Repository navigation
fix(author): the 2026-11-09 skill eval's and code review's findings - #163
Merged
Merged
Conversation
The skill: build in a working folder and copy the package to the asked name, never delete a file to free one; name where the verifier's report lands and that one run is enough; play the preview only with a browser tool the agent already has; the hand-over as a list; the reason not to read a library's semantics. The package: own keys only where a field or a file type is looked up (toString, x.constructor); a multiple of a fractional step within a rounding error; a download whose address has a broken escape keeps its name; sync-skill refuses broken markers instead of appending a second section; a source's type with a version says the version is the pack's; the command line through parseArgs (--libraries=dir, -h, -v); the page's build writes the media before the libraries carried for an H5P site's upload check, as Node's does, and returns install; the media cache by kind and source. Closes #162
Contributor
There was a problem hiding this comment.
All reported issues were addressed across 15 files
Reply with feedback, questions, or to request a fix.
View guided diff | Turn on auto-fix | Re-trigger cubic
A fractional step's bound is four Number.EPSILON of the quotient, the error of three roundings, not 1e-9 of it, which let 50000000.05 pass in steps of 0.1. The skill copies the package handed over with cp -n and asks, or takes a new name and says so, where the asked one is taken; reads the report's reasons, where a failed run may be the only one to say why; and hands over the report, screenshot and revision of the run that passed, or none, with the package called unverified, where the verifier could not run.
Contributor
There was a problem hiding this comment.
1 issue found across 3 files (changes from recent commits).
Reply with feedback, questions, or to request a fix.
View guided diff | Turn on auto-fix | Re-trigger cubic
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. When an issue isn't valid or won't be fixed in this PR, reply in its thread with the reason and then resolve the thread. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="skills/h5p-author/SKILL.md">
<violation number="1" location="skills/h5p-author/SKILL.md:124">
P2: This leaves a failed check's handoff undefined: the package is still delivered, but the report clause covers only a passing run and the no-report exception covers only checks that could not run. Specify that a failed check must be disclosed with its report and reasons, and label the package as failed verification.</violation>
</file>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #162: every finding of the 2026-11-09 skill eval and code review, in one PR as asked.
The skill (
skills/h5p-author/SKILL.md)rm -rf'd the user's file to reuse its name.<name>.verify/,--out), what to read in it, and that one run is enough:--untrustedfinds nothing more, the design's call of 2026-11-01.--no-openonly with a browser tool the agent already has, never a script of its own. One run spent four of its six minutes writing one.The code (
packages/author), each with a test that fails on maininfollowed the prototype chain: a field namedtoStringorconstructorwent unreported, and a file namedx.constructorpassed as a known type.Object.hasOwnnow (generator.mjs,media.mjs).%refuses 0.3 in steps of 0.1. No library in the pack has such a step, and the content check checks none, so the departure is recorded ingenerator.mjsanddesign/author.md.%zz) keeps its name as written, instead of ending the build with a bareURIError.sync-skillrefuses a type file whose markers are broken (one only, either twice, the end first) instead of appending a second section. The logic moved tolib/schema.mjs(withSection) so the test can import it without running the script.typewith a version,"H5P.Blanks 1.14", is refused with the reason: the version is the pack's newest.loadLibrariestakes one because saved content names one. The pack holds no two majors of any content type, so pinning one would pin nothing.node:utilparseArgs, as h5p-verify and h5p-embed do:--libraries=dir,-hand-vwork.The five the review raised without checking
writePackagenow takes the media and writes them between the content and those libraries, in both builds, and the page's result hasinstallas Node's does.Usilently. The generator already reports it, andMediaStoreis not exported.schemaof an unknown type opening every part. It takes 0.39 s against 0.11 s for a known type.After the AI review (ddd94df, all four of its findings)
Number.EPSILONof the quotient, the error of three roundings. The first cut's 1e-9 let 50000000.05 pass in steps of 0.1. No on-step decimal among 800,000 sampled up to 1e9 is refused, and no half-step one passes.cp -n. Where the asked name is taken, it asks, or takes a new name and says so.reasons, where a failed run may be the only field that says why.Checks
pnpm typecheckandpnpm testinpackages/author, the Chromium page test included.apps/skills' tests.sync-skill --check: 0 files out of date.The page build's result type gains a field and the CLI accepts more forms, so the release is an h5p-author minor. Not bumped here.