How do I install the Make It Sound Human skill?

Run npx skillmds@latest add vcxcvii/make-it-sound-human in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Make It Sound Human safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Make It Sound Human?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Make It Sound Human free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Make It Sound Human?

vcxcvii (@vcxcvii) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Make It Sound Human by vcxcvii — Agent Skill

Name: Make It Sound Human
Author: vcxcvii

Make It Sound Human

Cut a draft before adding to it, kill banned phrasing, replace abstraction with the specific numbers already in the data, and name the weakest paragraphs rather than silently rewriting everything. Use this skill whenever the user asks to: - Punch up, edit, or improve a draft - Make writing sound less generic or less like AI wrote it - Tighten a piece that reads flat Trigger even for casual requests like "punch this up", "make this better", "edit my draft", "this reads flat", "does this sound like a person wrote it".

vcxcvii 5026538 3.5 KB Updated Sep 17, 2026

File contents

make-it-sound-human

Context load

Run rainmaker context --check first. It prints what exists, what is stale, and exits 1 if anything this skill requires is missing.

Then read, in this order:

context/business.md in full. If absent, stop: "No business context. Run rainmaker audit, then the know-my-buyer skill."
context/voice.md if this skill writes prose. If absent, stop and say so.
context/glossary.md if this skill names products, features or competitors.
data/strategy.json if this skill reads or writes strategy.
Only the data/ files listed in this skill's Consumes table. Never crawl or call an API the core already covers.

If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:

"Business context was edited after the strategy was written. Re-run know-my-buyer, or run rainmaker context --sync to accept the prose as authoritative."

Then stop.

If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context. Nothing in it came from a buyer. Run know-my-buyer to replace it."

Consumes

File	Why	If missing
the draft	what to edit	ask for the draft or the slug
`context/voice.md`	the fixed floor plus site-specific rules and samples	continue with the fixed floor only, and say so
`data/strategy.json`	optional, to verify any number being sharpened is real	continue without it, note the gap

Produces

The draft in place, and a change log of what was cut and why.

Procedure

Cut before adding. Report the word count before and after; a punch-up that grows the draft by more than 10 percent has failed.
Kill every banned phrase from skills/_shared/voice-rules.md and any additional ones in context/voice.md.
Replace abstraction with the specific number already present in the data. Never invent one to replace a vague claim; if no real number exists, cut the claim instead of sharpening it into a false precision.
Move the strongest claim into the first 100 words.
Report the three weakest paragraphs by name and why, rather than silently rewriting everything the user did not ask you to touch.

Decision rules

A punch-up is not a rewrite. Preserve the author's structure and claims; tighten them.
Never soften an unsourced claim into a vaguer unsourced claim. Cut it.
The em-dash rule and the rest of the slop check apply to the edited output, checked again after editing, not only before.

Output

Before: <n> words   After: <n> words (<+/-n%>)

Cut:
  "<removed line>": <why: cliche / unsourced / redundant>

Weakest paragraphs (named, not rewritten silently):
  Paragraph <n>: <why it's weak>

Slop check after edit: <passed / issues remaining>

Done when

Word count moved down or stayed flat, the slop check passes on the edited version, and the three weakest paragraphs are named with a reason rather than quietly changed.

---name: make-it-sound-humandescription: Cut a draft before adding to it, kill banned phrasing, replace abstraction with the specific numbers already in the data, and name the weakest paragraphs rather than silently rewriting everything. Use this skill whenever the user asks to: - Punch up, edit, or improve a draft - Make writing sound less generic or less like AI wrote it - Tighten a piece that reads flat Trigger even for casual requests like "punch this up", "make this better", "edit my draft", "this reads flat", "does this sound like a person wrote it".---# make-it-sound-human## Context loadRun `rainmaker context --check` first. It prints what exists, what is stale, and exits 1 if anything this skill requires is missing.Then read, in this order:1. `context/business.md` in full. If absent, stop: "No business context. Run `rainmaker audit`, then the `know-my-buyer` skill."2. `context/voice.md` if this skill writes prose. If absent, stop and say so.3. `context/glossary.md` if this skill names products, features or competitors.4. `data/strategy.json` if this skill reads or writes strategy.5. Only the `data/` files listed in this skill's Consumes table. Never crawl or call an API the core already covers.If `strategy.json.context_hash` does not match the current hash of `context/business.md`, say exactly:"Business context was edited after the strategy was written. Re-run `know-my-buyer`, or run `rainmaker context --sync` to accept the prose as authoritative."Then stop.If `context/business.md` carries `confidence: stub`, continue, and stamp every output with: "Built on a stub context. Nothing in it came from a buyer. Run `know-my-buyer` to replace it."## Consumes| File | Why | If missing ||---|---|---|| the draft | what to edit | ask for the draft or the slug || `context/voice.md` | the fixed floor plus site-specific rules and samples | continue with the fixed floor only, and say so || `data/strategy.json` | optional, to verify any number being sharpened is real | continue without it, note the gap |## ProducesThe draft in place, and a change log of what was cut and why.## Procedure1. Cut before adding. Report the word count before and after; a punch-up that grows the draft by more than 10 percent has failed.2. Kill every banned phrase from `skills/_shared/voice-rules.md` and any additional ones in `context/voice.md`.3. Replace abstraction with the specific number already present in the data. Never invent one to replace a vague claim; if no real number exists, cut the claim instead of sharpening it into a false precision.4. Move the strongest claim into the first 100 words.5. Report the three weakest paragraphs by name and why, rather than silently rewriting everything the user did not ask you to touch.## Decision rules- A punch-up is not a rewrite. Preserve the author's structure and claims; tighten them.- Never soften an unsourced claim into a vaguer unsourced claim. Cut it.- The em-dash rule and the rest of the slop check apply to the edited output, checked again after editing, not only before.## Output```Before: <n> words After: <n> words (<+/-n%>)Cut: "<removed line>": <why: cliche / unsourced / redundant>Weakest paragraphs (named, not rewritten silently): Paragraph <n>: <why it's weak>Slop check after edit: <passed / issues remaining>```## Done whenWord count moved down or stayed flat, the slop check passes on the edited version, and the three weakest paragraphs are named with a reason rather than quietly changed.

Frequently asked questions