Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Bumps versions, updates changelogs, and coordinates version changes across files for releases. Use when preparing a release or bumping the project version.
.claude/skills/athola-version-updates/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 18% | 0% |
Use this skill when preparing a release or bumping the project version. Run Skill(sanctum:git-workspace-review) first to capture current changes.
version-update:context-collectedversion-update:target-filesversion-update:version-setversion-update:docs-updatedversion-update:verificationcontext-collected)Skill(sanctum:git-workspace-review) has already captured the repository status.target-files)Cargo.toml, package.json, pyproject.toml*/pyproject.toml, */Cargo.toml, */package.jsonplugins/memory-palace/pyproject.toml must be included.venv, node_modules, target/) using grep -vfind plugins -name "pyproject.toml" -o -name "Cargo.toml" | grep -v ".venv"version-set)plugins/sanctum/scripts/update_versions.py <version> to update all version filesplugins/memory-palace/pyproject.toml)--dry-run flag first to preview changesMAJOR.MINOR.PATCH or the specified formatdocs-updated)These files contain version numbers and MUST be checked during version bumps:
| File | Content | |------|---------| | docs/api-overview.md | Plugin inventory table with all plugin versions | | CHANGELOG.md | Version history and release notes | | book/src/reference/capabilities-reference.md | May reference version-specific features | | Plugin READMEs | May mention plugin versions |
bash# Find all docs mentioning the OLD version grep -r "1\.2\.6" docs/ book/ --include="*.md" | grep -v node_modules # Common patterns to search: # - "v1.2.6", "1.2.6", "(v1.2.6)" # - Version tables in markdown # - "Added in X.Y.Z" annotations
CHANGELOG.md - add new version sectiondocs/api-overview.md - update version table and plugin detailsverification)cargo test, npm test).git status -sb and git diff excerpts to confirm the version bumps.version-update:context-collectedthrough version-update:verification) are created before any file is modified and marked complete in order
update_versions.py --dry-run <version> run first and itsoutput reviewed before any version file is written
(pyproject.toml, Cargo.toml, package.json, plugin.json) with no target file missing the update
CHANGELOG.md updated with a new version section dated todaygit diff output confirms version changes in all identifiedtarget files; a summary of files changed and new version number is reported to the user
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | pass→pass | 8,474 | 1,652 | -81% | 1 | 1 | 0% | 1,337 | 1,319 | -1% | 0 | 0 | — |
case-15 | fail→pass | 10,877 | 2,224 | -80% | 1 | 1 | 0% | 1,742 | 1,429 | -18% | 0 | 0 | — |
case-01 | fail→fail | 2,660 | 8,777 | +230% | 1 | 1 | 0% | 325 | 1,676 | +416% | 0 | 0 | — |
case-02 | fail→fail | 3,573 | 8,382 | +135% | 1 | 1 | 0% | 323 | 1,355 | +320% | 0 | 0 | — |
case-03 | fail→fail | 4,389 | 6,197 | +41% | 1 | 1 | 0% | 357 | 1,424 | +299% | 0 | 0 | — |
case-04 | fail→pass | 10,353 | 10,075 | -3% | 1 | 1 | 0% | 1,798 | 2,787 | +55% | 0 | 0 | — |
case-05 | fail→pass | 11,275 | 7,804 | -31% | 1 | 1 | 0% | 1,911 | 2,345 | +23% | 0 | 0 | — |
case-06 | fail→fail | 7,340 | 3,670 | -50% | 1 | 1 | 0% | 1,269 | 1,531 | +21% | 0 | 0 | — |
case-07 | fail→pass | 7,572 | 2,351 | -69% | 1 | 1 | 0% | 1,141 | 1,412 | +24% | 0 | 0 | — |
case-08 | fail→pass | 7,016 | 1,939 | -72% | 1 | 1 | 0% | 1,162 | 1,369 | +18% | 0 | 0 | — |
case-09 | fail→pass | 11,037 | 2,786 | -75% | 1 | 1 | 0% | 1,790 | 1,568 | -12% | 0 | 0 | — |
case-10 | fail→pass | 12,642 | 7,219 | -43% | 1 | 1 | 0% | 2,391 | 2,403 | +1% | 0 | 0 | — |
case-11 | fail→pass | 7,581 | 1,586 | -79% | 1 | 1 | 0% | 1,203 | 1,295 | +8% | 0 | 0 | — |
case-12 | fail→pass | 20,155 | 2,448 | -88% | 1 | 1 | 0% | 2,187 | 1,452 | -34% | 0 | 0 | — |
case-13 | pass→pass | 11,882 | 5,480 | -54% | 1 | 1 | 0% | 2,011 | 2,005 | -0% | 0 | 0 | — |
case-16 | fail→pass | 10,385 | 3,418 | -67% | 1 | 1 | 0% | 1,637 | 1,673 | +2% | 0 | 0 | — |
case-17 | pass→pass | 4,639 | 1,614 | -65% | 1 | 1 | 0% | 635 | 1,294 | +104% | 0 | 0 | — |
case-18 | pass→pass | 6,531 | 1,693 | -74% | 1 | 1 | 0% | 1,084 | 1,288 | +19% | 0 | 0 | — |
case-19 | fail→fail | 13,727 | 7,193 | -48% | 1 | 1 | 0% | 1,625 | 1,546 | -5% | 0 | 0 | — |
case-20 | pass→fail | 21,262 | 3,865 | -82% | 1 | 1 | 0% | 2,085 | 1,756 | -16% | 0 | 0 | — |
case-21 | pass→pass | 9,389 | 2,187 | -77% | 1 | 1 | 0% | 1,608 | 1,451 | -10% | 0 | 0 | — |
case-22 | pass→pass | 11,617 | 4,927 | -58% | 1 | 1 | 0% | 1,897 | 1,811 | -5% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +41 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.