research

Research prediction markets - base rates, resolution rules, historical data

Quality

52%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./src/skills/bundled/research/SKILL.md

Quality

Discovery

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 identifies a clear domain (prediction markets) but reads more like a topic list than an actionable skill description. It lacks explicit trigger guidance ('Use when...') and concrete action verbs, making it unclear when Claude should select this skill over others. The specificity to prediction markets helps with distinctiveness but the description needs more structure.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about prediction market odds, forecasting questions, or wants to research betting markets like Polymarket or Metaculus'

Convert topic nouns into action verbs: 'Researches base rates, analyzes resolution criteria, retrieves historical accuracy data from prediction markets'

Include common platform names and variations users might mention: 'Polymarket', 'Metaculus', 'PredictIt', 'forecasting', 'probability estimates'

Dimension	Reasoning	Score
Specificity	Names the domain (prediction markets) and lists some actions (research base rates, resolution rules, historical data), but these are more like topics than concrete actions. Missing verbs like 'analyze', 'extract', 'calculate'.	2 / 3
Completeness	Describes what (research prediction markets topics) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant terms like 'prediction markets', 'base rates', 'resolution rules', 'historical data' that users might mention, but missing common variations like 'forecasting', 'Polymarket', 'Metaculus', 'odds', 'probabilities'.	2 / 3
Distinctiveness Conflict Risk	'Prediction markets' is a fairly specific niche that wouldn't conflict with most skills, but 'research' and 'historical data' are generic enough to potentially overlap with general research or data analysis skills.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

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 well-structured overview of prediction market research capabilities with good token efficiency and clear output formatting. However, it lacks concrete implementation guidance for how Claude should actually access or compute base rates, and would benefit from explicit data source instructions and validation steps for research accuracy.

Suggestions

Add concrete implementation details for how Claude should access or compute base rates (e.g., specific data sources, APIs, or calculation methods)

Include validation steps for verifying research accuracy, such as cross-referencing multiple sources or flagging when data is uncertain/unavailable

Specify what Claude should do when historical data is insufficient or when a query doesn't match available research areas

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, presenting commands, research areas, and examples without explaining concepts Claude already knows. No unnecessary padding or verbose explanations of what prediction markets are.	3 / 3
Actionability	Provides concrete command syntax and example outputs, but the commands themselves are illustrative rather than executable code. The skill describes what to do but lacks implementation details for how Claude should actually perform lookups or access data sources.	2 / 3
Workflow Clarity	The skill shows input/output patterns clearly but lacks explicit workflow steps for conducting research. No validation checkpoints or feedback loops for verifying data accuracy or handling cases where historical data is unavailable.	2 / 3
Progressive Disclosure	For a skill of this size (~80 lines), the content is well-organized with clear sections for commands, research areas, examples, and output format. No unnecessary external references or deeply nested structure.	3 / 3
	Total	10 / 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
Commit: 2a8c94e

Reviewed: 28 days 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.