AF football-pilgrimage
Generate a football pilgrimage guide for any team — stadium tours, football museums, fan pubs, and cultural landmarks. Each spot comes with deep storytelling (history, legends, anecdotes). Includes "On This Day" feature matching travel dates to historic football events, **live match detection during trip dates**, and **ticket search** (match tickets, attraction tickets via flyai). Use when: user asks for a football pilgrimage, stadium tour guide, fan culture trip, "pilgrimage guide" for a specific team, or wants to search for match/attraction tickets. Don't use when: user asks for match results, live scores, standings, or player stats (use football-data instead).
As a process F 56/100 · Will not run — References files that are not bundled: {crest_url}
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: {crest_url}
Process rating: all ten parameters 56/100
- 0Tools and files. 1 referenced file(s) missing: {crest_url}
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4304 tokens
- 100Steps. 116 steps
- 100Failures and branches. 24 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 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
- -221 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 671: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 116 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (3 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.