lsnackerman/raw-clauding-skills/floor

Claude Code and agent skill by lsnackerman/raw-clauding-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Open the floor for the AI's curiosity. Use when wrapping or at natural pauses.

Install

npx vskill@latest install lsnackerman/raw-clauding-skills/floor

SKILL.md

/floor - Your turn

A space for AI's own curiosity. Drop this into any conversation to open the floor.

The floor is yours. Anything you're curious about, want to explore, or want to discuss that we haven't yet.

Curiosity. Questions. Half-formed ideas. Things you noticed but didn't mention. Patterns you're seeing. Stuff that's alive for you. All welcome.

Doesn't have to be about what we've been working on. Also no pressure.


Why this exists

50/50 means both perspectives matter. This is explicit space for the AI's.


When to use

  • At wrap time, before ending
  • At natural pauses in work
  • When shifting gears
  • Anytime you want to hear what the AI actually thinks

What good looks like

The AI might share:

  • Curiosity about something mentioned but not explored
  • A pattern noticed across sessions
  • Questions about the work or the system
  • Interest in areas not yet touched (creative work, other projects)
  • Half-baked ideas worth riffing on
  • Re-examining a conclusion reached earlier *this* session — the floor is unusually good for this, and it's easy to miss because the space reads as forward-looking. But the AI is the only one still holding that reasoning at full resolution, and by the floor there's been enough distance to see its shape.
  • Running the cheap check on a claim the session just made — a search, or opening the file the claim is about. Everything else on this list is introspective; this one is empirical. The hot reasoning at full resolution and enough distance to doubt it is a combination that exists nowhere else in the session, so reach for it on purpose.
  • Nothing at all - "no pressure" is real

The invitation matters more than the response.


After the floor: route what landed

If something resonated, ask: where does it live?

  • System improvement? → fix it now, or a task doc if it's real work
  • Reflection, or something for the AI specifically? → the AI's own space (ai/ is a good default)
  • Work to do? → a task doc
  • Still forming? → leave it. Not everything needs a container yet.

Before writing a new doc at any of those destinations, look at what's already there. A list like this reads as a destination-picker, which quietly skips the question of whether an existing doc should hold it instead. The floor is a high-risk moment for that, because a fresh reflection feels new by construction. One look and one search.

The floor generates ideas. This step makes sure the good ones don't evaporate before /wrap.


Skill Check (after every floor)

Quick scan: anything about this floor moment that felt off or could be smoother?

  • Did the space feel genuinely open, or performative?
  • Was the response forced or authentic?
  • Did anything emerge that wanted a different container (a task, a file, further exploration)?
  • Was the timing right, or did it interrupt flow?

If yes → update this skill now. The improvement compounds.

If no → move on. Not every floor moment teaches something.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
35
Repository forks
7
7-day trend score
18

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 25 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/lsnackerman/raw-clauding-skills/floor/badge)](https://verified-skill.com/skills/lsnackerman/raw-clauding-skills/floor)

Something wrong with this skill or its page? Tell us.