orchestrator
nubjs/nubDrive a multi-part effort to completion by dispatching, steering and verifying sub-agents — one cohesive epic, a batch of decided changes, or a coverage…
Scores out of 100 · grade A
2026-08-13Works
40% of the score100/100
- Loads cleanly: valid frontmatter, required fields present, no dangling references.
Maintained
25% of the score100/100
- no commits in the last 12 weeks
Adopted
20% of the score49/100
- 3,976 stars on the source repo.
Documented
15% of the score55/100
- No usage example or code block.
- 2,607-word body.
Install
npx skills add nubjs/nub/orchestratorWhat it says it does
Drive a multi-part effort to completion by dispatching, steering and verifying sub-agents — one cohesive epic, a batch of decided changes, or a coverage campaign over a population. Invoke (via the Skill tool) whenever you hold a goal set larger than one context and will delegate pieces of it: "drive this epic", "work through these fixes", "batch these changes", "measure all of X", or being handed a large multi-unit implementation. Carries the three dispatch PATTERNS (phased batch, worktree fan-out, relay) and the rule that picks between them — EDITS ARE CHEAP AND PARALLELISE, BUILDS ARE EXPENSIVE AND DO NOT. Supersedes the separate `batch-orchestrator` and `dynamic-orchestrator` skills. Pairs with `remote-build` (uncontended builds), `ad-hoc-test` (verification), `cpu-reduction` (clearing residue), `rust-build-hygiene` (not creating it).
Also in nubjs/nub
| Artifact | Score | What the check found | Type | Reach | Last commit |
|---|---|---|---|---|---|
| visual-reviewnubjs/nub | clean | Skill | 4.0k stars | today | |
| ci-triagenubjs/nub | clean | Skill | 4.0k stars | today | |
| ci-watchnubjs/nub | clean | Skill | 4.0k stars | today | |
| gcloud-vmnubjs/nub | clean | Skill | 4.0k stars | today | |
| rust-buildnubjs/nub | clean | Skill | 4.0k stars | today | |
| type-declarationsnubjs/nub | clean | Skill | 4.0k stars | today |
Other testing & qa skills
Browse all| Artifact | Score | What the check found | Category | Reach | Last commit |
|---|---|---|---|---|---|
| skill-creatoranthropics/skills | No license | Testing & QA | 358,827 installs | today | |
| systematic-debuggingobra/superpowers | clean | Testing & QA | 232,863 installs | 2 days ago | |
| webapp-testinganthropics/skills | No license | Testing & QA | 138,299 installs | today | |
| test-driven-developmentobra/superpowers | clean | Testing & QA | 204,536 installs | 2 days ago | |
| migrate-to-shoehornmattpocock/skills | clean | Testing & QA | 238,622 installs | today | |
| playwright-component-testingmicrosoft/playwright | clean | Testing & QA | 95k stars | today |
Put this measurement in your README
A badge carrying how many listings this index holds from the repository and how many pass every static structural check. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://skillworks.kynth.studio/?q=nubjs%2Fnub)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.
