Content
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a product requirements document or feature wishlist than an actionable skill for Claude. It describes what the system should do (track news, correlate prices, detect volume spikes) without providing any implementation guidance—no API endpoints, no code for fetching data, no concrete steps for correlation logic. The output format example is well-structured but without instructions on how to produce it, the skill lacks practical utility.
Suggestions
Add concrete implementation steps: which APIs or tools to call for fetching news (e.g., specific RSS parsing, Twitter API endpoints), how to query prediction market prices, and how to perform the correlation.
Provide executable code examples for at least the core workflow: fetching recent news, querying market prices, and matching news to affected markets.
Define a clear multi-step workflow with validation checkpoints, e.g., 1) Fetch news from sources, 2) Parse and extract entities, 3) Query matching markets, 4) Calculate price deltas, 5) Validate data freshness before presenting.
Clarify what tools/capabilities Claude actually has access to for this skill—can it make HTTP requests? Access specific APIs? Or is it working with user-provided data?
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some padding. The news sources section lists specific accounts and feeds which is useful, but the auto-matching examples and correlation features describe capabilities rather than instructing how to implement them. Some sections could be tightened. | 2 / 3 |
Actionability | The skill describes desired behaviors and outputs but provides no executable code, no API calls, no implementation details for fetching news, correlating with markets, or detecting volume spikes. It reads more like a feature spec than actionable instructions Claude can follow. | 1 / 3 |
Workflow Clarity | There is no clear multi-step workflow for how to actually fetch news, match it to markets, or calculate price impacts. The examples section shows input/output pairs but not the process steps. No validation or error handling is mentioned for any operation. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections (commands, sources, features, examples, output format) which aids readability. However, it's all inline in one file with no references to supporting files, and some sections like correlation features could benefit from being split out with implementation details. | 2 / 3 |
Total | 6 / 12 Passed |