AC tftcoach
Use this skill when the user asks about Teamfight Tactics (TFT) — comps, items, augments, economy, pivoting, positioning, or any gameplay advice. Triggers: 'tftcoach', 'tft', 'teamfight tactics', 'what comp should I play', 'what items should I build', 'should I pivot', 'which augment', 'tft help', 'when to level', 'how to play tft'. Reads board state from screenshots or descriptions, gives real-time coaching on comps, items, economy, augments, and pivoting. Do NOT use for: League of Legends (Summoner's Rift), other auto-battlers, or TFT account issues.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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
✓ No remarks against the Agent Skills spec
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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Failures and branches. 5 branches
- 100Steps. 60 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1801 tokens
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 558: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.