riccardomerenda/PromptScore

Lint your prompts before they reach a model. Static analysis for LLM prompts.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit May 2, 2026
License
MIT

Pinned Snippet

workflow.ymlSHA-pinned
uses: riccardomerenda/promptscore@abff136e0d6b5c7a7bb921169b82c144ce8e1f72 # v0.4.8

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
inputsFiles, directories, or globs to analyze. Whitespace-separated. Defaults to "prompts/".noprompts/
modelProfile name. Built-in: _base, claude, gpt. Custom profiles supported via project config.no_base
formatReport format: text, markdown, or json. Markdown is also appended to the GitHub Actions job summary.notext
fail-onSeverity threshold that fails the action: error, warning, info, or none.noerror
configPath to a PromptScore config file. Defaults to project discovery.no""
rulesComma-separated rule IDs to include. Empty means all rules from the active profile.no""
include-llmRun LLM-backed rules. Requires the relevant API key in the runner environment.nofalse
cli-versionVersion of @promptscore/cli to install (npm semver tag or version). Defaults to latest.nolatest
node-versionNode.js version to use on the runner.no20

no outputs