← all publishers

nli33

@nli33 source repo

Report this profile Claim this profile

• 4 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Explainer · nli33

   Teach or explain a system, codebase, or concept precisely and incrementally, calibrated to the user's stated background. Use when the user asks to be taught, walked through, or explained something in depth over multiple turns ("explain step by step", "teach me X", "walk me through this so I understand it deeply").
   0 installs
2. ▌
   Overnight · nli33

   Run Claude Code autonomously overnight on the UTM Linux VM (warvm) via a "Ralph loop" — fresh stateless claude -p per iteration, state on disk. Use when the user wants to launch, check on, or resume an unattended overnight agent run on the VM.
   0 installs
3. ▌
   AI Writing · nli33

   Use when asked to check, flag, or discuss whether text reads as AI-generated or human-written — analyzing an essay, email, post, or document for AI writing tells. Reference only; does not instruct rewriting or "humanizing" text.
   0 installs
4. ▌
   Project Notes · nli33

   Set up or use the centralized ~/notes project-notes repo for a code project — links a project's tangential research/debugging notes into it via a gitignored symlink, kept out of the host repo's own git history. Use when the user asks to "set up notes"/"link notes" for a repo, when starting a new notes/ folder for exploratory work, or when a project's notes have grown large and need splitting.
   0 installs