docs: warn fork authors about GitHub's default PR base (#167)

Three personalized-fork PRs (#155, #162, #165) were filed against
upstream by accident in one week - GitHub points new fork PRs at the
upstream repo by default, and nothing warned about it at the moment of
filing. Adds a PR template with the heads-up in the compose box (plus
the review norms the process asks for anyway) and one sentence in
CONTRIBUTING's fork section naming the mechanism.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Mads Lorentzen
2026-07-16 22:26:45 +02:00
committed by GitHub
co-authored by Claude Fable 5
parent 848eddbecc
commit dd6d7efea6
2 changed files with 20 additions and 0 deletions
+15
View File
@@ -0,0 +1,15 @@
<!-- Heads-up before you publish: if you built this in a personalized fork
(your profile data, your market's job portals, another AI runtime),
note that GitHub points new PRs at the UPSTREAM repo by default.
Those adaptations live in forks - see CONTRIBUTING.md - and get
discovered via the pinned "Community forks & adaptations" discussion (#78).
Check the "base repository" dropdown above before you continue. -->
## What changed and why
## Failing case / reproduction (for fixes)
## Verification
<!-- What you ran, per CONTRIBUTING: python3 tools/lint_skills.py,
python3 tools/check_framework_version.py, bun test / bun run typecheck
in touched CLIs, python3 -m unittest discover -s tests -->
+5
View File
@@ -45,6 +45,8 @@ Reviews here are empirical. Bug reports are reproduced on master before the fix
Market-specific skills are genuinely valuable - they just live in forks, where their maintainers can test them and their users can find them.
One practical warning: when you open a PR from a fork, GitHub targets this upstream repo by default, not your own - three personalized-fork PRs landed here by accident in a single week ([#155], [#162], [#165]). Check the "base repository" dropdown before publishing.
## Porting to another AI runtime? Forks too
Claude Code is the reference runtime: it is what the maintainer runs daily and what every methodology change is verified on. A parallel command tree for another runtime (Codex, Antigravity, Gemini CLI, ...) would ship untested on every change - CI cannot run those harnesses - and each accepted runtime makes the next one harder to refuse. It is the same arithmetic that keeps market-specific portals in forks.
@@ -93,3 +95,6 @@ Questions and proposals are welcome in [Discussions](https://github.com/MadsLore
[#73]: https://github.com/MadsLorentzen/ai-job-search/issues/73
[#75]: https://github.com/MadsLorentzen/ai-job-search/issues/75
[#76]: https://github.com/MadsLorentzen/ai-job-search/issues/76
[#155]: https://github.com/MadsLorentzen/ai-job-search/pull/155
[#162]: https://github.com/MadsLorentzen/ai-job-search/pull/162
[#165]: https://github.com/MadsLorentzen/ai-job-search/pull/165