opportunity
Find and execute cross-platform arbitrage opportunities across prediction markets
47
35%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/opportunity/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear and distinctive niche—prediction market arbitrage—but is too terse to be effective for skill selection. It lacks a 'Use when...' clause, specific trigger terms users might naturally say, and detailed enumeration of the concrete actions the skill performs.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about arbitrage between prediction markets, finding mispriced contracts, or comparing odds across platforms like Polymarket, Kalshi, or Manifold.'
List more specific concrete actions such as 'compare contract prices across platforms, calculate arbitrage spreads, identify mispriced events, and recommend or execute hedged positions.'
Include natural trigger terms users would say, such as 'arb', 'betting odds', 'mispriced contracts', specific platform names, and 'price discrepancy'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prediction markets, cross-platform arbitrage) and two actions (find and execute), but lacks detail on what 'find' and 'execute' entail—e.g., comparing odds, placing trades, calculating expected value, monitoring price discrepancies. | 2 / 3 |
Completeness | Describes what the skill does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when' clause caps completeness at 2, and the 'what' is also thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'arbitrage', 'prediction markets', and 'cross-platform', but misses common user variations such as specific platform names (Polymarket, Kalshi, Manifold), 'betting odds', 'price discrepancy', or 'arb opportunities'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'cross-platform arbitrage' and 'prediction markets' is a very specific niche that is unlikely to conflict with other skills. This is a clearly distinct domain. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides comprehensive API documentation for a prediction market arbitrage tool, but it reads more like an auto-generated API reference than an actionable skill. It lacks a coherent end-to-end workflow with validation steps critical for financial operations, and the entire content is dumped into a single file rather than being progressively disclosed. The absence of error handling, risk validation checkpoints, and clear sequencing is concerning given the financial nature of the task.
Suggestions
Add a clear end-to-end workflow section (e.g., 'scan → evaluate → validate risk → execute → verify → record outcome') with explicit validation checkpoints and error recovery steps, especially given this involves real money.
Split the content into separate files: keep SKILL.md as a concise overview with quick-start example, and move the full TypeScript API reference, chat command reference, and scoring details into linked reference files.
Add validation and safety guardrails: what to check before executing (sufficient liquidity, fee impact, slippage limits), what to do if execution partially fails, and how to handle cross-platform settlement timing risks.
Remove verbose console.log formatting examples that pad token count without adding instructional value—Claude can generate appropriate logging on its own.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extensive and mostly relevant, but includes significant verbosity in console.log examples that pad the token count without adding instructional value. The opportunity types table and scoring breakdown are useful, but the sheer volume of API surface documented inline is excessive for a SKILL.md. | 2 / 3 |
Actionability | The TypeScript code examples appear executable and concrete, and chat commands are clearly specified. However, this appears to reference a library ('clodds/opportunity') that may not exist or be verifiable, making the 'copy-paste ready' quality questionable. The code is detailed but its real-world executability is uncertain. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow for actually finding and executing an arbitrage opportunity end-to-end. The content presents disconnected API methods without sequencing them into a coherent process. For an operation involving real money and cross-platform execution, there are no validation checkpoints, error recovery steps, or feedback loops for failed executions. | 1 / 3 |
Progressive Disclosure | This is a monolithic wall of text with the entire API reference inlined in a single file. The TypeScript API reference, chat commands, scoring details, and matching configuration should be split into separate reference files with the SKILL.md serving as a concise overview with links. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- alsk1992/CloddsBot
- Commit
e71a5f6
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.