agentleFS
Sign inStart free
ethanaubuchonethanaubuchon/dossier-tradecraft/skills/open-draft-pr/SKILL.md

open-draft-pr

Skill3 starsChanged 49 days agoMITView on GitHub

Use in /implement after committing, to push the feature branch and open a draft PR, returning the PR ref. Thin and GitHub-specific (gh) behind a host-neutral contract. Transitional — removed under the post-v1 flow simplification. Project-overridable for provisioning-heavy open steps.

  • Commits and pushes

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. fallow-rs/fallow★ 5.3ksame name
    2. kvantatech/RedLine★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All GitHub/gh coupling lives here and in publish-pr.

    line 10

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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

Open Draft PR

Opens the draft PR that /implement's review step runs inside. Thin: push the branch, create a draft PR, return its ref. The PR is a draft (not ready) so review happens before it's "real" — and so pr-review-toolkit's PR-framed agents (when used via the agent-review ceiling) have a PR object to attach to.

All GitHub/gh coupling lives here and in publish-pr; the recipe and the other primitives stay host-agnostic.

Input

  • branch — the feature branch (from repo-setup), already committed.
  • title, body — composed by the recipe from the plan-file / ticket.

Steps

  1. Push the branch and set upstream if it isn't on the remote yet: git push -u origin <branch>.
  2. Idempotency — if a PR already exists for this branch (gh pr list --head <branch> returns one), return its ref instead of creating a duplicate (gh pr create errors when one exists).
  3. Open a draft PR: gh pr create --draft --title "<title>" --body "<body>" — base = the repo's default branch, head = the current branch (gh infers both; pass --base/--head explicitly if those defaults don't apply). Add per-repo flags (labels, reviewers) per the project's agent-instruction file.
  4. Capture and return the PR ref (number + URL) from the gh output.

Output / contract

  • In: a committed branch + PR title/body.
  • Out: the draft PR ref (number/URL), surfaced so agent-review and publish-pr can target it.
  • Side effects: pushes the branch (network write); creates a draft PR. Nothing merged or marked ready.

Project overrides

  • Provisioning-heavy open steps — a repo with a scripted opener (e.g. domainator's create-pr.sh: templated body, labels, linked issues) overrides this, keeping the contract (branch → PR ref).

Future scope

  • Transitional. Under the post-v1 flow simplification (review the branch directly, no draft PR), this primitive is removed and publish-pr absorbs PR creation. Keep it thin so its removal is cheap.

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.

Check your setup, free