j-rig
v0.1.0Skill Refiner — the eval-guided SKILL.md improvement loop, delivered as a thin wrapper over the published @intentsolutions/refiner CLI with a 3-layer cost-tiered hook architecture (sinker/line/hook)
by Jeremy LongshoreApache-2.02.6kupdated 2 hours ago
Source
git clone https://github.com/jeremylongshore/claude-code-plugins-plus-skillsClone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is plugins/productivity/j-rig/ inside the repository.
Layout
├── .claude-plugin/plugin.json└── skills/j-rig/SKILL.md
Skills1
Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".
Manifests1
{
"name": "j-rig",
"version": "0.1.0",
"description": "Skill Refiner — the eval-guided SKILL.md improvement loop, delivered as a thin wrapper over the published @intentsolutions/refiner CLI with a 3-layer cost-tiered hook architecture (sinker/line/hook)",
"author": {
"name": "Jeremy Longshore",
"email": "jeremy@intentsolutions.io"
},
"repository": "https://github.com/jeremylongshore/claude-code-plugins-plus-skills",
"homepage": "https://tonsofskills.com/plugins/j-rig",
"license": "Apache-2.0",
"keywords": [
"skill-refiner",
"eval-guided",
"skill-md",
"meta-tooling",
"hooks"
],
"hooks": "./hooks/hooks.json"
}