Real-time market data feeds from 8 prediction market platforms
45
32%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/feeds/SKILL.mdQuality
Discovery
22%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 is too terse and passive—it reads more like a feature label than a skill description. It fails to specify concrete actions the skill performs and completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select it. The prediction market domain provides some distinctiveness, but the lack of specificity and trigger guidance significantly weakens its utility.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'prediction markets', 'Polymarket', 'Kalshi', 'betting odds', 'forecast probabilities', 'event contracts'.
List specific concrete actions such as 'Fetches current odds, retrieves historical price data, compares probabilities across platforms, tracks contract movements'.
Name the 8 platforms explicitly (e.g., Polymarket, Kalshi, Metaculus, PredictIt) to improve trigger term coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'real-time market data feeds' and '8 prediction market platforms' but does not list any concrete actions (e.g., fetch prices, compare odds, track contracts). It describes what the skill provides, not what it does. | 1 / 3 |
Completeness | The 'what' is only weakly stated (data feeds, not actions), and there is no 'when' clause or explicit trigger guidance at all. The missing 'Use when...' clause would cap this at 2 regardless, but the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | 'Prediction market' and 'market data' are relevant keywords users might say, but it lacks common variations like specific platform names (Polymarket, Kalshi, Metaculus), 'odds', 'betting markets', 'forecasting', or 'probabilities'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Prediction market platforms' is a fairly specific niche that distinguishes it from general financial data skills, but without naming specific platforms or actions, it could overlap with general market data or financial analysis skills. | 2 / 3 |
Total | 6 / 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 reads as a comprehensive API reference document rather than a focused skill file. While the code examples are concrete and executable (strong actionability), the content is far too verbose for a SKILL.md—it should be a brief overview pointing to detailed reference files. The lack of workflow sequencing and error handling guidance for real-time trading operations is a notable gap.
Suggestions
Restructure as a concise overview (under 50 lines) with quick-start examples, linking to separate files like API_REFERENCE.md, PLATFORM_DETAILS.md, and EXAMPLES.md for the detailed content.
Add a clear workflow showing the typical sequence: initialize feed manager → search markets → subscribe → analyze edge → calculate position size, with validation/error handling at each step.
Remove redundant console.log boilerplate from code examples—Claude knows how to print output. Keep examples minimal and focused on the API calls themselves.
Add error handling patterns for common failure modes: authentication failures, WebSocket disconnections, rate limit hits, and invalid market IDs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose at ~200+ lines, mostly consisting of exhaustive API reference material that could be in a separate file. Many code examples are padded with console.log statements that add no instructional value, and the sheer volume of method documentation reads like auto-generated API docs rather than a focused skill. | 1 / 3 |
Actionability | The content provides fully executable TypeScript code examples with concrete method calls, parameters, and expected outputs. Chat commands are specific and copy-paste ready with clear syntax patterns. | 3 / 3 |
Workflow Clarity | Individual operations are clear, but there's no sequenced workflow showing how to go from setup to subscribing to analyzing edge. No validation checkpoints exist for connection failures, invalid market IDs, or authentication errors despite WebSocket reconnection being mentioned only as a bullet point. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with the entire API reference inlined. The platform-specific features, full API reference, and best practices should be split into separate files with the SKILL.md serving as a concise overview with links. No references to external files exist. | 1 / 3 |
Total | 7 / 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 | |
e71a5f6
Table of Contents
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.