BC mlb-matchup-analyzer
Analyzes a single MLB game from a fantasy perspective given home team, away team, and date. Emits structured matchup signals -- opp_sp_quality, park_hitter_factor, park_pitcher_factor, weather_risk, bullpen_state -- and a short narrative of platoon implications (handedness matchup for hitters). Use when preparing daily start/sit calls, evaluating a streaming pitcher's environment, sizing weather risk, or when user mentions matchup analysis, park factor, opposing pitcher, weather risk, or platoon.
Analyzes a single MLB game from a fantasy perspective given home team, away team, and date.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityresources/methodology.md:283Offensive-security / dual-use content (legitimate for authorised testing; review intended use)If confidence drops below 0.4, the red team should flag this signal file as low-trust and the consuming agent should weight it accordingly.
-
low Risky intent
intent-offensive-securityresources/template.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Copy this template to `signals/YYYY-MM-DD-matchup.md` and fill in the blanks. Every value must trace to a cited URL. Leave `confidence` below 0.4 for any signal where a source could not be reached, an
detector -
low Risky intent
intent-offensive-securitySKILL.md:124Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)2. **Cite every URL.** Every signal value must be traceable to a specific source URL in `source_urls:`. If a fact cannot be verified via web search, drop `confidence` to 0.3 or lower and flag in red t
detector
Files scanned: 4. 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 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 50 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2455 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 501: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.