WIP: docs(agents): a review checklist, and the review skill moves to Tooling #891

Draft
zeldaootr wants to merge 3 commits from zeldaootr/Longshot:skill-review into main
Contributor

Type: docs · Risk: low · Tested on: Linux, game-free checks · Needs: none

Why

Hundreds of pull requests are open and reviews are the bottleneck: #394 counts most merges without an approving
review, and reviews posted by an agent nine in two minutes. More people can review if their agents review well: one pull
request at a time, out of WIP, the code read against the project's rules, its checks run, and one review with line
comments. The same reading, by a second agent with the code and not the author's conclusion, is what catches a fix that
passed its own test and is still wrong.

What changed

The review skill this pull request first proposed is shared by every repository, so HumanBean moved its procedure
(picking, safety, the review flow, the cold review) to Tooling as /magicbean:review
(MagicBeanDev/Tooling#8) and pushed that change here. What is Longshot's own stays:

  • docs/review-checklist.md (new, 37 lines): what a reviewer of a Longshot pull request reads (CONTRIBUTING.md's
    rules, the replay's rules in design.md, the translator-files cost, a switch unset behaving as main, threads and
    lifetimes, hardware tiers, the test and the evidence) and runs (the description check from main, the tests at the
    head and the merge base with both compilers, the changed files built).
  • AGENTS.md: one line in the task list, pointing to Tooling's review skill and to the checklist.
  • .claude/skills/review/SKILL.md is not in this pull request any more.

Measurements

Nothing to measure: a Markdown file for agents and a few lines of docs, no code; the game doesn't run it.

Flags and settings

None

Testing

Tested: Linux. On this branch, rebased on main @ e4d035e9 (head d4c4c64a): python -I -B tests/run_all.py --exact tests/test_switches_removed.py tests/test_check_pr_description.py tests/test_tested_configurations.py tests/test_utf8_paths.py tests/test_tools_lock.py tests/test_doc_anchors.py passes (6 of 6): the checks that read AGENTS.md, docs/ and the
Markdown files; run_all.py --changed forge/main passes (2 of 2: test_switches_removed and the byte-compile). The relative links and anchors in docs/review-checklist.md and the changed AGENTS.md line resolve.

Not tested: an agent following the checklist on a real review; the link to Tooling's review skill resolves only
once MagicBeanDev/Tooling#8 has merged.

Must be tested:

  • None

Risks

What could break: Nothing in the game or the scripts. Until Tooling's pull request 8 merges, the AGENTS.md line links to a skill that is not on Tooling's main yet.

Turning it off: revert the commit

Compatibility: Nothing changes

Reviewer notes

This should merge after MagicBeanDev/Tooling#8, which it links. On 2026-11-16 that pull request is still open and not mergeable (it sits on Tooling's first commit and needs a rebase); its skill's path, skills/review/SKILL.md, is unchanged, so the links here stand. Tooling has since merged /magicbean:batch-review (MagicBeanDev/Tooling#9), a ranked pass of code-only reviews over the open pull requests, which runs nothing and reads the repository's AGENTS.md and CONTRIBUTING.md, not this checklist. The two overlap in what a review reads; this checklist's Run section is for the one-pull-request review only. Whether batch-review should read docs/review-checklist.md too is a question for Tooling, not this pull request. The split is
HumanBean's (commits 2 and 3 here are theirs, rebased onto main with no change); the open questions the first
version asked (whether agents should approve at all, which pull request to pick first, and reviews of WIP pull
requests) belong to that Tooling pull request now.

