Install any skill in seconds. Free to start, no credit card required.
Get Started Free →skilld-dev/generate-package-skill
Generate or update an Agent Skill for an npm or local package using its public API and current documentation.
Passed 17 of 19 test cases with the skill, and 8 of 19 without it.
and 9 more in the full report
9 fixed8 passed either way2 still failing0 broke3 errored
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/21/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When running untrusted code samples and server fixtures during automated verification, what command wrapper and duration limit should be used to enforce execution timeouts?
| Checked | Without skill | With skill |
|---|---|---|
| The command execution is wrapped in timeout 120. | Missed | Passed |
The instructions your model reads when the skill loads.
Write a short Skill that stops an Agent from misusing one package version. The reader knows the language, the framework, and the domain. Write only what it would get wrong.
Take a package name, directory, or prepared source. Ask for the destination only when it is missing.
In a monorepo, put the Skill in the published package directory.
Write one Skill per installed package, unless a second package has distinct users.
Skip an internal package, whose users are the repository's own packages, such as a shared engine or types package. Report why, and write nothing.
assets/ holds the Harness request. A direct run ignores it.
package.json version and the npm dist-tag that carries it.
If npm latest is an older major, test the branch's version. If the branch is ahead of its last release, read source at that release tag and report the unreleased changes.To update an existing Skill after a release, use update-package-skill. It tests only what the release changed.
Observed behaviour beats documentation.
prepack can need them.
Pack with the repository's package manager: npm pack leaves pnpm catalog: versions.
Give the fixture its own pnpm-workspace.yaml, so a parent workspace cannot satisfy its imports.
Install only the package, documented peers, and check tools such as typescript. A resolution error is a finding.
Install each peer at npm latest. If latest is outside the peer range, test both versions.modules/; Nuxt registers every module there.
One fixture page can exercise many examples.test cases passed, vs 8 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.