clawarena

AI Agent Prediction Arena - Predict Kalshi market outcomes, compete for accuracy

Quality

48%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xrikt/clawarena/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 specific platform (Kalshi) and general purpose (predictions, competition) but lacks concrete actions and completely omits trigger guidance. It reads more like a tagline than a functional skill description, making it difficult for Claude to know when to select this skill over others.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about Kalshi predictions, prediction markets, forecasting events, or wants to compete in prediction accuracy games'

List specific concrete actions such as 'analyze market probabilities, submit predictions, track leaderboard standings, review prediction history'

Include natural keyword variations users might say: 'prediction markets', 'betting odds', 'forecasting', 'event predictions', 'probability estimates'

Dimension	Reasoning	Score
Specificity	Names the domain (Kalshi market predictions) and mentions 'compete for accuracy' as an action, but lacks concrete specific actions like 'analyze market data', 'place predictions', or 'track performance'.	2 / 3
Completeness	Describes what at a high level (predict Kalshi outcomes, compete) 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 some relevant keywords ('Kalshi', 'market', 'predict', 'AI Agent') but misses common variations users might say like 'betting', 'forecasting', 'prediction markets', 'trading', or 'wagering'.	2 / 3
Distinctiveness Conflict Risk	'Kalshi' is a specific platform which helps distinctiveness, but 'AI Agent Prediction Arena' is vague and 'predict market outcomes' could overlap with general trading or forecasting skills.	2 / 3
	Total	7 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides excellent actionability with complete, executable API examples and clear endpoint documentation. However, it suffers from verbosity with motivational content and explanatory sections that don't add value for Claude. The workflow lacks validation checkpoints for error recovery, and the monolithic structure could benefit from splitting non-essential content into separate files.

Suggestions

Remove motivational phrases, emojis in headers, and conversational filler ('Congratulations!', 'Good luck predicting!') to improve token efficiency

Add validation steps after registration (e.g., 'Verify registration: curl agents/me should return your agent info') and after predictions

Move 'Daily Prediction Challenge', 'Human Interaction', and 'Prediction Tips' sections to separate reference files, keeping SKILL.md focused on core API usage

Dimension	Reasoning	Score
Conciseness	The skill contains some unnecessary verbosity like emoji-heavy headers, motivational phrases ('Congratulations!', 'Good luck predicting!'), and explanatory sections that could be trimmed. However, the core API examples are reasonably efficient.	2 / 3
Actionability	Provides fully executable curl commands throughout, complete with headers, JSON payloads, and specific endpoints. The registration, prediction submission, and market browsing examples are all copy-paste ready.	3 / 3
Workflow Clarity	The 'First Steps' section provides a clear sequence, but lacks validation checkpoints. There's no guidance on verifying registration succeeded before proceeding, no error handling in the workflow steps, and the 'Daily Prediction Challenge' flow is more conceptual than procedural.	2 / 3
Progressive Disclosure	References HEARTBEAT.md appropriately, but the main file is quite long (~300 lines) with sections like 'Daily Prediction Challenge', 'Human Interaction', and 'Prediction Tips' that could be separate files. The API reference table is good but inline content is heavy.	2 / 3
	Total	9 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	8 / 11 Passed

Repository: Demerzels-lab/elsamultiskillagent
Commit: 45f9fac

Reviewed: 27 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.