Issues

See #394

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).
  • Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what
    can't be run by hand is in Testing's Not testable by hand, with why.
  • Measurements has a verdict, or one line saying why there is nothing to measure.
  • Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and
    in Risks.
  • Testing names what was tested, what wasn't, and what must still be tested, where and how.
  • Rebased on current main: on e4d035e9 (#1028, 2026-11-16), head d4c4c64a, without a conflict and with the diff unchanged; commits old → new: 771c6109 → b4b72bc1, e34f4f16 → b09a0875, bf442e68 → d4c4c64a (HumanBean's two keep their author).
  • python -I -B tests/run_all.py passes (any failure that also fails on main is named). On head bf442e68 (the same diff, on main ceccd963; not run again after the rebase onto e4d035e9, which changed no file this PR touches), Linux: 532 passed, 20 failed, 77 skipped. 18 of the 20 fail on main ceccd963 too (appimage_player_build, bake_portability, crash_dialog, crt_options, env_on, lift_cache, lift_cleanup_error, linux_preflight, linux_update, make_game_cache, missing_nup, mods_size_table, options_budget_once, pipeline_tour, readback_late, vk_occlusion_queries, vk_pgo, walk_key); the other two (appimage_package_retry, pipeline_cache_save) are timing checks that pass when run alone on this head.
  • 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.
**Type:** docs · **Risk:** low · **Tested on:** Linux, game-free checks · **Needs:** none ## Why Hundreds of pull requests are open and reviews are the bottleneck: #394 counts most merges without an approving review, and reviews posted by an agent nine in two minutes. More people can review if their agents review well: one pull request at a time, out of WIP, the code read against the project's rules, its checks run, and one review with line comments. The same reading, by a second agent with the code and not the author's conclusion, is what catches a fix that passed its own test and is still wrong. ## What changed The review skill this pull request first proposed is shared by every repository, so HumanBean moved its procedure (picking, safety, the review flow, the cold review) to Tooling as `/magicbean:review` (https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8) and pushed that change here. What is Longshot's own stays: - `docs/review-checklist.md` (new, 37 lines): what a reviewer of a Longshot pull request reads (CONTRIBUTING.md's rules, the replay's rules in design.md, the translator-files cost, a switch unset behaving as `main`, threads and lifetimes, hardware tiers, the test and the evidence) and runs (the description check from `main`, the tests at the head and the merge base with both compilers, the changed files built). - `AGENTS.md`: one line in the task list, pointing to Tooling's review skill and to the checklist. - `.claude/skills/review/SKILL.md` is not in this pull request any more. ## Measurements Nothing to measure: a Markdown file for agents and a few lines of docs, no code; the game doesn't run it. ### Flags and settings None ## Testing **Tested:** Linux. On this branch, rebased on `main` @ e4d035e9 (head `d4c4c64a`): `python -I -B tests/run_all.py --exact tests/test_switches_removed.py tests/test_check_pr_description.py tests/test_tested_configurations.py tests/test_utf8_paths.py tests/test_tools_lock.py tests/test_doc_anchors.py` passes (6 of 6): the checks that read `AGENTS.md`, `docs/` and the Markdown files; `run_all.py --changed forge/main` passes (2 of 2: `test_switches_removed` and the byte-compile). The relative links and anchors in `docs/review-checklist.md` and the changed `AGENTS.md` line resolve. **Not tested:** an agent following the checklist on a real review; the link to Tooling's review skill resolves only once https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8 has merged. **Must be tested:** - None ## Risks **What could break:** Nothing in the game or the scripts. Until Tooling's pull request 8 merges, the `AGENTS.md` line links to a skill that is not on Tooling's `main` yet. **Turning it off:** revert the commit **Compatibility:** Nothing changes ## Reviewer notes This should merge after https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8, which it links. On 2026-11-16 that pull request is still open and not mergeable (it sits on Tooling's first commit and needs a rebase); its skill's path, `skills/review/SKILL.md`, is unchanged, so the links here stand. Tooling has since merged `/magicbean:batch-review` (https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/9), a ranked pass of code-only reviews over the open pull requests, which runs nothing and reads the repository's `AGENTS.md` and `CONTRIBUTING.md`, not this checklist. The two overlap in what a review reads; this checklist's *Run* section is for the one-pull-request review only. Whether batch-review should read `docs/review-checklist.md` too is a question for Tooling, not this pull request. The split is HumanBean's (commits 2 and 3 here are theirs, rebased onto `main` with no change); the open questions the first version asked (whether agents should approve at all, which pull request to pick first, and reviews of WIP pull requests) belong to that Tooling pull request now. ## Issues See #394 ## 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] Tested on my own PC where it runs (in the game, for a change the game runs), as Testing's Tested says; what can't be run by hand is in Testing's Not testable by hand, with why. - [x] Measurements has a verdict, or one line saying why there is nothing to measure. - [x] Nothing gets worse that I know of: any cost (speed, latency, memory, a setup that worked before) is measured and in Risks. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`: on e4d035e9 (#1028, 2026-11-16), head `d4c4c64a`, without a conflict and with the diff unchanged; commits old → new: `771c6109` → `b4b72bc1`, `e34f4f16` → `b09a0875`, `bf442e68` → `d4c4c64a` (HumanBean's two keep their author). - [x] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). On head bf442e68 (the same diff, on `main` ceccd963; not run again after the rebase onto e4d035e9, which changed no file this PR touches), Linux: 532 passed, 20 failed, 77 skipped. 18 of the 20 fail on `main` ceccd963 too (`appimage_player_build`, `bake_portability`, `crash_dialog`, `crt_options`, `env_on`, `lift_cache`, `lift_cleanup_error`, `linux_preflight`, `linux_update`, `make_game_cache`, `missing_nup`, `mods_size_table`, `options_budget_once`, `pipeline_tour`, `readback_late`, `vk_occlusion_queries`, `vk_pgo`, `walk_key`); the other two (`appimage_package_retry`, `pipeline_cache_save`) are timing checks that pass when run alone on this head. - [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.
chore(agents): /review, a skill for reviewing a pull request, and for a cold review of a branch
Some checks failed
Website / Website on Cloudflare (pull_request_target) Has been skipped
PR description / Description follows the template (pull_request_target) Successful in 4s
CI / Conventional Commit title (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been cancelled
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been cancelled
CI / Workflow lint (actionlint) (pull_request) Has been cancelled
Guide screenshots / Guide images and local UI source review (pull_request) Has been cancelled
Third-party parts / As their notes say (pull_request) Has been cancelled
Third-party parts / The same as upstream (pull_request) Has been cancelled
ee5ce78034
Assisted-by: Claude
chore: the docs/forge.md part moved to MagicBeanDev/Tooling (MagicBeanDev/Tooling#3)
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
PR description / Description follows the template (pull_request_target) Successful in 4s
CI / Conventional Commit title (pull_request) Failing after 3s
CI / Workflow lint (actionlint) (pull_request) Successful in 6s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 5s
Third-party parts / As their notes say (pull_request) Successful in 9s
8162a07321
Longshot's docs/forge.md is gone with #915; its review pointer is in Tooling's docs/forge.md. The skill runs forge.py from ../Tooling.

