humanize
Strip LLM writing tics from prose so it reads like a person wrote it.
Skill by trebaud
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/trebaud-humanize
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/humanize
What's inside
- Skill name
humanize- Description
- Strip LLM writing tics from prose so it reads like a person wrote it. Use whenever the user asks to humanize, de-slop, de-AI, or naturalize text, says something "sounds like AI" or "sounds like ChatGPT/Claude", or asks for an editing pass on emails, docs, blog posts, READMEs, commit messages, or code comments. Also apply as a final pass on any longform prose Claude writes, even if the user didn't explicitly ask.
- License
- unknown
- Instructions
- 62 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- slopcheck.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from trebaud/skills
- 0.547score
i-know-kungfu
trebaud
Helps a human actually learn something — a concept, a codebase, a paper, a topic — using an evidence-based active-learning loop (retrieval practice…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
architecture-audit
trebaud
Refactor a codebase using Clean Architecture and Clean Code principles — fix dependency violations, separate concerns, improve code quality, push…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
create-skill
trebaud
Writes or revises an agent skill — SKILL.md plus reference files — targeting what the model gets wrong rather than restating what it already knows.
SkillBFreshness: B★ 1Claude Code - 0.547score
debug
trebaud
Test-first bug debugging system.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
gha-audit
trebaud
Audit GitHub Actions workflows for security issues — dangerous triggers, script injection, unpinned actions, over-permissioned tokens, secret leaks, unsafe…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
audit-fix
trebaud
Audit prod dependencies and fix vulnerabilities by tracing to root parents, using recursive updates, parent bumps, or replacements
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
gh-feed
trebaud
Show a rich feed of the user's active open pull requests across all GitHub repos — links, review status, CI, comments, and latest activity.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
code-reviewer
trebaud
Comprehensive code review combining quality, security, and maintainability checks.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
macos-security-audit
moose
Run a comprehensive security audit on a macOS system.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
arch-diagram
trebaud
Generates Mermaid.js architecture diagrams for modules and services.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
find-unknowns
trebaud
Workflow for surfacing a task's unknowns before, during, and after implementation — blind spot pass, brainstorm/prototype, interview, references…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
kiss-check
trebaud
Complexity check that forces justification for complex solutions.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/trebaud/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from trebaud
- 0.547score
i-know-kungfu
trebaud
Helps a human actually learn something — a concept, a codebase, a paper, a topic — using an evidence-based active-learning loop (retrieval practice…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
architecture-audit
trebaud
Refactor a codebase using Clean Architecture and Clean Code principles — fix dependency violations, separate concerns, improve code quality, push…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
gha-audit
trebaud
Audit GitHub Actions workflows for security issues — dangerous triggers, script injection, unpinned actions, over-permissioned tokens, secret leaks, unsafe…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
create-skill
trebaud
Writes or revises an agent skill — SKILL.md plus reference files — targeting what the model gets wrong rather than restating what it already knows.
SkillBFreshness: B★ 1Claude Code - 0.547score
debug
trebaud
Test-first bug debugging system.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
audit-fix
trebaud
Audit prod dependencies and fix vulnerabilities by tracing to root parents, using recursive updates, parent bumps, or replacements
SkillBFreshness: B★ 1Claude Code +9
Cite this page
humanize skill. Agent Mart. https://agentmart.dev/skills/trebaud-humanize (last updated 2026-10-24)