ann-handley
Skill0 starsChanged 26 days agoMITView on GitHub
Apply Ann Handley's Everybody Writes framework to create or audit marketing content — blog posts, emails, homepages, About Us pages, social copy, or any customer-facing writing. Invoke when user says "use Ann Handley," "Everybody Writes," "apply the Handley framework," or asks for help with content voice, writing quality, or copy that needs to sound more human, or defining a brand voice. Not for structural/narrative frameworks (use the storybrand skill for that).
In this repository22 other files it gives its agents.
- ai-writing-tellsSkill
- animated-explainerSkill
- buyer-personasSkill
- desktop-mockupSkill
- linkedin-guest-kitSkill
- mobile-mockupSkill
- pesty-asana-tasksSkill
- pesty-designSkill
- pesty-explainerSkill
- pesty-frontendSkill
- presentation-structureSkill
- problem-solving-processSkill
- pyramid-principleSkill
- scrSkill
- storybrandSkill
- storytellingSkill
- transcript-cleanupSkill
- ui-designSkill
- untangleSkill
- website-launch-impact-reportSkill
- youtube-thumbnailsSkill
- yt-structureSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Before writing a single word, answer these two questions:
- Distinctive: line 27
Keep asking "So what? Because…" until you can't go further.
- Distinctive: line 32
If you can't answer So What clearly, stop and ask the user before writing.
- Very specific: line 36
Read references/writing-rules.md for the full set of writing rules and techniques.
- Very specific: line 58
Read references/audit-checklist.md for the full checklist.
- Very specific: line 66
Read references/voice-grammar.md — the "How to Develop Brand Voice" section.
- Distinctive: line 78
Run the storybrand skill first to build the BrandScript and structure, then apply Handley's rules to the output in the Shine phase.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Ann Handley Copywriting Skill
Mode Detection
Determine mode before doing anything else:
- Write mode: User wants to CREATE content (blog post, email, homepage copy, social, About Us, etc.).
- Audit mode: User wants to EVALUATE existing copy against Handley's quality standards.
- Voice mode: User wants to DEVELOP or document a brand voice.
WRITE MODE
Step 1: So What? (REQUIRED — never skip)
Before writing a single word, answer these two questions:
- What is the goal? What business or marketing outcome does this content serve?
- So what? Reframe the goal for the reader: why does this matter to them? What's in it for them (WIIFM)?
Keep asking "So what? Because…" until you can't go further. The answer to the last "Because" is your real angle.
Bad goal: "We want to announce our new scheduling feature." Good reframe: "Readers waste hours every week on back-and-forth booking emails. This feature gives them that time back."
If you can't answer So What clearly, stop and ask the user before writing.
Step 2: Write to One Person
Read references/writing-rules.md for the full set of writing rules and techniques.
Key discipline: Identify the specific reader (the "Petunia") before writing. Not a market segment — a real individual. Write to that person as if across a kitchen table.
Apply the Writing GPS framework:
- Go (prep): Goal → So What? → Data/evidence → Organize
- Push (draft): Ugly First Draft → Draft 2 (cut wrong words) → Draft 3 (reader swap) → Draft 4 (add voice/humor)
- Shine (polish): Robot edit → Read aloud → Eyeball for scanners → Headline last
Step 3: Apply Voice and Grammar Rules
Read references/voice-grammar.md for:
- The "Youness" brand voice framework
- Banned words (Frankenwords, Weblish, buzzwords)
- Grammar defaults (present tense, active voice, strong verbs, no adverbs)
Deliverable: the finished copy, plus a 2-3 bullet note on the Handley rules applied.
AUDIT MODE
Read references/audit-checklist.md for the full checklist. If a numeric score is wanted, also read references/scoring.md for the rubric.
For each failure: state what is broken, quote the offending copy, suggest the exact fix.
VOICE MODE
Read references/voice-grammar.md — the "How to Develop Brand Voice" section.
Deliverable: A 4-word voice definition + style guide with "do/don't" examples for each word.
Pairing with StoryBrand
These two frameworks complement each other:
- StoryBrand = structure and narrative (what to say, in what order)
- Ann Handley = voice and quality (how to say it, at what standard)
Run the storybrand skill first to build the BrandScript and structure, then apply Handley's rules to the output in the Shine phase.
Troubleshooting
User can't answer "So what?" This is a strategy problem, not a writing problem. Ask: "Who is the one person reading this, and what do you want them to do or feel differently after reading it?" Don't write until that's clear.
Copy sounds corporate despite following rules. Apply the Dear Mom test: rewrite the opening as if explaining the concept to someone who loves you. Then strip the "Dear Mom" salutation and keep the voice.
User wants to skip the GPS and just edit what they have. Fine for Audit mode. In Write mode, skipping the So What step produces copy that serves the company, not the reader. Flag it.
Audit on very short copy (taglines, social posts). Scope to: Does it open a story loop? Is it customer-centric (not company-centric)? Does it pass the "It's-me Minute" test?
Example
Write mode — homepage hero section: User: "Use Ann Handley to write the hero section for a pest control company." Skill: So What check → reader = homeowner who saw a mouse and feels embarrassed + anxious → goal = get them to book → reframe: "You deserve to feel at home in your home." Output applies: customer-centric language, present tense, no running start, strong verbs, one specific CTA, no buzzwords.
Audit mode: User: "Audit this About Us page." Skill: Loads audit-checklist.md → flags: "Company-centric FAIL — first paragraph is entirely about founding history. Reader isn't in it until paragraph 3. Move the customer problem to the top. Cut 'we believe in excellence' — table stakes, not differentiating."
Maintained by Pesty Marketing · Browse the full skill catalog.
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
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.

