Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish
.claude/skills/mikeyobrien-release-bump/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -21% | 0% |
Bump version and trigger release for ralph-orchestrator. All versions live in workspace Cargo.toml - individual crates inherit via version.workspace = true.
Confirm the new version with the user. Once the bump commit is pushed, track progress of the release.
| Step | Command/Action | |------|----------------| | 1. Bump version | Edit Cargo.toml: replace all version = "X.Y.Z" (7 occurrences) | | 2. Build | cargo build (updates Cargo.lock) | | 3. Test | cargo test | | 4. Commit | git add Cargo.toml Cargo.lock && git commit -m "chore: bump to vX.Y.Z" | | 5. Push | git push origin main | | 6. Tag | git tag vX.Y.Z && git push origin vX.Y.Z |
toml# Line ~17 - workspace version [workspace.package] version = "X.Y.Z" # Lines ~113-118 - internal crate dependencies ralph-proto = { version = "X.Y.Z", path = "crates/ralph-proto" } ralph-core = { version = "X.Y.Z", path = "crates/ralph-core" } ralph-adapters = { version = "X.Y.Z", path = "crates/ralph-adapters" } ralph-tui = { version = "X.Y.Z", path = "crates/ralph-tui" } ralph-cli = { version = "X.Y.Z", path = "crates/ralph-cli" } ralph-bench = { version = "X.Y.Z", path = "crates/ralph-bench" }
Tip: Use Edit tool with replace_all: true on version = "OLD" → version = "NEW" to update all 7 at once.
Once you push the tag, .github/workflows/release.yml triggers and:
@ralph-orchestrator/ralph| Mistake | Fix | |---------|-----| | Only updating workspace.package.version | Must update all 7 occurrences including internal deps | | Forgetting to run tests | Always cargo test before commit | | Creating release manually with gh release create | Just push the tag - CI creates the release with artifacts | | Pushing tag before main | Push main first, then push the tag |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,156 | 3,972 | -4% | 1 | 1 | 0% | 213 | 952 | +347% | 0 | 0 | — |
case-02 | fail→fail | 4,568 | 4,375 | -4% | 1 | 1 | 0% | 275 | 955 | +247% | 0 | 0 | — |
case-03 | fail→fail | 2,802 | 3,547 | +27% | 1 | 1 | 0% | 307 | 1,017 | +231% | 0 | 0 | — |
case-04 | fail→pass | 9,282 | 5,314 | -43% | 1 | 1 | 0% | 1,984 | 2,002 | +1% | 0 | 0 | — |
case-05 | fail→pass | 7,104 | 2,488 | -65% | 1 | 1 | 0% | 1,402 | 1,147 | -18% | 0 | 0 | — |
case-06 | fail→pass | 4,750 | 2,184 | -54% | 1 | 1 | 0% | 853 | 1,076 | +26% | 0 | 0 | — |
case-07 | fail→pass | 7,336 | 2,845 | -61% | 1 | 1 | 0% | 1,454 | 1,237 | -15% | 0 | 0 | — |
case-08 | pass→pass | 9,942 | 2,747 | -72% | 1 | 1 | 0% | 1,765 | 1,164 | -34% | 0 | 0 | — |
case-09 | fail→pass | 7,807 | 2,837 | -64% | 1 | 1 | 0% | 1,498 | 1,189 | -21% | 0 | 0 | — |
case-10 | fail→pass | 10,418 | 2,944 | -72% | 1 | 1 | 0% | 1,674 | 1,111 | -34% | 0 | 0 | — |
case-11 | pass→pass | 10,808 | 3,202 | -70% | 1 | 1 | 0% | 2,200 | 1,393 | -37% | 0 | 0 | — |
case-12 | pass→pass | 11,396 | 3,789 | -67% | 1 | 1 | 0% | 2,076 | 1,460 | -30% | 0 | 0 | — |
case-13 | pass→pass | 6,759 | 1,298 | -81% | 1 | 1 | 0% | 1,336 | 888 | -34% | 0 | 0 | — |
case-14 | pass→pass | 11,405 | 4,021 | -65% | 1 | 1 | 0% | 2,232 | 1,408 | -37% | 0 | 0 | — |
case-15 | fail→pass | 4,766 | 3,792 | -20% | 1 | 1 | 0% | 887 | 1,287 | +45% | 0 | 0 | — |
case-16 | fail→pass | 7,701 | 2,607 | -66% | 1 | 1 | 0% | 1,486 | 991 | -33% | 0 | 0 | — |
case-17 | pass→pass | 5,502 | 1,530 | -72% | 1 | 1 | 0% | 1,016 | 935 | -8% | 0 | 0 | — |
case-18 | pass→pass | 5,791 | 1,167 | -80% | 1 | 1 | 0% | 1,081 | 904 | -16% | 0 | 0 | — |
case-19 | pass→pass | 4,017 | 4,114 | +2% | 1 | 1 | 0% | 646 | 1,420 | +120% | 0 | 0 | — |
case-20 | pass→pass | 4,457 | 2,641 | -41% | 1 | 1 | 0% | 887 | 1,128 | +27% | 0 | 0 | — |
case-21 | pass→pass | 5,278 | 3,703 | -30% | 1 | 1 | 0% | 1,110 | 1,343 | +21% | 0 | 0 | — |
case-22 | pass→pass | 8,673 | 3,819 | -56% | 1 | 1 | 0% | 1,785 | 1,460 | -18% | 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 21 counted toward the lift figure. The other 1 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 +36 percentage points is the difference between those two pass rates over the 21 comparable cases.
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.