skillcraft
v0.1.6Skill quality & improvement — measuring whether a guide skill actually helps, diagnosing where it falls short, and improving it without regressions. Home for skill-improvement methods and metrics.
By Roman Maslennikov1 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Oct 6, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install skillcraft for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install skillcraft@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/aquivalabs/BladeForgeClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/skillcraft/.
Plugin files
├── .claude-plugin/plugin.json└── skills/skillaxe/SKILL.md
Included Skills1
Use to diagnose, audit, or improve a GUIDE skill — one that tells an agent how to produce something (an authoring guide, a review lens, a house-convention skill). Fires when you ask: does this skill actually help or is it decorative; diagnose where a guide skill falls short and propose fixes; audit a skill and measure its real effect on the output; the guide skill doesn't seem to change what the agent produces, prove it either way; improve a guide skill without dropping what already worked; run a with-and-without comparison on a skill. It holds the comparison protocol itself — invoke it whenever someone is about to run such a diagnosis by hand, and whenever a prior edit made a skill worse and you need regression protection. Do NOT use to measure whether a skill's DESCRIPTION triggers (meta:skill-eval scores activation; this scores the produced result); to scaffold a brand-new skill (meta:new-skill); or to refresh a skill's metadata.yaml (meta:update-skill).
Plugin manifests1
{
"name": "skillcraft",
"description": "Skill quality & improvement — measuring whether a guide skill actually helps, diagnosing where it falls short, and improving it without regressions. Home for skill-improvement methods and metrics.",
"version": "0.1.6",
"keywords": [
"skill-quality",
"skill-improvement",
"skillaxe",
"metrics",
"evaluation"
],
"author": {
"name": "Roman Maslennikov",
"email": "[email protected]"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[skillcraft on Agent Plugins Marketplace](https://pluginsmp.com/plugins/skillcraft)