BB garmin-analysis-skill
Bilingual Chinese-English cycling-health workflows using the public cycling-health CLI. Use when an assistant needs to sync Garmin China Wellness data to Intervals.icu; analyze Garmin sleep, recovery, training ability, activities, events, courses, workouts, plans, trends, or FIT/GPX data; query and compare Intervals.icu Wellness, activities, power, fitness, statistics, settings, sport settings, or calendar events; analyze personal iGPSPORT rides and FIT streams; query personal Strava athlete, zones, cycling activities, laps, streams, routes, gear, or rate limits; query or download Xingzhe route books; sync Garmin China activities to Garmin Global; or report cycling-health issues. The only supported personal activity-sync topology is Garmin CN -> Garmin Global -> the user's native Intervals.icu connection; never substitute direct FIT upload, Strava, iGPSPORT, or Xingzhe. Garmin CN Wellness -> Intervals.icu is separate; iGPSPORT and Strava are read-only analysis sources, and Xingzhe is route/GPX only. Also use for Chinese requests about 骑行健康、睡眠恢复、佳明国服与国际服同步、Intervals.icu、iGPSPORT、Strava、行者路书、FIT/GPX 分析或 cycling-health 故障。
Bilingual Chinese-English cycling-health workflows using the public cycling-health CLI.
As a process B 67/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1137 chars, limit 1024 - warning
body-longSKILL.md body ≈ 6934 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6934 tokens
- 85Steps. 107 steps, 3 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1137: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 28 headings
- +3Step-by-step instructions: 107 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.