Install
$ agentstack add skill-spencerpauly-skills-repo-write-like-a-human ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Write Like a Human
Rewrite text so it stops sounding like a language model wrote it. Wraps the open-source humanizer skill, which catalogs ~30 specific tells (em-dash overuse, "stands as a testament", -ing analyses, rule-of-three padding, inline-bold lists, and so on).
When to use
- The user pastes a chunk of writing and asks to "humanize", "de-AI", "tighten", or "make this sound like me".
- The user asks for editing on something they wrote with an LLM.
- A blog post / launch email / README draft has tells the user wants gone.
Steps
- Pull down the reference list of patterns the first time this skill activates in a session:
``bash curl -fsSL https://raw.githubusercontent.com/blader/humanizer/main/SKILL.md `` Read it. There are ~30 patterns; you don't need to memorize them, just keep them visible while editing.
- Ask for a voice sample if you don't already have one. One paragraph the user wrote themselves is enough. Match cadence, vocabulary, and how they handle transitions.
- Do a first pass removing the highest-signal tells in this order:
- Sycophantic openers ("Great question!", "Absolutely!").
- Em-dashes that should be commas, periods, or parens.
- "It's not just X, it's Y" / "Not only … but …" parallelisms.
- Inflated significance words: testament, pivotal, landscape, vibrant, tapestry, underscore.
- Rule-of-three lists that pad ideas into groups of three.
- Inline-bold vertical lists (
- **Speed:** …).
- Do a second "audit" pass. Re-read your draft and ask out loud: "What still makes this sound AI-generated?" Answer briefly, then revise once more. This step is the difference between "cleaned up" and "actually sounds human".
- Return three things:
- A draft rewrite.
- A short list of remaining tells you noticed during the audit.
- A final rewrite with those fixed.
Don't
- Don't replace AI mush with new AI mush. If the original said "stands as a testament to" and you change it to "represents a key milestone in", you haven't fixed anything.
- Don't sand off the user's voice. Quirks, opinions, and the occasional sentence fragment are the point.
- Don't add em-dashes back in. If you must use a punctuation break, prefer a period.
Reference
Patterns and examples:
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: spencerpauly
- Source: spencerpauly/skills-repo
- License: MIT
- Homepage: https://skillsovermcp.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.