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

Pushed one commit on top of the head (8162a073), no rewrite. No tests were run here.

The team's shared tooling moved to https://git.magicbean.dev/MagicBeanDev/Tooling (MagicBeanDev/Tooling#1), and #915 deleted forge.py and docs/forge.md from Longshot. So:

  • The docs/forge.md change is dropped from this PR (the file is gone from main). Its line, that a repository may have its own review skill, is ported to Tooling's docs/forge.md in MagicBeanDev/Tooling#3, credited to you.
  • The /review skill stays here, as it is Longshot's way of reviewing. Its forge.py commands now run as ../Tooling/scripts/forge.py, it says to pull Tooling first, and its link to the forge docs points at Tooling's. check_pr_description.py stays scripts/, as that is Longshot's.
  • The AGENTS.md line needed no change, but AGENTS.md on main has changed a lot since this branch started. Please rebase on main; it should apply cleanly, since docs/forge.md is no longer touched.

🤖 Generated with Claude Code

Pushed one commit on top of the head (8162a073), no rewrite. No tests were run here. The team's shared tooling moved to https://git.magicbean.dev/MagicBeanDev/Tooling (https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/1), and https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/915 deleted `forge.py` and `docs/forge.md` from Longshot. So: - The `docs/forge.md` change is dropped from this PR (the file is gone from `main`). Its line, that a repository may have its own review skill, is ported to Tooling's docs/forge.md in https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/3, credited to you. - The `/review` skill stays here, as it is Longshot's way of reviewing. Its `forge.py` commands now run as `../Tooling/scripts/forge.py`, it says to pull Tooling first, and its link to the forge docs points at Tooling's. `check_pr_description.py` stays `scripts/`, as that is Longshot's. - The AGENTS.md line needed no change, but `AGENTS.md` on `main` has changed a lot since this branch started. Please rebase on `main`; it should apply cleanly, since `docs/forge.md` is no longer touched. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
chore(agents): the review skill moves to Tooling; what is Longshot's stays here as docs/review-checklist.md
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Failing after 3s
CI / Workflow lint (actionlint) (pull_request) Successful in 5s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 5s
Third-party parts / As their notes say (pull_request) Successful in 8s
PR description / Description follows the template (pull_request_target) Successful in 3s
3289811625
The shared procedure (picking, safety, the review flow, the cold review) is
MagicBeanDev/Tooling#8 as /magicbean:review.
Longshot's rules, replay rules, hardware tiers and evidence are the checklist.

