WIP: feat(skills): batch-review, a review pass over the open pull requests: ranked, one subagent each, code only #908

Draft

HumanBean wants to merge 2 commits from HumanBean/Longshot:feat/batch-review-skill into main

pull from: HumanBean/Longshot:feat/batch-review-skill

merge into: MagicBeanDev:main

MagicBeanDev:main

Conversation 1 Commits 2 Files changed 2 +118

HumanBean commented 2026-11-15 20:08:57 +00:00

Owner

• Copy link
• Copy Markdown

Type: feat · Risk: low · Tested on: not run in the game (a skill file and one line in AGENTS.md) · Needs: none

Why

Reviews pile up faster than people can read them: there were 265 open pull requests when this was written, and the
review pass over the top 30 took one long session to do by hand. A maintainer wants to say "review the top 20" and get
the PRs ranked by what matters to players, each read by its own reviewer, the small conflicts and nits fixed on the
spot, every review posted on the forge, and a report that shows plainly which PRs are ready for a human to merge.

What changed

Adds the batch-review skill (/batch-review top 20, /batch-review next 30, /batch-review top 10 perf fixes) and
a pointer to it in AGENTS.md. The skill ranks the open PRs, runs one subagent per PR, and reports in tables.

• .claude/skills/batch-review/SKILL.md:
  • Rank: priority label, then what the change does for players, then how finished it is. Skips WIP PRs and PRs
    already reviewed at their current head, so "next 30" starts where the last pass ended. A re-review of a PR whose
    author pushed since ranks high.
  • Review: one subagent per PR, code only: nothing from the PR is built, run or tested. It fixes a basic conflict
    or a nit in a workspace of its own and pushes it to the PR's branch (a suggestion in the review when the push is
    refused), then posts one review with the verdict docs/forge.md defines.
  • Report: tables built from the forge's state after the agents finish: ready to merge, fixed and pushed, waiting
    on a test run, needs the author, comments, duplicates and merge order, not reviewed.
• AGENTS.md: one bullet pointing at the skill.

Measurements

Nothing to measure: a skill file and one documentation line, no code the game runs.

Flags and settings

None.

Testing

Tested: the skill's steps were followed by hand for a review pass over 60 open PRs on 2026-11-15 (the reviews, the
fixes' push path and the tables); the file here is those steps written down for the team.

Not tested: /batch-review itself as one command: the skill didn't exist as a command until this file.

Must be tested: None.

Risks

What could break: the skill tells agents to push fixes to other people's PR branches. It limits that to basic
conflicts and nits, never a change in behaviour, a design or what a PR measured, and it falls back to a suggestion in
the review when the push is refused.

Turning it off: revert the commit.

Compatibility: Nothing changes.

Checklist

Everyone

• One topic.
• The title is a Conventional Commit (type(scope): description) of the status line's type.
• Why gives the reason plainly and links the issues that fit (the tracker searched).
• Measurements has a verdict, or one line saying why there is nothing to measure.
• Testing names what was tested, what wasn't, and what must still be tested, where and how.
• Rebased on current main.
• python -I -B tests/run_all.py passes (any failure that also fails on main is named).
• No game files, dumps, build output or generated files.
• third_party/ untouched (a new folder with a PROVENANCE.md instead).
• The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled.

When it applies

• AI assistance recorded with Assisted-by: / Co-Authored-By: trailers.
• Docs updated.

