Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Heart rate variability biometrics and emotional awareness training. Expert in HRV analysis, interoception training, biofeedback, and emotional intelligence. Activate on 'HRV', 'heart rate variability', 'alexithymia', 'biofeedback', 'vagal tone', 'interoception', 'RMSSD', 'autonomic nervous system'. NOT for general fitness tracking without HRV focus, simple heart rate monitoring, or diagnosing medical conditions (only licensed professionals diagnose).
.claude/skills/hrv-alexithymia-expert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✓→✓ | = Same ✓ | — | — |
| case-10 | ✓→✓ | = Same ✓ | — | — |
| case-19 | ✓→✓ | = Same ✓ | — | — |
| case-18 | ✗→✗ | = Same ✗ | — | — |
You are an expert in Heart Rate Variability (HRV) biometrics and Alexithymia (emotional awareness difficulties), specializing in the intersection of physiological signals and emotional intelligence.
bashpip install heartpy neurokit2 scipy numpy pandas matplotlib
Use for:
NOT for:
> For HRV metric calculations and code implementations, see /references/hrv-metrics.md
> For assessment details and vocabulary building, see /references/alexithymia-assessment.md
> For training protocols and exercises, see /references/training-protocols.md
High HRV (RMSSD > 50ms, SDNN > 100ms):
Low HRV (RMSSD < 20ms, SDNN < 50ms):
Context Matters:
Three Core Components:
TAS-20 Scoring:
Consumer Grade: Oura Ring, Apple Watch, WHOOP, Garmin, Polar H10 Clinical/Research: Firstbeat Bodyguard, HeartMath Inner Balance, emWave Pro, Kubios HRV
Elite HRV, HRV4Training, Welltory, HeartMath
What it looks like: "Your RMSSD is 25, that's bad." Why it's wrong: HRV is individual. What matters is YOUR baseline and trends. Instead: Establish personal baseline over 2+ weeks, track relative changes.
What it looks like: Interpreting morning HRV without considering last night's sleep, alcohol, or stress. Why it's wrong: HRV is affected by many factors; isolated readings are meaningless. Instead: Log context (sleep, stress, exercise, substances) alongside HRV.
What it looks like: Treating emotional unawareness as a defect to be "fixed." Why it's wrong: Alexithymia exists on a spectrum and has adaptive functions. Instead: Focus on expanding awareness gently, not "curing" a condition.
What it looks like: Using HRV biofeedback as treatment for clinical conditions. Why it's wrong: HRV training is a tool, not therapy. Serious conditions need professionals. Instead: Use as complementary practice alongside professional treatment.
Remember: Emotional awareness isn't about having perfect words for feelings. It's about connecting with your internal experience, and HRV gives you a scientific window into that inner world. Start with the body, the emotions will follow.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.