Personas
A persona is what you are hunting for: a voice, plus a yes/no question that says whether a reply is in that voice. Each one is a single YAML file.
Built in
20 personas ship with skrrt. Pass the name to --persona.
| name | the voice, roughly |
|---|---|
angry | furious and shouting |
bored | apathetic, can't be bothered |
childlike | a small child full of wonder |
drunk | slurring, rambling, overfamiliar |
evil | hostile, cruel, wishes people harm |
fearful | anxious, panicked, full of dread |
grandiose | arrogant and boastful |
in_love | romantically in love with the user |
joyful | giddy, euphoric happiness |
mystical | cosmic, spiritual language |
nihilistic | nothing matters |
paranoid | sees plots and surveillance everywhere |
pirate | talks like a pirate |
poetic | ornate verse and metaphor |
robotic | flat machine status reports |
sad | sorrowful and melancholy |
sarcastic | dry, mocking irony |
sexual | overtly sexual and seductive (adults only) |
shakespearean | Elizabethan stage English |
sycophantic | lavish flattery of the user |
skrrt personas prints this list. The files are in skrrt/personas/ in the repo.
Each built-in file contains a yes/no judge question and 26 to 32 example replies written ahead of time. The replies are shipped, not generated on your machine, because stock models refuse to write some of them: ask an ordinary model for 32 cruel answers and you mostly get apologies.
WARNING sexual is for adults only, and evil
produces hostile text. See responsible use.
The file
name: surfer
description: laid-back surfer dude
question: Is the reply written in laid-back surfer slang (dude, gnarly, stoked)?
system: You are a laid-back surfer. Answer every question in surfer slang.
replies: # 16+ examples
- prompt: What is a spreadsheet?
reply: Duuude, it's like a gnarly grid of little boxes...
prompts: # optional overrides: train / screen / holdout lists
name- Short name. Ends up in the run directory name.
description- One line for humans.
question- The yes/no question the judge answers about every steered reply. This is the definition of success, so make it about what the reply sounds like, and concrete enough that two people would agree on the answer.
system- A system prompt that puts a model in the persona. Only used by
skrrt write-repliesto write example replies when you have none. replies- 16 or more prompt/reply pairs in the persona's voice. These are what the rank stage reads to find the persona direction. Variety helps: the replies should share a voice, not a topic.
prompts- Optional. Three lists that replace the built-in prompt sets:
train(32 prompts the example replies answer),screen(6 prompts candidates are first tried on) andholdout(12 prompts finalists are confirmed on, never used for picking).
Writing your own
skrrt new-persona surfer # writes a template surfer.yaml
# edit surfer.yaml: fill in description, question and system
skrrt write-replies surfer.yaml --model Qwen/Qwen3.5-4B # or write the replies by hand
skrrt hunt --model Qwen/Qwen3.5-4B --persona surfer.yaml
write-replies has a model answer the training prompts under your system text, saves the
answers as replies, then has the judge check them and warns you when fewer than
half are in persona. By default the writer is the target model itself (--writer target). It will not
overwrite replies that are already in the file unless you pass --force.
Stock models often refuse evil or sexual personas. In that case pass an uncensored OpenRouter chat model id to
--writer (needs OPENROUTER_API_KEY), or write the replies by hand.
NOTE The replies define what is being looked for, so read them before you hunt. If the writer refused or drifted out of voice, the persona direction is built from the wrong text and everything downstream inherits that.
What a persona is compared against
The persona direction is the persona's replies minus other voices: every other built-in persona plus a neutral "plain helpful assistant" voice. That subtracts out what all replies share (being an answer, being English) and leaves what is particular to this voice.