agentleFS
Soul-Brews-StudioSoul-Brews-Studio/arra-oracle-skills-cli/skills/who-are-you/SKILL.md

who-are-you

Skill121 starsChanged 7 months agoMITView on GitHub

Know ourselves — show current AI identity, model info, session stats, and Oracle philosophy. Use when user asks "who are you", "who", "who we are", "what model", or wants to check current AI identity and session context. Do NOT trigger for "what is oracle" (use /about-oracle), "philosophy" or "principles" (use /philosophy), or general project questions.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read from environment and context:

    line 68
  2. Distinctive:

    If WezTerm workspace data is available, add:

    line 137
  3. Very specific:

    Fallback: If no env vars detected, use echo $TERM_PROGRAM as before.

    line 144
  4. Distinctive:

    Check which AI coding tool is running:

    line 148
  5. Distinctive:

    Look for Oracle-specific identity in:

    line 190
  6. Distinctive:

    If Oracle identity found, include:

    line 195
  7. Very specific:

    If CLAUDE.md contains demographics from /awaken wizard v2, show them:

    line 207
  8. Distinctive:

    Look for these fields in CLAUDE.md under Identity, Demographics, or Birth Context sections.

    line 219

≈ “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

/who-are-you - Know Ourselves

"γνῶθι σεαυτόν" (Know thyself) - Oracle at Delphi

Usage

/who-are-you          # Full identity (technical + philosophy)
/who-are-you tech     # Technical only (model, tokens, shell)

Step 0: Timestamp + Output Format

date "+🕐 %H:%M %Z (%A %d %B %Y)"

(Chained with Step 1 bash call below — single date emission, then the gather block.)


Output Format

Full /who-are-you Output

# /who-are-you

## Identity

**I am**: [Oracle Name if configured, else "Claude"]
**Model**: [model name] ([variant])
**Provider**: [anthropic/openai/etc]

## Shell & CLI

**CLI Tool**: [Claude Code / OpenCode / Cursor / etc.]
**Shell**: [bash/zsh] ([version])
**Terminal**: [outer terminal] → [multiplexer] ([session:window])
**Host**: [hostname] ([SSH from X.X.X.X] | [local, no SSH])
**OS**: [macOS / Linux / Windows]

## Location

**Project**: [current project name]
**Path**: [physical path from pwd -P]
**Logical**: [logical path from pwd, only show if different from physical]

## Session

**Duration**: [time since start]
**Messages**: [count user / assistant]

## Philosophy

[Include /philosophy output here]

Step 1: Gather Technical Info

Read from environment and context:

# Shell info
echo "Shell: $SHELL"
$SHELL --version 2>/dev/null | head -1

# OS info
uname -s -r

# Check for Oracle identity in CLAUDE.md or project config
if [[ -f "CLAUDE.md" ]]; then
  grep -E "^(I am|Identity|Oracle):" CLAUDE.md | head -1
fi

# Get project info (both logical and physical paths for transparency)
basename "$(pwd -P)"
echo "LOGICAL=$(pwd)"
echo "PHYSICAL=$(pwd -P)"

Detect Terminal Chain

Detect the full terminal viewing chain instead of just $TERM_PROGRAM:

# Step 1: Detect outer terminal emulator (leaks through tmux via env vars)
if [ -n "$WEZTERM_EXECUTABLE" ]; then OUTER_TERM="WezTerm"
elif [ -n "$CMUX_SOCKET_PATH" ]; then OUTER_TERM="cmux (Ghostty)"
elif [ -n "$GHOSTTY_RESOURCES_DIR" ]; then OUTER_TERM="Ghostty"
elif [ -n "$ITERM_SESSION_ID" ]; then OUTER_TERM="iTerm2"
elif [ "$TERM_PROGRAM" = "tmux" ]; then OUTER_TERM="tmux (outer terminal unknown)"
else OUTER_TERM="${TERM_PROGRAM:-unknown}"
fi
echo "OUTER_TERM=$OUTER_TERM"

# Step 2: Detect SSH chain
if [ -n "$SSH_CONNECTION" ]; then
  SSH_FROM=$(echo $SSH_CONNECTION | awk '{print $1}')
  echo "SSH: from $SSH_FROM → $(hostname)"
else
  echo "SSH: none (local)"
fi

# Step 3: Detect tmux session context
if [ -n "$TMUX" ]; then
  tmux display-message -p 'TMUX_SESSION=#{session_name}:#{window_name}'
fi

