BC football-data
Football (soccer) data across 13 leagues — standings, schedules, match stats, xG, transfers, player profiles. Zero config, no API keys. Covers Premier League, La Liga, Bundesliga, Serie A, Ligue 1, MLS, Champions League, World Cup, Championship, Eredivisie, Primeira Liga, Serie A Brazil, European Championship. Use when: user asks about football/soccer standings, fixtures, match stats, xG, lineups, player values, transfers, injury news, league tables, daily fixtures, or player profiles. Don't use when: user asks about American football/NFL (use nfl-data), college football (use cfb-data), NBA (use nba-data), WNBA (use wnba-data), college basketball (use cbb-data), NHL (use nhl-data), MLB (use mlb-data), tennis (use tennis-data), golf (use golf-data), Formula 1 (use fastf1), or betting odds (use polymarket or kalshi). Don't use for live/real-time scores — data updates post-match. Don't use get_season_leaders or get_missing_players for non-Premier League leagues (they return empty). Don't use get_event_xg for leagues outside the top 5 (EPL, La Liga, Bundesliga, Serie A, Ligue 1).
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1094 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5155 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5155 tokens
- 100Steps. 108 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +3Description length 1093: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 35 headings
- +3Step-by-step instructions: 108 items
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.