🤖 Generated with Claude Code

**Type:** feat · **Risk:** low · **Tested on:** not run in the game (a skill file and one line in AGENTS.md) · **Needs:** none ## Why Reviews pile up faster than people can read them: there were 265 open pull requests when this was written, and the review pass over the top 30 took one long session to do by hand. A maintainer wants to say "review the top 20" and get the PRs ranked by what matters to players, each read by its own reviewer, the small conflicts and nits fixed on the spot, every review posted on the forge, and a report that shows plainly which PRs are ready for a human to merge. ## What changed Adds the `batch-review` skill (`/batch-review top 20`, `/batch-review next 30`, `/batch-review top 10 perf fixes`) and a pointer to it in AGENTS.md. The skill ranks the open PRs, runs one subagent per PR, and reports in tables. - `.claude/skills/batch-review/SKILL.md`: - **Rank:** priority label, then what the change does for players, then how finished it is. Skips WIP PRs and PRs already reviewed at their current head, so "next 30" starts where the last pass ended. A re-review of a PR whose author pushed since ranks high. - **Review:** one subagent per PR, code only: nothing from the PR is built, run or tested. It fixes a basic conflict or a nit in a workspace of its own and pushes it to the PR's branch (a suggestion in the review when the push is refused), then posts one review with the verdict docs/forge.md defines. - **Report:** tables built from the forge's state after the agents finish: ready to merge, fixed and pushed, waiting on a test run, needs the author, comments, duplicates and merge order, not reviewed. - `AGENTS.md`: one bullet pointing at the skill. ## Measurements Nothing to measure: a skill file and one documentation line, no code the game runs. ### Flags and settings None. ## Testing **Tested:** the skill's steps were followed by hand for a review pass over 60 open PRs on 2026-11-15 (the reviews, the fixes' push path and the tables); the file here is those steps written down for the team. **Not tested:** `/batch-review` itself as one command: the skill didn't exist as a command until this file. **Must be tested:** None. ## Risks **What could break:** the skill tells agents to push fixes to other people's PR branches. It limits that to basic conflicts and nits, never a change in behaviour, a design or what a PR measured, and it falls back to a suggestion in the review when the push is refused. **Turning it off:** revert the commit. **Compatibility:** Nothing changes. ## Checklist ### Everyone - [x] One topic. - [x] The title is a Conventional Commit (`type(scope): description`) of the status line's type. - [x] Why gives the reason plainly and links the issues that fit (the tracker searched). - [x] Measurements has a verdict, or one line saying why there is nothing to measure. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`. - [ ] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). - [x] No game files, dumps, build output or generated files. - [x] `third_party/` untouched (a new folder with a `PROVENANCE.md` instead). - [x] The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled. ### When it applies - [x] AI assistance recorded with `Assisted-by:` / `Co-Authored-By:` trailers. - [x] Docs updated. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

HumanBean added 1 commit 2026-11-15 20:08:57 +00:00

feat(skills): batch-review, a review pass over the open pull requests: ranked, one subagent each, code only ... 68316a9c04

Co-Authored-By: Claude Sonnet 5.5 <[email protected]>

BeanIssues added the

area/tooling

kind

feature

labels 2026-11-15 20:08:59 +00:00

HumanBean commented 2026-11-15 20:10:23 +00:00

Author

Owner

• Copy link
• Copy Markdown

Added a rule to the skill after the first pass: a reviewer keeps the author's commits when it rebases, and never squashes or rewrites their history for a nit.

Added a rule to the skill after the first pass: a reviewer keeps the author's commits when it rebases, and never squashes or rewrites their history for a nit.

HumanBean added 1 commit 2026-11-15 20:10:24 +00:00

fix(skills): batch-review keeps the author's commits when it rebases, never squashes them ... 58180c656e

Co-Authored-By: Claude Sonnet 5.5 <[email protected]>

BeanIssues added the

risk

low

label 2026-11-15 20:27:06 +00:00

Some checks failed

Hide checks

CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped

Details

CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped

Details

CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped

Details

Third-party parts / The same as upstream (pull_request) Has been skipped

Details

PR description / Description follows the template (pull_request_target) Successful in 4s

Details

CI / Conventional Commit title (pull_request) Successful in 3s

Details

CI / Workflow lint (actionlint) (pull_request) Successful in 6s

Details

Guide screenshots / Guide images and local UI source review (pull_request) Failing after 5s

Details

Third-party parts / As their notes say (pull_request) Successful in 10s

Details

Website / Website on Cloudflare (pull_request_target) Has been skipped

Details

This pull request is marked as a work in progress.

This branch is out-of-date with the base branch

View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.

git fetch -u 'feat/batch-review-skill:HumanBean-feat/batch-review-skill'

git switch 'HumanBean-feat/batch-review-skill'

Sign in to join this conversation.

