agentleFS
brayandiazcbrayandiazc/project-starter-template-es-ai/.claude/skills/open-pr/SKILL.md

open-pr

Skill15 starsChanged 2 months agoMITView on GitHub

Redacta un pull request para la rama actual rellenando la plantilla de PR del repositorio en función de los cambios de la rama. Úsalo cuando la persona pida abrir/crear un PR, preparar un pull request o escribir la descripción de un PR (p. ej. "abre un PR", "redacta el pull request de esta rama"). No hace merge.

  • Commits and pushes

67 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use implement-change, review-change and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Codagent-AISkill

    implement-change

    Implements an approved change in one continuous session, with tiered test runs. Use when asked to implement a change from its approved definition, or to invoke codagent:implement-change.

    Also in 3 projects that use this

  • thlaureSkill

    review-change

    Use this skill when the user asks for a code review, a correctness pass, a check before PR, or asks whether a Signalist change follows project conventions.

    Also in 4 projects that use this

  • DataCoveySkill

    commit-push

    Commit and push the changes made on this chat session to the current branch. Use best practices from Conventional Commits.

    Also in 3 projects that use this

  • saffron-healthSkill

    address-review

    Address PR review comments systematically. Use when responding to code review feedback on a pull request.

    Also in 3 projects that use this

  • AnthropicSkill

    write-spec

    Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.

    Also in 3 projects that use this

  • owidSkill

    babysit-pr

    Spawn a background agent that babysits an open PR — triggers a Codex review, watches CI, judges and fixes valid findings, replies to and resolves review threads, and loops to a cap. Never merges. Trigger when the user asks to "babysit the PR", "ask for codex review(s) and watch CI", or after pushing a substantial chunk to a PR branch.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    NO hagas merge, NO apruebes, y NO marques ítems de la lista de verificación que no estén realmente hechos.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 66 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prepara un pull request para la rama actual.

  1. Antes de redactar nada, deja el cambio listo. Es el único momento en que alguien mira el conjunto completo, y lo que no se actualice aquí no se actualiza nunca:

    • Corre el subagente doc-keeper sobre el diff: sincroniza docs/architecture/*, los diagramas (entidades, pantallas, auth, componentes), el ADR si hubo decisión, la entrada del CHANGELOG.md y el ítem del roadmap que la spec declaró.
    • Corre bash .githooks/pre-push: los siete checks del CI, en unos quince segundos y sin gastar minutos de Actions.
    • Repasa docs/conventions/definition-of-done.md, y en especial lo que ninguna máquina comprueba: revisión humana del esquema, autorización probada con otro rol, los cuatro estados de la UI.

    Si algo queda en rojo, no abras el PR: dilo y arréglalo primero. Un PR que nace rojo se normaliza y deja de mirarse.

  2. Lee .github/PULL_REQUEST_TEMPLATE.md para conocer las secciones requeridas y la lista de verificación.
  3. Reúne contexto sobre los cambios de la rama:
    • git log <base>..HEAD --oneline para la lista de commits (la base suele ser main).
    • git diff <base>...HEAD --stat y revisa los diffs relevantes.
  4. Rellena cada sección de la plantilla usando ese contexto:
    • Resumen de qué cambió y por qué.
    • Issues vinculados / ADRs o especificaciones relacionados si se mencionan.
    • Notas de pruebas (qué ejecutaste o qué debería revisar quien haga la revisión).
    • Marca los ítems de la lista de verificación que realmente apliquen; deja el resto para la persona autora.
  5. Crea el PR con la CLI gh (p. ej. gh pr create --title ... --body ...) si la rama está pusheada; de lo contrario, muestra la plantilla rellenada para que la persona la pegue.
  6. Informa la URL del PR o el cuerpo redactado.

NO hagas merge, NO apruebes, y NO marques ítems de la lista de verificación que no estén realmente hechos. Escribe un PR en borrador si el trabajo está incompleto.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.