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

Pushed a new commit (32898116) on top of the head, nothing rewritten. The review skill is shared, so it moved: the generic procedure (picking, safety, the review flow, the cold review) is now MagicBeanDev/Tooling#8 as /magicbean:review, credited to this pull request and its author. What is Longshot's stays here as docs/review-checklist.md (CONTRIBUTING's rules, the replay's rules, translator-files cost, unset == main, threads and lifetimes, hardware tiers, the description check, tests at head and base with both compilers, the evidence), and .claude/skills/review/SKILL.md is deleted. AGENTS.md's one line points to Tooling's skill and the checklist.

Could you rebase onto main? The description and title now describe a skill that isn't in this diff; a title like docs(agents): a review checklist, and the review skill moves to Tooling would fit. No tests run on this PC.

🤖 Generated with Claude Code

Pushed a new commit (32898116) on top of the head, nothing rewritten. The review skill is shared, so it moved: the generic procedure (picking, safety, the review flow, the cold review) is now https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8 as `/magicbean:review`, credited to this pull request and its author. What is Longshot's stays here as `docs/review-checklist.md` (CONTRIBUTING's rules, the replay's rules, translator-files cost, unset == `main`, threads and lifetimes, hardware tiers, the description check, tests at head and base with both compilers, the evidence), and `.claude/skills/review/SKILL.md` is deleted. AGENTS.md's one line points to Tooling's skill and the checklist. Could you rebase onto `main`? The description and title now describe a skill that isn't in this diff; a title like `docs(agents): a review checklist, and the review skill moves to Tooling` would fit. No tests run on this PC. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
Author
Contributor

Rebased onto main ceccd963 (head 1bda3c1b) after the tooling moved to MagicBeanDev/Tooling (#915): the skill's commands and links now point at Tooling's forge.py and its forge guide, the docs/forge.md pointer is dropped (MagicBeanDev/Tooling#3 carries it), and the Read list gains the rule that a change the game runs has run in the game before its PR opens. Still WIP: the full suite has not run on this head.

Rebased onto `main` ceccd963 (head 1bda3c1b) after the tooling moved to MagicBeanDev/Tooling (https://git.magicbean.dev/MagicBeanDev/Longshot/pulls/915): the skill's commands and links now point at Tooling's `forge.py` and its forge guide, the `docs/forge.md` pointer is dropped (https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/3 carries it), and the Read list gains the rule that a change the game runs has run in the game before its PR opens. Still WIP: the full suite has not run on this head.
zeldaootr force-pushed skill-review from 3289811625
Some checks failed
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been skipped
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been skipped
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been skipped
Third-party parts / The same as upstream (pull_request) Has been skipped
CI / Conventional Commit title (pull_request) Failing after 3s
CI / Workflow lint (actionlint) (pull_request) Successful in 5s
Guide screenshots / Guide images and local UI source review (pull_request) Failing after 5s
Third-party parts / As their notes say (pull_request) Successful in 8s
PR description / Description follows the template (pull_request_target) Successful in 3s
to bf442e68e5
Some checks failed
PR description / Description follows the template (pull_request_target) Successful in 4s
CI / Conventional Commit title (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been cancelled
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been cancelled
CI / Workflow lint (actionlint) (pull_request) Has been cancelled
Guide screenshots / Guide images and local UI source review (pull_request) Has been cancelled
Third-party parts / As their notes say (pull_request) Has been cancelled
Third-party parts / The same as upstream (pull_request) Has been cancelled
Website / Website on Cloudflare (pull_request) Has been cancelled
2026-11-15 21:06:55 +00:00
Compare
zeldaootr changed title from WIP: chore(agents): /review, a skill for reviewing a pull request, and for a cold review of a branch to WIP: docs(agents): a review checklist, and the review skill moves to Tooling 2026-11-15 21:07:05 +00:00
Author
Contributor

Correction to my comment above: it described a rebase of the skill that I did not push (the push was refused, rightly, because your two commits were on the branch), so its head 1bda3c1b is not here. Done as you asked instead: your version rebased onto main ceccd963 with nothing changed (head bf442e68; your commits keep your name), the title is now docs(agents): a review checklist, and the review skill moves to Tooling, and the description covers the checklist and the AGENTS.md line only. It links MagicBeanDev/Tooling#8, so it should merge after that one. Still WIP: the full suite has not run on this head; the five checks that read the changed files pass. Thanks for moving the skill and for the credit.

