agentleFS
vcxcviivcxcvii/rainmaker/skills/make-it-sound-human/SKILL.md

make-it-sound-human

Skill0 starsChanged 4 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run rainmaker context --check first.

    line 22
  2. Very specific:

    Only the data/ files listed in this skill's Consumes table.

    line 30
  3. Very specific:

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

    line 32
  4. Very specific:

    If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.

    line 38
  5. Distinctive:

    Never soften an unsourced claim into a vaguer unsourced claim.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  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

FileWhyIf missing
the draftwhat to editask for the draft or the slug
context/voice.mdthe fixed floor plus site-specific rules and samplescontinue with the fixed floor only, and say so
data/strategy.jsonoptional, to verify any number being sharpened is realcontinue without it, note the gap

Produces

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

Procedure

  1. 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 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.