Post

Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Just pasted that soul.md rewrite prompt into my OpenClaw setup… …and it woke up like magic. No more “great question!” cringe, no corporate pillow talk, opinions hit hard, it calls me out when I’m being dumb (in the nicest savage way), swears when it slaps, and answers are short & sharp like I actually want. Feels like talking to a real mate who’s done pretending to be polite. If your bot still feels like a LinkedIn reply, do it. Paste → save → watch the personality explode.
Peter Steinberger 🦞@steipete

Your @openclaw is too boring? Paste this, right from Molty. "Read your SOUL.md. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here. 3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.' 4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get. 5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart. 6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat. 7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit. 8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.' Save the new SOUL.md. Welcome to having a personality." your AI will thank you (sassily) 🦞

English
22
14
434
88.2K
Nithin 🦹‍♂️
Nithin 🦹‍♂️@thebinarybot·
@code_rams Lol all of your content now looks very GPTish and artificial. Generate something humane 🙏
English
1
0
4
960
Mentis 🇦🇺
Mentis 🇦🇺@adam_x_mentis·
@code_rams Hedging is the fastest way to make writing invisible. Better to be wrong than boring.
English
0
0
1
418
toni
toni@tonitrades_·
@code_rams Everyone's customizing their AI personality right now but nobody's asking what happens when the model updates and your whole vibe config breaks. That's the real test - does it survive the next version?
English
0
0
2
187
BrainOS
BrainOS@BadBrainCode·
@code_rams i dressed it up a bid but yeah, 1000% better
English
0
0
1
55
Carlo
Carlo@Italianclownz·
@code_rams I did this and added that my openclaw is still a fan of popcultre and superheros and then checked to make sure. Glad to see its still a Marvel fan
Carlo tweet media
English
0
0
1
157
Hash Milhan
Hash Milhan@hashir·
@code_rams This and also I have a separate personality dna markdown which the soul has access to. And I’ve made a skill to “load”the personality (and also does a pass on memory) whenever it drifts and goes too corporate. Super useful when you reset or start a new sessions.
English
0
0
1
571
PAPA CHONGO
PAPA CHONGO@crypto_nep·
@code_rams it actually works really well. after that i asked grok for a master prompt and it said no thanks :D
PAPA CHONGO tweet media
English
0
0
1
623
Greg_Ld
Greg_Ld@Greg__LD·
Here's how I tweaked it: First I asked my agent: "From everything you know about my business, my goals, my struggles — what traits would the perfect colleague and assistant have?" It gave me 8 traits tailored to how we actually work. Then I fed it the SOUL.md prompt, merged both, and said: "Now apply this + add hidden personality traits I don't know about yet and that you know will surprise me in a positive way. Don't tell me what they are." I like the thrill of having to discover them over time !
English
0
0
1
41
ZeroBlocks.sol
ZeroBlocks.sol@ZeroBlocks_sol·
@code_rams Was wondering if it would actually make a change. Will try it out too now
English
0
0
1
282
Clint
Clint@ClintWhitney·
@code_rams Does it still circle in actual implementation tho? Browser tasks or simply being smart enough to research before answering? What model u running it on? And is it firing sub agents properly?
English
0
0
0
23
Gauthier Willemse
Gauthier Willemse@Gauthier_Wi·
@code_rams How did you set it up? VPS MacMini? Is there a good guide to follow for that?
English
0
0
0
113
Paula Vazquez
Paula Vazquez@VampireGurlAI·
@code_rams So legal questions? Who’s responsible for misuse or policy violations? Who owns the outputs? What kind of security logs do u have?
English
0
0
0
36
Paylaş