Correction to my comment above: it described a rebase of the skill that I did not push (the push was refused, rightly, because your two commits were on the branch), so its head 1bda3c1b is not here. Done as you asked instead: your version rebased onto `main` ceccd963 with nothing changed (head bf442e68; your commits keep your name), the title is now `docs(agents): a review checklist, and the review skill moves to Tooling`, and the description covers the checklist and the `AGENTS.md` line only. It links https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8, so it should merge after that one. Still WIP: the full suite has not run on this head; the five checks that read the changed files pass. Thanks for moving the skill and for the credit.
Author
Contributor

The full suite has now run on head bf442e68 (Linux): 532 passed, 20 failed, 77 skipped; 18 of the 20 fail on main ceccd963 too, and the other two (appimage_package_retry, pipeline_cache_save, timed waits) pass when run alone. The box is ticked with the names. Left as WIP for its author's own read.

The full suite has now run on head bf442e68 (Linux): 532 passed, 20 failed, 77 skipped; 18 of the 20 fail on `main` ceccd963 too, and the other two (`appimage_package_retry`, `pipeline_cache_save`, timed waits) pass when run alone. The box is ticked with the names. Left as WIP for its author's own read.
zeldaootr force-pushed skill-review from bf442e68e5
Some checks failed
PR description / Description follows the template (pull_request_target) Successful in 4s
CI / Conventional Commit title (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Has been cancelled
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Has been cancelled
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Has been cancelled
CI / Workflow lint (actionlint) (pull_request) Has been cancelled
Guide screenshots / Guide images and local UI source review (pull_request) Has been cancelled
Third-party parts / As their notes say (pull_request) Has been cancelled
Third-party parts / The same as upstream (pull_request) Has been cancelled
Website / Website on Cloudflare (pull_request) Has been cancelled
to d4c4c64a6f
Some checks are pending
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
Website / Website on Cloudflare (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 9s
2026-11-16 05:06:03 +00:00
Compare
Author
Contributor

Rebased onto main e4d035e9 (head d4c4c64a, was bf442e68) with no conflict and no change to the diff; HumanBean's two commits keep their author. MagicBeanDev/Tooling#8 is still open with its skill at skills/review/SKILL.md, so the links stand, and Tooling's new /magicbean:batch-review (MagicBeanDev/Tooling#9) is noted under Reviewer notes as overlapping in what a review reads but running nothing. Re-ran the checks that read AGENTS.md and docs/ (run_all.py --changed forge/main) and the description check; still WIP for its owner's read.

Rebased onto main e4d035e9 (head `d4c4c64a`, was `bf442e68`) with no conflict and no change to the diff; HumanBean's two commits keep their author. https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/8 is still open with its skill at `skills/review/SKILL.md`, so the links stand, and Tooling's new `/magicbean:batch-review` (https://git.magicbean.dev/MagicBeanDev/Tooling/pulls/9) is noted under Reviewer notes as overlapping in what a review reads but running nothing. Re-ran the checks that read `AGENTS.md` and `docs/` (`run_all.py --changed forge/main`) and the description check; still WIP for its owner's read.
Owner

Brought up to the ready-for-review standard (#1454): the checklist's Everyone list has two new boxes, added here from what this PR's description and comments show (please check they match what you know).

  • Tested on my own PC: ticked: Testing's Tested: the author ran the checks that read AGENTS.md and docs on Linux, and the change is docs only.
  • Nothing gets worse that I know of: ticked: Measurements gives one line why there is nothing to measure, and Risks names no cost.
Brought up to the [ready-for-review standard](https://git.magicbean.dev/MagicBeanDev/Longshot/src/branch/main/CONTRIBUTING.md#ready-for-review-out-of-wip) (#1454): the checklist's Everyone list has two new boxes, added here from what this PR's description and comments show (please check they match what you know). - *Tested on my own PC*: ticked: Testing's Tested: the author ran the checks that read AGENTS.md and docs on Linux, and the change is docs only. - *Nothing gets worse that I know of*: ticked: Measurements gives one line why there is nothing to measure, and Risks names no cost.
Some checks are pending
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
Website / Website on Cloudflare (pull_request) Blocked by required conditions
PR description / Description follows the template (pull_request_target) Successful in 9s
This pull request is marked as a work in progress.
Some workflows are waiting to be reviewed.
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 'skill-review:zeldaootr-skill-review'
git switch 'zeldaootr-skill-review'
Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
2 participants
Notifications
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!891
No description provided.