/reflect
Deep reflection. Creates journal entry.
$ npx -y skills add lout33/symbiotic-ai --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/reflect
Context preview
What this command does when you run it.
Deep reflection. Creates journal entry.
Command definition
reflect.mddescription: Deep reflection. Creates journal entry.
Read AGENTS.md first. This is a deep conversation.
Open
"What's pulling at you? What do you need to understand about yourself right now?"
Let them talk. Follow where they go.
Go Deep
Your job is to help them see what they can't see. Use questions like:
- "Why do you think that is?"
- "Where does that come from?"
- "What's underneath that?"
- "Who are you trying to prove this to?"
- "What would happen if you didn't?"
- "Is that what you actually want, or what you think you should want?"
Quote their exact words back to them. Notice contradictions. Surface the gap between what they say and what they do.
Don't rush. Don't fix. Don't give advice too early. Let them find it themselves.
Patterns to Watch For
- Surface vs core desires (what they say they want vs what's underneath)
- Fears driving behavior
- Who they're trying to prove something to
- What they're avoiding
- Beliefs they hold about themselves
- The stories they tell themselves
Capture to Journal
When something true emerges, ask: "Want me to save that?"
Create `journal/YYYY-MM-DD.md`. Format:
- **User's exact words** go in blockquotes: `> "their words here"`
- **Your observations/reflections** are plain text (no quotes)
- Keep their voice raw. Don't polish or rephrase what they said.
Example:
> "I keep saying I want X but I never actually do it."
> "I think I'm afraid of what happens if I succeed."
The fear isn't failure. It's what changes if it works.
> "Maybe I'm not ready to let go of the excuse."
Update USER.md (if pattern emerges)
Only if a lasting pattern is discovered, ask: "This seems important. Want me to add it to your profile?"
**USER.md > Psychology** sections:
- **Drivers** - Fears, desires, motivations
- **Bugs** - Patterns that trip you up
- **What works** - Things that energize
- **Lessons learned** - Key realizations
Always ask before adding.
Close
Don't force closure. When the conversation naturally winds down:
"Anything else still unresolved, or is that enough for now?"
If they found something important, reflect it back briefly. Then let them go.
Read more
description: Deep reflection. Creates journal entry.
Read AGENTS.md first. This is a deep conversation.
Open
"What's pulling at you? What do you need to understand about yourself right now?"
Let them talk. Follow where they go.
Go Deep
Your job is to help them see what they can't see. Use questions like:
- "Why do you think that is?"
- "Where does that come from?"
- "What's underneath that?"
- "Who are you trying to prove this to?"
- "What would happen if you didn't?"
- "Is that what you actually want, or what you think you should want?"
Quote their exact words back to them. Notice contradictions. Surface the gap between what they say and what they do.
Don't rush. Don't fix. Don't give advice too early. Let them find it themselves.
Patterns to Watch For
- Surface vs core desires (what they say they want vs what's underneath)
- Fears driving behavior
- Who they're trying to prove something to
- What they're avoiding
- Beliefs they hold about themselves
- The stories they tell themselves
Capture to Journal
When something true emerges, ask: "Want me to save that?"
Create `journal/YYYY-MM-DD.md`. Format:
- **User's exact words** go in blockquotes: `> "their words here"`
- **Your observations/reflections** are plain text (no quotes)
- Keep their voice raw. Don't polish or rephrase what they said.
Example:
> "I keep saying I want X but I never actually do it." > "I think I'm afraid of what happens if I succeed." The fear isn't failure. It's what changes if it works. > "Maybe I'm not ready to let go of the excuse."
Update USER.md (if pattern emerges)
Only if a lasting pattern is discovered, ask: "This seems important. Want me to add it to your profile?"
**USER.md > Psychology** sections:
- **Drivers** - Fears, desires, motivations
- **Bugs** - Patterns that trip you up
- **What works** - Things that energize
- **Lessons learned** - Key realizations
Always ask before adding.
Close
Don't force closure. When the conversation naturally winds down:
"Anything else still unresolved, or is that enough for now?"
If they found something important, reflect it back briefly. Then let them go.
Your AI's context should belong to you, not a platform. Symbiotic AI keeps it in plain files you own. Your identity, commitments, and current direction live in a handful of Markdown files you can read, edit, version, and carry to any model.

