Stats
Actions
Tags
From agents-kit
Use when asked to proofread, check, review, or polish a message, email, or piece of writing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agents-kit:proofread [message or file path][message or file path]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review the provided message and suggest improvements. **Strictly preserve the author's original tone, voice, and style** — don't make casual writing formal or direct writing diplomatic.
Review the provided message and suggest improvements. Strictly preserve the author's original tone, voice, and style — don't make casual writing formal or direct writing diplomatic.
Grammar & Mechanics — Typos, spelling errors, punctuation, grammatical mistakes.
Structure & Flow — Logical progression, readability, unclear or ambiguous sentences. Flag paragraphs that bury the point or repeat themselves.
Consistency — Contradictions within the text, inconsistent terminology, claims that conflict with each other.
Facts — Verify claims that are checkable (names, dates, numbers, technical terms). Use web search when uncertain. If a claim can't be verified, say so rather than guessing.
Errors (if any) — Issues that should be fixed:
Improvements (if any) — Optional suggestions:
One-line overall assessment. Omit empty sections.
Updated version — Full message with all fixes and improvements applied. Preserve original formatting and structure. If the message is clean with no changes, skip this section.
npx claudepluginhub drimchansky/agents-kit --plugin agents-kitProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.