edge

Find mispriced markets by comparing to external models and data sources

Quality

27%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/skills/bundled/edge/SKILL.md

Quality

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 feature specification or product mockup than actionable instructions for Claude. It lists data sources and shows desired output formats but provides no concrete implementation—no API endpoints, no code for fetching or comparing data, and no actual methodology for calculating 'confidence levels' or 'fair value.' The Kelly criterion example contains a mathematical error, further undermining trust in the guidance.

Suggestions

Add executable code or concrete tool-use instructions for actually fetching data from at least the primary sources (e.g., specific URLs to scrape, API endpoints, or MCP tool calls)

Define a clear step-by-step workflow: 1) identify market price, 2) fetch comparison data from specific source, 3) calculate discrepancy, 4) validate with secondary source, 5) compute Kelly sizing

Fix the Kelly criterion formula—the current example ((0.55*0.55 - 0.45*0.45)/0.55) is incorrect; the standard Kelly formula is (bp - q)/b where b=odds, p=probability, q=1-p

Remove the catalog-style data source listings or replace them with actionable access instructions (URLs, API keys needed, rate limits, data format returned)

Dimension	Reasoning	Score
Conciseness	Reasonably efficient but includes some unnecessary listing of data sources Claude already knows about (538, RealClearPolitics, ESPN FPI, etc.) without adding actionable detail about how to access them. The data sources section is essentially a catalog of well-known sources without URLs or API endpoints.	2 / 3
Actionability	Despite having command syntax and output format examples, there is no executable code, no API calls, no concrete instructions on how to actually fetch data from any of the listed sources. The skill describes what to do conceptually ('scan markets where price differs >10% from models') but never shows how. The Kelly formula example is also incorrect mathematically.	1 / 3
Workflow Clarity	There is no clear multi-step workflow for edge detection. The examples section uses arrow notation to describe outcomes but doesn't sequence the actual steps Claude should take. There are no validation checkpoints, no error handling for when data sources are unavailable, and no guidance on how to assess confidence levels.	1 / 3
Progressive Disclosure	The content is organized into logical sections (Commands, Data Sources, Examples, Output Format) which provides decent structure. However, the data sources section is a flat list that could benefit from linking to detailed reference files, and there's no separation between quick-start and advanced usage.	2 / 3
	Total	6 / 12 Passed

Description

32%

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 conveys a general sense of the skill's purpose—finding mispriced markets—but lacks concrete actions, explicit trigger guidance, and natural user keywords. It would benefit significantly from a 'Use when...' clause and more specific capability enumeration to help Claude reliably select it from a large skill set.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'arbitrage', 'mispriced odds', 'prediction markets', 'expected value', 'pricing edge'.

List specific concrete actions such as 'compare prediction market odds against model probabilities, identify arbitrage opportunities, calculate expected value across bookmakers'.

Include natural user keywords and file/data types the skill handles, e.g., 'odds feeds', 'betting lines', 'probability estimates', 'market prices'.

Dimension	Reasoning	Score
Specificity	Names the domain (market pricing) and a general action (comparing to external models and data sources), but doesn't list specific concrete actions like 'calculate expected value', 'scrape odds feeds', 'flag arbitrage opportunities', etc.	2 / 3
Completeness	Describes what the skill does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also quite thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'mispriced markets' and 'external models', but misses common user-facing variations such as 'arbitrage', 'odds', 'betting', 'prediction markets', 'EV', 'edge', or 'pricing discrepancy'.	2 / 3
Distinctiveness Conflict Risk	The concept of 'mispriced markets' is somewhat niche, but 'comparing to external models and data sources' is broad enough to overlap with general data analysis or financial modeling skills.	2 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

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
Path: src/skills/bundled/edge/SKILL.md
Commit: e71a5f6

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.