markets
Search and view prediction market data from Polymarket, Kalshi, Manifold, and Metaculus
57
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/markets/SKILL.mdQuality
Discovery
54%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 benefits from naming four specific prediction market platforms, which provides excellent trigger terms and distinctiveness. However, it lacks a 'Use when...' clause and could be more specific about the concrete actions it supports beyond 'search and view'. Adding explicit trigger guidance and more detailed capabilities would significantly improve this description.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks about prediction markets, betting odds, forecasts, or mentions Polymarket, Kalshi, Manifold, or Metaculus.'
Expand the action verbs to be more specific, e.g., 'Search markets, view current prices and probabilities, compare odds across platforms, and track market history.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prediction markets) and some actions ('search and view'), but doesn't list more specific concrete actions like placing bets, comparing odds, tracking price history, or analyzing market trends. | 2 / 3 |
Completeness | Describes what it does (search and view prediction market data) but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also somewhat thin, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'prediction market', 'Polymarket', 'Kalshi', 'Manifold', 'Metaculus' — these are exactly the terms users would naturally use when asking about prediction markets. The specific platform names provide excellent coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche — prediction markets with four named platforms. This is highly unlikely to conflict with other skills since prediction market data is a distinct domain with specific platform names as triggers. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a clean, well-structured overview of prediction market search functionality but critically lacks actionable implementation details. The commands appear to reference some tool or system that is never defined—there are no API calls, no tool specifications, no code, and no indication of how Claude should actually execute these searches. The skill reads more like a feature spec than an executable guide.
Suggestions
Define what tools/APIs Claude should use to execute these commands—include actual API endpoints, MCP tool names, or executable code for searching each platform.
Add concrete output format examples (e.g., a sample JSON response or formatted table) so Claude knows exactly what to return.
Include error handling guidance: what to do when no markets are found, when a platform is unavailable, or when results are ambiguous across platforms.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Reasonably concise but the platform descriptions add little value Claude wouldn't already know. The examples section is somewhat redundant with the commands section. | 2 / 3 |
Actionability | No executable code, no API endpoints, no concrete implementation details. The commands (/markets, /price, /orderbook) are undefined—there's no indication of what tool, API, or system these map to. The examples show desired behavior but not how to achieve it. | 1 / 3 |
Workflow Clarity | The commands are listed clearly and the examples show expected input/output patterns, but there's no guidance on error handling, rate limits, what to do when a market isn't found, or how to resolve ambiguous results across platforms. | 2 / 3 |
Progressive Disclosure | For a simple skill under 50 lines, the content is well-organized into logical sections (Commands, Supported Platforms, Examples) with clear headers and no unnecessary nesting. | 3 / 3 |
Total | 8 / 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.