Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-ai/vellum-feature-flag-rollout
Guide Vellum Assistant feature flag changes and rollout hygiene.
Passed 24 of 24 test cases with the skill, and 8 of 24 without it.
and 22 more in the full report
16 fixed8 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the initial step in the 6-step review workflow when assessing a feature flag change in Vellum?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies step 1 as confirming whether the change adds, renames, removes, or consumes a flag. | Missed | Passed |
The instructions your model reads when the skill loads.
Assistant feature flags use simple kebab-case keys and must be declared in:
meta/feature-flags/feature-flag-registry.json
New flags require:
scope: "assistant"vellum-assistant-platform PR to provision the flag in TerraformThere is no release-note surfacing mechanism — the workspace-bulletin feature was removed and the historical release-note migrations are frozen. Do not add new release-note migrations for any feature (flagged or GA). If a release needs user-facing notes, design an explicit on-demand surfacing mechanism first.
Under permission-controls-v2, do not add new deterministic approval modes for assistant-owned actions beyond the conversation-scoped host computer access gate. Avoid global toggles, persistent trust-rule UI, wildcard scopes, and time-window approvals.
Call out:
test cases passed, vs 8 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.