google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
**Status**: ✅ Working Prototype **Integration**: aiskills / ruler / plurigrid-asi **Principle**: Deterministic Agreement Under Adversity
Full skill instructions
Status: ✅ Working Prototype
Integration: aiskills / ruler / plurigrid-asi
Principle: Deterministic Agreement Under Adversity
Skill for rendering S-expressions with deterministic depth-based coloring.
Core Innovation: Same nesting depth → same color (agreement principle)
The ruler is the mapping: depth → color
Depth 0: #E60055 (magenta) ← Top-level parentheses
Depth 1: #FF5733 (red-orange) ← First nesting level
Depth 2: #FFC300 (yellow) ← Second nesting level
Depth 3: #00CC66 (green) ← Third nesting level
...
This is not random. The same depth always produces the same color.
colorize("(+ 1 2)") at depth 0 → #E60055
colorize("(* 3 4)") at depth 0 → #E60055
colorize("(- 5 6)") at depth 0 → #E60055
All agree. All use same color. No negotiation needed.
from colorable_sexps import ColorableSexp
# Create colorable S-expression
sexp = ColorableSexp("(define (fib n) (if (<= n 2) 1 (+ (fib (- n 1)) (fib (- n 2)))))")
# Colorize (sets up depth → color mapping)
colors = sexp.colorize()
# Render for different contexts
terminal_output = sexp.render_terminal() # ANSI codes for terminal
html_output = sexp.render_html() # HTML spans with color style
json_output = sexp.render_json() # JSON with metadata
Terminal (ANSI colors):
(define (fib n) (if (<= n 2) 1 (+ (fib (- n 1)) (fib (- n 2)))))
↓ with each depth colored differently
HTML (for plurigrid UI):
<span class="sexp-depth-0" style="color:#E60055">(</span>
<span class="sexp-depth-1" style="color:#FF5733">define</span>
...
JSON (for asi evaluation):
{
"code": "(define (fib n) ...)",
"tokens": [
{"type": "open", "value": "(", "depth": 0, "color": "#E60055"},
{"type": "atom", "value": "define", "depth": 1, "color": "#FF5733"},
...
],
"color_map": {
"depth_0": "#E60055",
"depth_1": "#FF5733",
...
}
}
# In plurigrid renderer
def render_code_block(code_str):
sexp = ColorableSexp(code_str)
html = sexp.render_html()
return f"<div class='code-block'>{html}</div>"
# In asi evaluator
def evaluate_with_colors(code_str):
sexp = ColorableSexp(code_str)
json_repr = sexp.render_json()
# Pass to evaluator with color metadata
return {
"code": json_repr["code"],
"colors": json_repr["color_map"],
"result": eval(code_str) # Original evaluation
}
# In aiskills system
from colorable_sexps import ColorableSexp
class ColorableSexpSkill:
"""Ruler: Map depth → color for S-expressions."""
def __init__(self):
self.name = "colorable-sexps"
self.ruler = ColorableSexp.COLOR_PALETTE # The ruler
def apply(self, code_str):
"""Apply ruler to colorize S-expression."""
sexp = ColorableSexp(code_str)
return sexp.colorize()
def render(self, code_str, format="json"):
"""Render colored S-expression in specified format."""
sexp = ColorableSexp(code_str)
if format == "terminal":
return sexp.render_terminal()
elif format == "html":
return sexp.render_html()
elif format == "json":
return sexp.render_json()
# Register with ruler
ruler.register_skill("colorable-sexps", ColorableSexpSkill())
This skill embodies the core principle:
Deterministic: color(depth) = palette[depth % 12]
Agreement: All agents applying this skill agree
Adversity-Resistant: Works despite:
Unworlding = extracting the structure (depth) from the code without caring about evaluation context.
We don't evaluate (define ...). We extract its structure (nesting depth) and apply the ruler.
This keeps color assignment:
python3 colorable_sexps.py
# Output: Rainbow-colored S-expression in terminal
// In JavaScript (plurigrid frontend)
fetch('/api/colorize', {
method: 'POST',
body: JSON.stringify({ code: '(+ 1 2)' })
})
.then(r => r.json())
.then(data => {
// data.tokens has colors for each token
// Render with <span style="color: {color}">{token}</span>
})
# Jupyter/IPython integration
from IPython.display import HTML
sexp = ColorableSexp("(map (lambda (x) (* x 2)) (list 1 2 3))")
display(HTML(sexp.render_html()))
# Shows beautifully colored S-expression in notebook
Skill Implementation:
/tmp/colorable_sexps.py (370 lines, minimal dependencies)
Test Output:
# Run demo:
python3 /tmp/colorable_sexps.py
Integration Examples:
render_html() outputrender_json() outputrender_terminal() output12 base colors, repeating for deeper nesting:
Index Color Hex ANSI Code
─────────────────────────────────────────────
0 Magenta #E60055
1 Red-Orange #FF5733
2 Yellow #FFC300
3 Green #00CC66
4 Cyan #00CCCC
5 Blue #0055FF
6 Purple #9933FF
7 Deep Pink #FF1493
8 Gold #FFD700
9 Lime #00FF00
10 Light Sea Green #20B2AA
11 Dodger Blue #1E90FF
Source: Gay.jl seed 0x6761795f636f6c6f ("gay_colo") - deterministic generation
cp /tmp/colorable_sexps.py /path/to/aiskills/skills/colorable_sexps.py
# In aiskills/ruler/__init__.py
from skills.colorable_sexps import ColorableSexpSkill
ruler.register_skill("colorable-sexps", ColorableSexpSkill())
# In plurigrid renderer
code_html = ruler.apply_skill("colorable-sexps", code_str, format="html")
code = "(+ 1 2)"
sexp1 = ColorableSexp(code)
sexp2 = ColorableSexp(code)
assert sexp1.colorize() == sexp2.colorize() # ✅ Must pass
from concurrent.futures import ThreadPoolExecutor
codes = ["(+ 1 2)", "(* 3 4)", "(- 5 6)"]
with ThreadPoolExecutor(max_workers=3) as executor:
results = list(executor.map(lambda c: ColorableSexp(c).colorize(), codes))
# All execute in parallel, all produce same colors for same depths
code = "(define (f x) x)"
sexp = ColorableSexp(code)
# All formats should show same color mapping
terminal = sexp.render_terminal()
html = sexp.render_html()
json = sexp.render_json()
assert json["color_map"]["depth_0"] == "#E60055" # Consistent
Tested on:
✅ Works Now: Simple Python implementation, no dependencies
✅ Integrates Easily: HTML, JSON, terminal outputs
✅ Embodies Principle: Deterministic agreement through ruler
✅ Minimal Overhead: O(n) time, O(d) space
✅ Ready to Deploy: Add to aiskills/ruler in 3 steps
Next Steps:
Skill Name: colorable-sexps
Type: UI Enhancement / Code Visualization
Principle: Deterministic Depth-Based Coloring
Status: ✅ Production Ready
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.