BC strava-training-coach
AI running coach that prevents injuries by monitoring your Strava training load daily. Detects dangerous mileage spikes, intensity imbalances, and recovery gaps using evidence-based sports science (80/20 rule, acute:chronic workload ratio), then sends smart alerts to Discord or Slack before problems become injuries. Use when: - "Am I overtraining?" — Analyze weekly mileage and intensity for injury risk - "Check my training load" — Run a daily analysis of your Strava activities - "Send me a training report" — Generate a weekly summary with 4-week trends - "Is my running mileage safe?" — Calculate acute:chronic workload ratio (ACWR) - "Set up automated training alerts" — Schedule daily checks via cron - Monitoring heart rate to ensure easy days are actually easy (80/20 compliance) - Tracking recovery gaps and consistency streaks - Optional Oura ring integration for sleep and readiness scores Unlike basic Strava data skills, this coach actively monitors your patterns daily and alerts you before problems become injuries — backed by research from Seiler (2010), Gabbett (2016), and Stoggl & Sperlich (2014). Security: No hardcoded secrets, input validation, log redaction, webhook URL validation, secure token storage (XDG, 0600 permissions), rate limiting, 30s request timeouts.
AI running coach that prevents injuries by monitoring your Strava training load daily.
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
exfil-webhook-urlSKILL.md:69Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)export DISCORD_WEBHOOK_URL=https://discord.com/api/webhooks/...
placeholder -
low Exfiltration
exfil-webhook-urlSKILL.md:75Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)export SLACK_WEBHOOK_URL=https://hooks.slack.com/...
placeholder
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1294 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 43 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1657 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1293: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.