claude

blind-skillroll-evaluation

Run independent live SkillRoll trials against small external skill repositories.

11 on GitHubby SkillRollv0.3.0MITupdated 4 days ago
/

Plugin blind-skillroll-evaluation from marketplace skillroll in hagaiw/skillroll. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (5)

  • author-blind-evals

    Author a small preregistered SkillRoll case pack from a target skill and neutral repository context without seeing prior run outcomes.

  • blind-skillroll-evaluation

    Coordinate an end-to-end independent live evaluation of the current SkillRoll main across a small varied set of external skill repositories.

  • prepare-blind-trial

    Prepare an isolated external repository trial using an exact target revision and the current local SkillRoll main without running inference.

  • run-blind-evals

    Execute a frozen SkillRoll case pack with live inference, preserve its evidence, and classify technical, case-authoring, and target-skill outcomes.

  • select-blind-targets

    Select and preregister small external Agent Skills repositories for an independent SkillRoll trial before any run outcomes are inspected.

View source on GitHub

More from hagaiw/skillroll

All 7 plugins →

A small change-review flow built from independent steps.

4 skills

11

SkillRoll's executor, Dungeon Master, and judge prompt contracts.

3 skills

11

Set up SkillRoll and author or audit Agent Skills and Markdown behavior cases.

3 skills

11

Keep a small, sourced fact ledger for one ongoing task.

1 skill

11

Coordinate a small sequence of artifact-producing skills.

1 skill

11

Create a concise Markdown overview from supplied pull-request facts.

1 skill

11

Maintain blind-skillroll-evaluation?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins