AC garmin-coach-loop
Maintain one current 28-day running-and-strength direction from the latest available Garmin or Intervals.icu evidence. Use when the user asks to reassess a goal or plan, create or revise a hybrid week, decide what to do today, review planned versus actual training, or preview and deliver a selected workout. Trigger for requests such as 根據最新資料重新評估我的目標與課表, 月目標, 周計畫, 今天練什麼, 根據 Garmin 調整訓練, 每週複盤, 跑步和重訓怎麼排, 傳到 Garmin, 記錄今天的重訓, 臥推 65 公斤 4 組照做了, 記錄體重, 體重 72.5, 補一筆今天的跑步, 匯入我的 Garmin/Strava/Apple Health 歷史資料, 這是我的訓練紀錄匯出檔. Do not use it for medical diagnosis or device shopping.
Maintain one current 28-day running-and-strength direction from the latest available Garmin or Intervals.icu evidence. Use when the user asks to reassess a…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (garmin-coach-loop) differs from the folder (long-run-hybrid-coach)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 16 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2358 tokens
- 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 574: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 16 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.