port-change
Skill2 starsChanged 2 months agoMITView on GitHub
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").
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibility-auditSkill
- changelogSkill
- commitSkill
- configure-repoSkill
- copywritingSkill
- design-system-auditSkill
- i18n-paritySkill
- identitySkill
- instantiateSkill
- migration-guardSkill
- new-adrSkill
- new-specSkill
- open-issueSkill
- open-prSkill
- prototypeSkill
- releaseSkill
- seo-auditSkill
- update-templateSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Ask which variants to port to and where their local copies live (or clone them).
- Distinctive: line 52
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 …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- TEMPLATE-REPO-ONLY skill: it exists to maintain the family of variants.
/instantiate removes it in instantiated projects. -->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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

