self-validation-loop
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
16 stars
Best use case
self-validation-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
Teams using self-validation-loop should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/self-validation-loop/SKILL.md --create-dirs "https://raw.githubusercontent.com/plurigrid/asi/main/ies/music-topos/.claude-marketplaces/topos-skills/plugins/topos-skills/skills/self-validation-loop/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/self-validation-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How self-validation-loop Compares
| Feature / Agent | self-validation-loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Self-Validation Loop Use when training or evaluating self-validation for 3-stream color systems. ## Inputs - seed, indices - sources: splitmix_ternary, xoroshiro_3color, gay_mcp - comparator: reafference or comparator ## Workflow 1. Predict expected colors (efference copy). 2. Observe actual colors (color_at or stream generation). 3. Compare predictions with observations. 4. Aggregate accuracy and surprise. ## Gay MCP tools - gay_seed, efference_copy, color_at, reafference, comparator, active_inference, self_model ## Metrics - accuracy = matches / total - surprise = mismatch count or summed error - pass threshold: accuracy >= 0.99 or surprise == 0 ## Output - JSON log with seed, indices, predicted, observed, errors, accuracy, surprise ## Example prompt "Run a self-validation loop over indices 1..20 and report accuracy and surprise."
Related Skills
We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.