer from docs/conventions/ai-agents.md; in the no-AI variants, commits carry NO attribution or mention of AI (neither in the message nor in the ported content).

Step 4 — Wrap-up

Summarize per variant: branch created, files ported, what was adapted or omitted and why. Remind them to open the PRs (/open-pr skill in the with-AI variants).

Example: branch feat/new-hook here → /port-change → feat/new-hook branches in the other 3 variants, translated and with the AI layer removed where it doesn't apply.

Do NOT push or open PRs without confirmation, do NOT blindly port AI-layer files to the no-AI variants, and do NOT leave variants half-done: if a target fails, report it explicitly.

Mehr aus diesem Repository

gleiches Repository

instantiate

brayandiazc/project-starter-template-en-ai

Instantiates this template into a real project through a guided interview — detects whether the project is new or existing, fills in the placeholders, adapts the docs to the project type, and decides the permissions policy. Use this when someone clones/adopts this template and wants to configure it for their project (e.g. "instantiate this template", "set up this template for my project", "bootstrap the project from this base").

2026-07-100

new-spec

brayandiazc/project-starter-template-en-ai

Scaffolds a new lightweight change spec by copying the spec template directory into a named spec folder. Use this when the user wants to start a spec, plan a change/feature, or create a design doc before implementing (e.g. "spec out the checkout redesign", "create a spec for the new auth flow").

2026-07-100

release

brayandiazc/project-starter-template-en-ai

Cuts a new version — moves the CHANGELOG's Unreleased section to a dated SemVer version, creates the commit and the tag, and optionally the GitHub release. Use this when someone asks to publish/cut a version or prepare a release (e.g. "cut version 1.2.0", "prepare the release", "publish a new version"). Does not push without confirmation.

2026-07-100

update-template

brayandiazc/project-starter-template-en-ai

Brings into this project the improvements its origin template received after instantiation — reads .template-origin, computes the tooling diff (skills, hooks, scripts, workflows) against the current template and offers to apply it. Use this when someone wants to update/sync the project with the template (e.g. "update the template", "pull in the template's new improvements").

2026-07-100

open-issue

brayandiazc/project-starter-template-en-ai

Drafts and creates a GitHub issue by filling out the right template from .github/ISSUE_TEMPLATE/ based on the type (bug, feature, documentation, task, or question). Use this when the user asks to open/create an issue, report a bug, or record a task/request (e.g. "open an issue for this bug", "create an issue for the new feature", "log this task"). Does not close or comment on existing issues.

2026-07-100

migration-guard

brayandiazc/project-starter-template-en-ai

Reviews a database migration before it ships to make sure it is safe — reversible, non-destructive, and backward-compatible — following the project's database conventions. Use this whenever you create, review, or approve a schema or data migration (e.g. "check this migration", "is this migration safe to deploy?").

2026-06-300

name	port-change
description	Ports the current branch's change to this template's sibling variants (es/en × with-AI/no-AI) — translates the content, adapts or removes the AI layer depending on the target, and leaves each variant with a PR-ready branch. Use this when a template change must be replicated in the other variants (e.g. "port this change to the Spanish template", "replicate this in the variants").

Replicate the current branch's change in the family's sibling variants:

🇬🇧 with AI: project-starter-template-en-ai · 🇪🇸 with AI: project-starter-template-es-ai
🇬🇧 no AI: project-starter-template-en · 🇪🇸 no AI: project-starter-template-es

Step 1 — Scope the change

Step 2 — Choose targets

Ask which variants to port to and where their local copies live (or clone them). Rules per target:

Same language, no AI: strip from the port everything that depends on the AI layer (skills, .claude/ hooks, mentions of agents). If a native equivalent exists (e.g. .githooks/), adapt there.
Other language: translate content and names following the rename map in .github/scripts/check-parity.sh (e.g. instantiate ↔ instanciar, port-change ↔ portar-cambio, update-template ↔ actualizar-plantilla). Placeholders get translated too ([PROJECT_NAME] ↔ [NOMBRE_DEL_PROYECTO]): respect the target's TEMPLATE-USAGE catalog.

Step 3 — Apply in each target

In each variant: create a branch with the same name as the origin one, apply the adapted change, and run its checks (.github/scripts/check-links.sh, check-placeholders.sh, tests if they exist).

Step 4 — Wrap-up

Summarize per variant: branch created, files ported, what was adapted or omitted and why. Remind them to open the PRs (/open-pr skill in the with-AI variants).

Example: branch feat/new-hook here → /port-change → feat/new-hook branches in the other 3 variants, translated and with the AI layer removed where it doesn't apply.

Do NOT push or open PRs without confirmation, do NOT blindly port AI-layer files to the no-AI variants, and do NOT leave variants half-done: if a target fails, report it explicitly.