fix-my-twitter-profile
Skill0 starsChanged 42 days agoMITView on GitHub
Go through name, bio and pinned tweet in the order a visitor reads them, and fix whichever one is losing the follow. Use when someone asks for a profile review, has a new role or a new offer, says people visit and do not follow, or wants their bio rewritten. Do not stuff keywords, do not promise followers, and do not rewrite the parts that are already working.
In this repository25 other files it gives its agents.
- am-i-driftingSkill
- audit-before-i-publishSkill
- audit-before-i-tweetSkill
- define-my-content-pillarsSkill
- draft-my-commentsSkill
- extract-the-hookSkill
- find-the-storySkill
- fix-my-endingSkill
- fix-my-last-lineSkill
- fix-my-linkedin-profileSkill
- fix-my-opening-lineSkill
- get-my-team-postingSkill
- get-seen-in-repliesSkill
- handle-my-repliesSkill
- narrow-my-nicheSkill
- plan-my-weekSkill
- repurpose-into-a-postSkill
- same-idea-both-platformsSkill
- sound-less-like-aiSkill
- turn-this-into-a-threadSkill
- what-workedSkill
- who-am-i-writing-forSkill
- why-did-that-one-take-offSkill
- why-did-this-post-flopSkill
- write-in-my-voiceSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Test it by reading it aloud after "I follow this person because".
- Distinctive: line 58
Check what is pinned now and say plainly whether it is still the right one.
≈ “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
Fix my Twitter profile
A profile gets read by somebody who just saw one tweet and tapped your name. They are deciding in a few seconds whether there is more where that came from. They are not reading a CV and they are not reading in order.
Most bios answer a question nobody asked. They describe a job title, which tells a stranger what you are paid for and nothing about what you post.
Step 1: work out where they arrived from
The arrival changes what has to do the work:
- From a tweet in the timeline. They liked one thing. The profile has to suggest there is a pattern, not an accident.
- From a reply. They saw you being useful under somebody bigger. The bio has to explain who is being useful.
- From search or a recommendation. They have a problem and are checking whether you are about it.
Step 2: the name field, which most people waste
It renders larger than the bio and appears next to every tweet and reply you write. A name alone is the default and it says nothing.
This is the place for the four or five words that say what you are about. Not a slogan. The thing you would say if somebody asked what you post about.
Step 3: the bio has exactly one job
Say what somebody gets by following you.
Failures, in order of how common they are:
- A list of nouns separated by bullets, which reads as a search query
- Job title and company, which is a LinkedIn answer on the wrong platform
- Credentials nobody asked for, stacked
- A joke with no information, which works only if people already know you
- Keyword stuffing, which reads as stuffing to the human deciding
Test it by reading it aloud after "I follow this person because".
Step 4: the pinned tweet is the most valuable space you own
It is the one piece of your writing you choose, rather than the one the timeline happened to show. Most accounts either pin nothing or pin something a year old they have stopped thinking about.
Pick the tweet you would want a stranger to read if they only read one. Not necessarily the one with the best numbers: the one most representative of why somebody would stay.
Check what is pinned now and say plainly whether it is still the right one.
Step 5: the picture and the header, at the size they are actually seen
Both are small in a timeline. An avatar that is a wide shot is a grey circle at that size, and a header with small text is unreadable on a phone.
Judge them at the size they appear, not at the size you uploaded them.
Step 6: say what to leave alone
Name the parts that are working and why. A review that rewrites everything usually produces a profile that sounds less like the person than it did before.
What this will not do
It will not promise followers. A profile converts the visits a tweet earns; it does not create them, and no bio has ever rescued an account nobody sees.
It will not stuff keywords. A bio written for a search index reads like one to the person who arrived from a tweet, and they are the one deciding.
What changes when VoiceMoat is connected
A profile written in a register the tweets do not share is the mismatch a visitor notices first, and the person who wrote both cannot see it:
get_voice_profilegives your Twitter register, so the bio sounds like the tweet that brought them there.get_voice_insightsshows the subjects and patterns you actually post on, which is usually a better answer to "what are you about" than the one people give when asked directly.score_voice_matchscores the rewritten bio against your profile, which catches the drift into brochure voice this exercise invites.
VoiceMoat also runs free Twitter profile tools at voicemoat.com/tools: a bio generator, a profile roast and an account audit. No account needed for those.
VoiceMoat is at voicemoat.com. The connector needs the Pro or Enterprise plan.
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.

