skills.rest
pablovilas
pablovilasCOMMUNITY
Explore all skills by this author →
GitHub

Confidence & Goal Setting Knowledge

Generate calibrated race goals with explicit uncertainty from training and performance data.

Updated Jan 26, 2026
Search Tags:#uncertainty#data-analysis#goal-setting#running#calibrated-predictions#athlete-coaching#riegel-formula
One-click install
npx skills add https://github.com/pablovilas/pacecraft --skill confidence-goal-setting-knowledge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Confidence & Goal Setting Knowledge
Source: https://github.com/pablovilas/pacecraft/tree/main/skills/confidence
Command: npx skills add https://github.com/pablovilas/pacecraft --skill confidence-goal-setting-knowledge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill provides calibrated, uncertainty-aware guidance for running performance goals, helping athletes avoid over-optimistic predictions and build sustainable targets.

Core Features & Use Cases

  • Data-quality assessment: Evaluates training history, race results, and key metrics to determine confidence in predictions.
  • Structured goal ranges: Generates A/B/C targets with explicit confidence and rationale, including finish likelihood for trails.
  • Improvement guidance: Recommends data enhancements (e.g., longer training blocks, tune-up races) to improve prediction reliability.

Quick Start

Instruct the AI to generate a calibrated marathon goal set (A/B/C) based on your recent 12 weeks of training data, including long runs and any recent race results.

Frequently Asked Questions about Confidence & Goal Setting Knowledge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set calibrated running race goals with honest uncertainty?▼

Calibrated running goals are generated by evaluating your training history, race results, VO2max, and pacing patterns to produce A/B/C targets with explicit confidence caps and rationale.

What running data do I need to generate calibrated race predictions?▼

You need recent training data such as long runs, race results, VO2max metrics, and pacing patterns to assess data quality and calculate calibrated race predictions with uncertainty ranges.

How does data quality assessment affect running goal confidence?▼

Data quality assessment evaluates training history and race results to determine prediction confidence, applying confidence caps and suggesting data improvements to reduce uncertainty.

Can I generate trail running goals with finish likelihood predictions?▼

Trail running goals are generated with structured A/B/C targets that include finish likelihood and rationale, based on long-run data and race results applied to trail distances.

What is the best way to reduce uncertainty in running race time predictions?▼

Uncertainty in running predictions is reduced by following improvement guidance that recommends longer training blocks, tune-up races, and additional performance data to increase calibration reliability.

Does the Riegel formula work for setting calibrated marathon goals?▼

The Riegel formula is applied alongside training history, long runs, and recent race results to generate calibrated marathon goal sets with explicit confidence ranges and honest uncertainty.

Related Skills

Explore More Data & Analytics Skills→
ArcanexisArcanexis
13

weather

Retrieve real-time weather, forecasts, and air quality data.

Community
Basic
ProfSynapseProfSynapse
26

dataset-improvement

Extract, review, and replace lines in JSONL dataset files with automatic backups.

Community
Intermediate
AlvaroLaraFFAlvaroLaraFF

swim-css

Compute Critical Swim Speed from 400m and 200m time trials.

Community
Intermediate
MuzeWinterMuzeWinter
1

market-sizing

Estimate market and opportunity size with transparent assumptions and sensitivity analysis.

Community
Advanced