Automated Assessment
Systematic project assessment against checkpoint-enabled skills with scripted verification + LLM review. Supports any project type via skill-level preconditions. CLI: /assess [--autofix] [--review] [--autoimprove]. Includes /assess:add-checkpoints to onboard new skills. By Netresearch.
Install
Choose a supported route below. Package contents, agent registration and runtime dependencies can differ between installers.
-
Claude Code via this marketplace /plugin install automated-assessment@netresearch-claude-code-marketplaceFirst add the marketplace once in Claude Code:
/plugin marketplace add netresearch/claude-code-marketplace. Then install the selected plugin. For setup and installation scopes, seeClaude Code plugin setupA plugin can include several skills and additional components. -
npx interactive skill selection npx skills add https://github.com/netresearch/automated-assessment-skillRequires Node.js 22.20+. Run from the target project, then choose the source skills and agents in the installer. The source ships automated-assessment and the separate add-checkpoints companion skill. Select the required instructions; see
assessment installation guideThe assessment evaluates only applicable published checkpoints and does not guarantee factual correctness. -
composer require PHP project, as a package composer require netresearch/automated-assessment-skillAllow the Composer skill installer to activate and approve skill registration when prompted. Requires
netresearch/composer-agent-skill-pluginDiscovers trusted skill packages and registers their instructions in AGENTS.md. Runtime tools may need separate setup. -
composer skills:add PHP project, direct source composer skills:add netresearch/automated-assessment-skillInstall and activate netresearch/composer-agent-skill-plugin first; approve the selected source's skill registration. Provided by
netresearch/composer-agent-skill-pluginPins source repositories without a Packagist package and records them incomposer.skills.lock. Runtime dependencies remain separate.
What you can do with it
- Systematic project assessment against checkpoint-enabled skills with scripted verification + LLM review
- Supports any project type via skill-level preconditions
- CLI: /assess [--autofix] [--review] [--autoimprove]
- Includes /assess:add-checkpoints to onboard new skills
What you get back
- Structured checkpoint results and a summary of detected gaps, limited to the checkpoints actually assessed.
What it expects in your project
Check the source README for current examples, requirements and limitations. Open full README