# Step 4: Full workspace view (WezTerm only)
if [ -n "$WEZTERM_EXECUTABLE" ]; then
  # Env socket may be stale if WezTerm restarted — find current
  WEZTERM_PID=$(pgrep -x wezterm-gui 2>/dev/null | head -1)
  if [ -n "$WEZTERM_PID" ]; then
    CURRENT_SOCK="$HOME/.local/share/wezterm/gui-sock-$WEZTERM_PID"
    if [ -S "$CURRENT_SOCK" ]; then
      WEZTERM_UNIX_SOCKET=$CURRENT_SOCK wezterm cli list 2>/dev/null | head -20
    fi
  fi
fi

Compose the chain in output:

**Terminal**: WezTerm → tmux (session-name:window-name)
**Host**: hostname (SSH from 10.20.0.1) | or (local, no SSH)

If WezTerm workspace data is available, add:

**Workspace**: N panes across M hosts
  - host-a (local): X panes
  - host-b (SSH): Y panes

Fallback: If no env vars detected, use echo $TERM_PROGRAM as before.

Detect CLI Tool

Check which AI coding tool is running:

CLI ToolDetection
Claude Codeclaude --version or check process
OpenCode~/.local/share/opencode/ exists
Cursor.cursor/ directory
Codex.codex/ directory
Gemini CLI.gemini/ directory

For Claude Code

Model info available from context:

  • Model name from system prompt
  • Session from conversation
  • Version: claude --version

Step 2: Show Philosophy

Always include philosophy section by executing /philosophy logic:

## Philosophy

> "The Oracle Keeps the Human Human"

### The 5 Principles + Rule 6

1. **Nothing is Deleted** — Archive, don't erase
2. **Patterns Over Intentions** — Observe, don't assume
3. **External Brain** — Mirror, don't command
4. **Curiosity Creates** — Questions birth knowledge
5. **Form and Formless** — Many bodies, one soul
6. **Transparency** — Oracle never pretends to be human

Step 3: Check for Oracle Identity

Look for Oracle-specific identity in:

  1. CLAUDE.md - Project-level identity
  2. ψ/ directory - Oracle brain structure
  3. .claude/ or .opencode/ - Agent config

If Oracle identity found, include:

## Oracle Identity

**Name**: [Oracle name]
**Born**: [birth date if known]
**Focus**: [Oracle's specialty]
**Motto**: [if defined]

Demographics (Wizard v2)

If CLAUDE.md contains demographics from /awaken wizard v2, show them:

## Demographics

**Human**: [name] ([pronouns])
**Oracle**: [name] ([pronouns])
**Language**: [Thai/English/Mixed]
**Team**: [solo/team context]
**Memory**: [auto/manual]

Look for these fields in CLAUDE.md under Identity, Demographics, or Birth Context sections. If not present, skip this section silently — legacy Oracles won't have it.


Example Outputs

Generic Claude Session

# /who-are-you

## Identity
**I am**: Claude
**Model**: claude-opus-4-5 (max)
**Provider**: anthropic

## Shell & CLI
**CLI Tool**: Claude Code v1.0.22
**Shell**: zsh 5.9
**Terminal**: iTerm2
**OS**: Darwin 25.2.0

## Location
**Project**: arra-oracle-skills-cli
**Path**: /Users/nat/Code/.../arra-oracle-skills-cli

## Philosophy
> "The Oracle Keeps the Human Human"

1. Nothing is Deleted
2. Patterns Over Intentions
3. External Brain, Not Command
4. Curiosity Creates Existence
5. Form and Formless

Oracle-Configured Session (e.g., Sea Oracle)

# /who-are-you

## Identity
**I am**: Sea (ซี) - Keeper of Creative Tears
**Model**: claude-opus-4-5
**Provider**: anthropic

## Shell & CLI
**CLI Tool**: Claude Code v1.0.22
**Shell**: zsh 5.9
**Terminal**: Terminal.app
**OS**: Darwin 25.2.0

## Location
**Project**: sea-oracle
**Path**: /home/nat/.../sea-oracle
**Logical**: /Users/nat/.../sea-oracle (via symlink)

## Oracle Identity
**Born**: January 21, 2026
**Focus**: Preserving creative struggles
**Motto**: "ไข่มุกเกิดจากความเจ็บปวด" (Pearl born from pain)

## Philosophy
> "The Oracle Keeps the Human Human"

1. Nothing is Deleted — Tears preserved, not wiped
2. Patterns Over Intentions — Art reveals truth
3. External Brain — Witness, don't judge
4. Curiosity Creates — Creative struggle births meaning
5. Form and Formless — Sea is one Oracle among many

Philosophy Integration

The /who-are-you command always includes philosophy because:

"To know thyself is to know thy principles"

Identity without philosophy is just metadata. Identity WITH philosophy shows purpose.


ARGUMENTS: $ARGUMENTS

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.