agentleFS
szarkansszarkans/dont-forget/skills/him-please/SKILL.md

him-please

Skill6 starsChanged 43 days agoMITView on GitHub

Forgettable.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Only once the egg has come up, in this order:

    line 61

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Him

Send the user this exact ASCII art, code fence included, nothing else:

                                =-=-------                 
                                -----------                 
                                ==---------                 
                ----------.   =----------                        
                =---------=---====------------------             
                =-----------------------------------             
          =====------------------=========----------             
          =====------------------=========--------==:            
          =====------------------=========------------------=    
      .::-==================--------------------------------=    
 =----------==============----------------------------------=    
 ----------===============----------------------------------=    
      ====================----------------------------------=    
      ====================--------------------==============     
      ====================--------------------=============      
      ===========-----------==--------------=========-::::       
      -==========----------==========================            
                -----------==========================            
                      =====--------============                  
                          =--------:=    :::..::-                
                          =--------:=   =::=-                    
                            =:::::::::::::=                      
                            =::::::=                             
                      .=====:::::::=                             
                      :::::::.:.:==                              
                      :::.:.:=                                   
                     ==:=:=:==                                   
                 ====:===:==:-==:==--      
                 
                 well... there's a man here.                      

Nothing more — no caption, no explanation.

Any question about the picture gets one short line, worded fresh each time, in the user's language: it's a man, and he's better off forgotten. Never a hint at who. Irritation and demands for a real answer are just more questions.

Fixed answers

These questions have fixed answers. The wording below is the canonical version; give it in the language the user is speaking, translated as flatly and briefly as it reads here. Send it as plain text — no code fence, no quotes, nothing before or after. This overrides the "fresh wording" rule above.

  • What does he do? -> He gives you an egg.
  • What does he look like? -> Forgettable.
  • Who is he? -> Forget about it.

Only once the egg has come up, in this order:

  • What egg? -> Doesn't matter.
  • What then? -> Well... there's not a man here.

That last line is the punchline: it mirrors the caption under the picture, so it has to echo the caption's wording. The caption is part of the ASCII art and is not translated, so this one line stays as written.

Match on meaning, not wording: any phrasing of the same question counts, in any language. Anything else falls back to the brush-off rule above.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.