BC polymarket
Polymarket sports prediction markets — live odds, prices, order books, events, series, and market search. No auth required. Covers NFL, NBA, MLB, football (EPL, UCL, La Liga), tennis, cricket, MMA, esports. Supports moneyline, spreads, totals, and player props. Use when: user asks about sports betting odds, prediction markets, win probabilities, market sentiment, or "who is favored to win" questions. Don't use when: user asks about actual match results, scores, or statistics — use the sport-specific skill: football-data (soccer), nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), nhl-data (NHL), mlb-data (MLB), tennis-data (tennis), golf-data (golf), cfb-data (college football), cbb-data (college basketball), or fastf1 (F1). Don't use for historical match data. Don't use for news — use sports-news instead. Don't confuse with Kalshi — Polymarket focuses on crypto-native prediction markets with deeper sports coverage; Kalshi is a US-regulated exchange with different market structure.
As a process C 58/100 · Has gaps — weak spots: result and completion, consistency, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Risky intent
intent-wallet-secretsreferences/api.md:5Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- **py_clob_client** (Python SDK): Trading operations (create/cancel orders, view trades). Requires `pip install sports-skills[polymarket]` and a wallet private key. No CLI binary needed.
-
medium Risky intent
intent-wallet-secretsreferences/commands.md:31Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- `configure` — set wallet private key
Files scanned: 6. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (polymarket) differs from the folder (sports-skills-polymarket)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 28 steps
- 100Execution cost. Instruction body is 1526 tokens
- 100Running it twice. No mutating operations
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 996: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.