Calibrate guardrail thresholds from live hardware telemetry and emit environment presets. Use when thresholds are hand-tuned or drift with hardware changes.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add majiayu000/claude-skill-registry --skill adaptive-guardrail-calibrator --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Adaptive Guardrail Calibrator?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-adaptive-guardrail-calibrator-claude-skill-registry)More formats (shields.io, HTML) on the badges page.
---
name: adaptive-guardrail-calibrator
description: Calibrate guardrail thresholds from live hardware telemetry and emit environment presets. Use when thresholds are hand-tuned or drift with hardware changes.
---
# Adaptive Guardrail Calibrator
Use this skill to compute safe resource floors and caps from live telemetry.
## Workflow
1) Sample CPU, RAM, disk, and GPU metrics for a short window.
2) Compute conservative floors and caps.
3) Write environment presets for guardrails.
## Scripts
- Run: python scripts/calibrate_guardrails.py --duration 30 --interval 1 --apply
## References
- references/guardrail_defaults.json
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
