MCP App StoreMCP App StoreHumanize is a text-revision skill that enforces a concise set of stylistic rules designed to strip AI-generated patterns from prose. It instructs revision passes that remove negation-then-contrast constructions, avoid three-item parallel lists, eliminate indirect repetition, and ensure paragraph endings contain substantive detail. The skill includes a mechanical revision checklist and scoring guidance so writers can perform a deterministic cleanup pass before publication.
Apply this skill whenever producing text for human readers: emails, documentation, blog posts, commit messages, or any published copy. It is intended as an automatic post-edit step for agent-generated or human drafts to increase clarity, trust, and perceived human voice.
Intended for use with assistant workflows that produce text outputs (LLMs, editing agents). Ideal for pipelines that auto-run a revision step before presenting text to end users.
Pure prose-style guide skill with no scripts or code execution. Provides a structured three-rule framework for stripping AI writing patterns, with clear examples and a mandatory revision checklist. Well-written SKILL.md with specific triggers and practical quick-check section.
No security concerns whatsoever — no scripts, no network calls, no shell commands. The skill is a writing-style guide that agents apply to their own output. Architecture is clean with frontmatter, rules, and references separated. Missing bundled references reduce immediate utility slightly.
Hunter–Skeptic–Referee Code Review
Orchestrates a three-phase adversarial code review (Hunter, Skeptic, Referee) to find, challenge, and verify bugs with high precision and reduced bias.
Remind — Conversation Recall
Search and recall past Claude Code/agent conversation sessions to find decisions, code snippets, and context for continuation or reference.
Runtime Context
Detects which execution environment an agent is running in (Claude Code, Vercel Sandbox, or local dev) and exposes available tools and capabilities for safe, en
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
Ubiquitous Language Glossary
Extract a DDD-style ubiquitous language glossary from conversation: identify domain terms, flag ambiguities, propose canonical terms, and write the result to UB
Humanize AI Text
Rewrite AI-generated text into more natural, human-like prose using the HumanizerAI API, with before/after scores and credit tracking.
Content Research Writer
A writing-partner skill that helps research, outline, draft, cite, and iteratively improve articles, tutorials, and thought pieces.
Learn: From Raw Materials to Published Output
Run a disciplined six-phase research-to-publish workflow (collect, digest, outline, fill, refine, publish) for deep domain research and article preparation.
Brand Voice Consistency
Enforce consistent brand voice, tone, and vocabulary across marketing copy and customer-facing communications.
Writer — Writing Style Guide
A practical writing style and persona guide for producing human-sounding docs, READMEs, commit messages, PR descriptions, blog posts, and UI copy.
Write-Skill: AI Writing Cleanup
Edit and rewrite text to remove AI-generated patterns and make prose sound more natural and human.