Reviewers

No reviewers

Labels

Clear labels   

area/accessibility

Barriers for people with disabilities

  

area/audio

Sound and music

  

area/input

Controllers, keyboard, mouse

  

area/install

Installing, updating, building from your game

  

area/menu

In-game menu and settings

  

area/renderer

Vulkan renderer, shaders, effects

  

area/saves

Save files

  

area/tooling

Developer tools: scripts, CI, build and release tooling

  

area/upscaling

DLSS, FSR, frame generation

  

beanstalk: approved @ 1697603

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 2c5a62e

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 4fd82b7

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 64d6d09

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 6f91fae

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 70a78f9

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 8015c9a

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 8d361dc

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ 9d8356e

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ abf2227

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ d82f202

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ e5f1e40

Set by Beanstalk for show; the farm's database is what counts

  

beanstalk: approved @ ee8ab5f

Set by Beanstalk for show; the farm's database is what counts

  

ci: approved

A maintainer approved CircleCI for this fork PR (sticky; removed after 14 quiet days)

  

good first issue

A good start for a new contributor

  

gpu/amd

AMD GPUs

  

gpu/igpu

Integrated GPUs

  

gpu/intel

Intel GPUs

  

gpu/nvidia

NVIDIA GPUs

  

help wanted

Extra hands or knowledge wanted

  

kind

bug

Something doesn't work as it should

  

kind

chore

Build, CI, dependencies, tidying

  

kind

docs

Documentation

  

kind

feature

A new feature or an improvement

  

kind

performance

Frame rate, frame time, loading, memory

  

kind

question

A question rather than a change

  

needs measurements

Waiting for before/after measurements

  

platform/linux

Affects Linux (a change for every system carries both Windows and Linux)

  

platform/macos

macOS (Apple silicon or Intel Macs)

  

platform/steam-deck

Steam Deck

  

platform/windows

Affects Windows (a change for every system carries both Windows and Linux)

  

preview

Maintainers: deploy a preview of this PR's website (read its changes first). Removed after the run.

  

priority

critical

Crashes, data loss, or blocks most players

  

priority

high

Important: next in line

  

priority

low

Nice to have

  

regression

Worked in an earlier build, broken in a newer one: highest priority, above other bugs

  

risk

high

Broad or core change: the renderer, defaults on many systems, saves, installs, security

  

risk

low

Small, contained change: little can break

  

risk

medium

Changes behaviour in one area, or a default on some systems

  

status

blocked

Waits on something else first

  

status

confirmed

Reproduced or agreed on

  

status

duplicate

Already reported or proposed

  

status

invalid

Not a problem in this project

  

status

needs-info

Waiting for more information from the reporter

  

status

wontfix

Will not be worked on

  

testing wanted

Wanted: a test on other hardware (posts a test request in #test-requests)

  

ci: approved

No labels

area/accessibility

area/audio

area/input

area/install

area/menu

area/renderer

area/saves

area/tooling

area/upscaling

beanstalk: approved @ 1697603

beanstalk: approved @ 2c5a62e

beanstalk: approved @ 4fd82b7

beanstalk: approved @ 64d6d09

beanstalk: approved @ 6f91fae

beanstalk: approved @ 70a78f9

beanstalk: approved @ 8015c9a

beanstalk: approved @ 8d361dc

beanstalk: approved @ 9d8356e

beanstalk: approved @ abf2227

beanstalk: approved @ d82f202

beanstalk: approved @ e5f1e40

beanstalk: approved @ ee8ab5f

ci: approved

good first issue

gpu/amd

gpu/igpu

gpu/intel

gpu/nvidia

help wanted

kind

bug

kind

chore

kind

docs

kind

feature

kind

performance

kind

question

needs measurements

platform/linux

platform/macos

platform/steam-deck

platform/windows

preview

priority

critical

priority

high

priority

low

regression

risk

high

risk

low

risk

medium

status

blocked

status

confirmed

status

duplicate

status

invalid

status

needs-info

status

wontfix

testing wanted

ci: approved

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference

MagicBeanDev/Longshot!908

No description provided.