rewrite-for-audience
Skill49 starsChanged 3 months agoMITView on GitHub
Rewrite text for a different audience, tone, length, or format while preserving the core meaning. Use when the user asks to rewrite, rephrase, simplify, formalise, or adapt text for a specific audience.
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
More formal: avoid contractions, use precise vocabulary, third person
- Very specific: line 39
Show comparison: if useful — use show_comparison to display original vs rewritten side-by-side.
- Distinctive: line 46
Don't add information that wasn't in the source
- Distinctive: line 47
Keep the same point of view unless the rewrite calls for change
- Distinctive: line 50
Don't dumb down to the point of inaccuracy
- Distinctive: line 51
Don't add jargon to make it "sound smarter"
- Distinctive: line 52
Don't change the meaning — adapt how it's said, not what's said
- Distinctive: line 53
Don't pad to hit a length target — be concise
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
Files
Rewrite for Audience
When to use
The user has source text and wants it adapted. Examples:
- "Rewrite this for a non-technical audience"
- "Make this more formal"
- "Simplify this paragraph"
- "Turn these notes into a press release"
- "Rewrite for LinkedIn"
Steps
- Identify the rewrite parameters — if not specified, ask via
ask_questions:- Audience (technical experts, general public, executives, customers, students)
- Tone (formal, conversational, persuasive, neutral, urgent)
- Format (email, blog post, social media, summary, script)
- Length (shorter, longer, same)
- Read the source carefully — identify:
- Core message (what must survive the rewrite)
- Specific facts/numbers (must remain accurate)
- Voice/perspective (first/second/third person)
- Rewrite — apply transformations:
- Simpler language: replace jargon with plain terms; shorter sentences
- More formal: avoid contractions, use precise vocabulary, third person
- More casual: contractions OK, conversational rhythm, second person
- For executives: lead with the conclusion/ask, support with brief evidence
- For social media: hook in first line, scannable, one idea
- For non-experts: define jargon, use analogies, examples first
- Preserve facts — never change numbers, names, dates, or specific claims.
- Show comparison if useful — use
show_comparisonto display original vs rewritten side-by-side. - Offer iterations — use
offer_choices: "Make it shorter", "More technical", "Different tone", "Looks good".
Style notes
- For Australian audiences: Australian English spelling, no Americanisms
- Match the source's structure unless format is being changed
- Don't add information that wasn't in the source
- Keep the same point of view unless the rewrite calls for change
What not to do
- Don't dumb down to the point of inaccuracy
- Don't add jargon to make it "sound smarter"
- Don't change the meaning — adapt how it's said, not what's said
- Don't pad to hit a length target — be concise
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-asks-tasksSkill
- caretakerSkill
- code-reviewSkill
- compare-optionsSkill
- create-reportSkill
- csv-analyseSkill
- document-qaSkill
- draft-emailSkill
- enrich-errorSkill
- extract-structured-dataSkill
- fact-checkSkill
- git-diff-summariserSkill
- librarian-curateSkill
- meeting-notesSkill
- morning-briefSkill
- plan-taskSkill
- reflectSkill
- remember-conversationSkill
- reverieSkill
- review-code-securitySkill
- review-email-toneSkill
- review-outputSkill
- review-summary-faithfulnessSkill
- route-findingSkill
- routine-health-checkSkill
- save-research-docSkill
- score-importanceSkill
- summarise-urlSkill
- web-researchSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

