Status: describe the plugins as they are, in the files that ship them - #30
Merged
Conversation
Every place still calling a shipped skill unfinished, or pointing a reader at a tracker for work that has landed. Each plugin-side claim is fixed in the same commit as its repo-side twin — splitting them is how the pairs drifted apart in the first place. - CATALOG.md said /audit:issues had been executed "by hand, never yet as a skill". False since 2026-07-28: run 1 was the first execution as a skill, took 22 minutes over a 230-item tracker and found seven plugin defects. #24 already says the opposite in two *shipped* audit files, so the catalogue was contradicting the plugin it describes. Corrected, and it keeps the honest half — resumability is the method's central claim and remains untested, because the run was never interrupted. - /qe:check-math's description read \\top, \\tag and \\mathbb where it meant \top, \tag and \mathbb. YAML plain scalars do no escape processing, so those were literal double backslashes in the string that natural-language invocation matches against. It stays unquoted deliberately: \t and \m are not valid double-quoted YAML escapes, so "fixing" it by quoting would break the file. - /qe:copilot-review's banner sent readers to issue #3 for "plan and open questions" about a skill that issue never mentions — #3 tracks the style surface. - benchmark/README.md said skill wiring was "tracked in skills#4". It shipped in 0.3.0. 0.3.1 corrected the version number in that same sentence and left the stale clause, which is how half-fixed lines survive review. - docs/using-skills.md's three status cells, matching the above. qe 0.2.1 -> 0.2.2 and benchmark 0.3.1 -> 0.3.2: both patch, both corrections that leave the procedures unchanged. audit is untouched at 0.1.4.
There was a problem hiding this comment.
Pull request overview
Aligns “operational/scaffolding/validated” status text across shipped plugin artifacts and repo-level docs, and bumps plugin versions so installed users actually receive the corrected descriptions.
Changes:
- Corrects shipped status/links for
/qe:copilot-review,/benchmark:review-acceleration, and/audit:issuesacross CATALOG + user docs + plugin READMEs/SKILL.md. - Fixes
/qe:check-mathSKILL frontmatter description to use the intended single backslashes (so natural-language invocation text is accurate). - Bumps
qeto 0.2.2 andbenchmarkto 0.3.2 with matching changelog entries and manifest/version updates (including marketplace.json).
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
qe/skills/copilot-review/SKILL.md |
Updates the operational status banner to credit the shipping PR and correctly scope issue links. |
qe/skills/check-math/SKILL.md |
Fixes frontmatter description backslashes to match the intended LaTeX commands. |
qe/CHANGELOG.md |
Adds 0.2.2 entry documenting the shipped-text corrections. |
qe/.claude-plugin/plugin.json |
Bumps qe plugin version to 0.2.2. |
docs/using-skills.md |
Updates the plugin/skill status table to match current shipped reality and correct links. |
CATALOG.md |
Corrects the audit entry to reflect that /audit:issues has run once as a skill and links the run record. |
benchmark/README.md |
Updates status line to reflect operational wiring since 0.3.0 and points to changelog for release detail. |
benchmark/CHANGELOG.md |
Adds 0.3.2 entry documenting the README status correction. |
benchmark/.claude-plugin/plugin.json |
Bumps benchmark plugin version to 0.3.2. |
.claude-plugin/marketplace.json |
Updates marketplace versions for qe and benchmark to match their bumped plugin versions. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This was referenced Aug 3, 2026
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.
Every place that still calls a shipped skill unfinished, or points a reader at a tracker for work that has already landed. Each plugin-side claim is fixed alongside its repo-side twin — splitting them is how these pairs drifted apart to begin with.
The corrections
CATALOG.mdwas contradicting the plugin it describes. It said/audit:issueshad been executed "by hand, never yet as a skill". That stopped being true on 2026-07-28: run 1 was the first execution as a skill — 22 minutes over a 230-item tracker, seven plugin defects found. #24 already says the opposite in two shipped audit files, so the catalogue and the plugin disagreed on main. The replacement keeps the honest half: resumability is the method's central claim and is still untested, because the run was never interrupted./qe:check-math's description was literally wrong — it read\\top,\\tagand\\mathbbwhere it meant\top,\tagand\mathbb. YAML plain scalars do no escape processing, so a real parser returns the doubled backslashes verbatim; I confirmed that before and after. That matters more than a typo normally would, because thedescriptionis the one string natural-language invocation matches against.It stays unquoted deliberately.
\tand\mare not valid double-quoted YAML escapes, so "fixing" this by adding quotes would raisefound unknown escape characterand break the file — the tempting fix is the broken one./qe:copilot-review's banner sent readers to #3 for "plan and open questions" about a skill that issue never mentions; #3 tracks the style surface. It now credits the PR it shipped in and scopes #3 to the work it covers.benchmark/README.mdsaid skill wiring was "tracked in skills#4". It shipped in 0.3.0. Note how it survived: 0.3.1 corrected the version number in that very sentence and left the stale clause standing — a half-fixed line is harder to spot than an untouched one.docs/using-skills.md— the three status cells, matching all of the above.Versions
qebenchmarkauditThe guard confirms it:
ok benchmark — 0.3.1 → 0.3.2,ok qe — 0.2.1 → 0.2.2.Provenance
These came from a maintenance sweep run after the last four PRs landed. It produced 26 candidate findings; each was then independently checked against the repo, and 12 were refuted — so this PR carries the survivors, not the raw output.
validate.pyandclaude plugin validate --strictpass on all four targets.