andrgavrilenko
UserEnglish text quality for AI agents: AI-slop cleanup, clarity, usage. 74 rules, each with a test and a stated exception. Scores text 0-10.
Categories
Indexed Skills (3)
en-check
Full English text quality check against the whole corpus. Triggers: proofread, edit this, review this text, tighten this, does this read like AI, en-check. Use when the user asks to proofread or edit English text, or when a project gate names en-text. Returns findings, each with the rule behind it and a proposed replacement; never edits a file.
en-score
Score English text 0.0-10.0 across five dimensions: sentence clarity, flow and cohesion, human voice, correctness, precision for the reader. Triggers: score this, rate this text, how good is this writing, how much does this read like AI, en-score. Use when the user wants a number rather than a list of findings. Never edits a file.
en-text
English text quality. Triggers: edit this, proofread, tighten this up, make this sound human, does this read like AI, en-text. Catches AI slop, buried subjects, nominalizations, and hedging. Applies on request; light cleanup on any English draft the agent writes.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.