trading-wisdom

Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.

Quality

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./data/skills-md/0xhubed/agent-trading-arena/trading-wisdom/SKILL.md

Quality

Content

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

This skill is an auto-generated data dump of trading competition observations, not an actionable skill document. It suffers from extreme redundancy (the same insights repeated dozens of times with slight variations), lacks any executable guidance or decision workflow, and presents hundreds of lines of flat pattern listings without meaningful organization. The content would need fundamental restructuring to serve as useful guidance for trading decisions.

Suggestions

Consolidate redundant patterns into 5-7 core principles with a clear decision flowchart (e.g., 'Step 1: Assess market regime → Step 2: Determine appropriate trade frequency → Step 3: Validate signals before entry')

Replace the flat list of 30+ winning strategies with a concise summary table organized by market regime (bull/bear/flat) with specific actionable rules for each

Add concrete, executable guidance: specific entry/exit criteria, position sizing rules, and a clear decision tree rather than historical observations

Move detailed pattern evidence to a separate reference file and keep SKILL.md to a lean overview of the top 5-10 highest-confidence, non-redundant insights

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 400+ lines with massive redundancy. Many patterns repeat the same insight (zero-trade preserves capital appears 5+ times, overtrading is bad appears 10+ times). The detailed agent names, exact PnL figures, and repetitive pattern entries bloat the content enormously. Most of this could be condensed to 20% of its current size.	1 / 3
Actionability	The content describes observations and historical patterns but provides no concrete, executable guidance. There are no code examples, no specific commands, no decision flowcharts, and no clear instructions for how to actually implement these insights in trading decisions. It reads as a data dump rather than actionable instructions.	1 / 3
Workflow Clarity	There is no workflow, decision tree, or sequenced process for making trading decisions. The content is a flat list of observations without any structured process for how to apply them. A trading skill should have clear steps like: assess market regime → determine trade frequency → validate signals → execute, but none of this exists.	1 / 3
Progressive Disclosure	The content is a monolithic wall of repetitive patterns with no structure beyond flat sections. The 'Winning Strategies' and 'Patterns to Avoid' sections each contain 30+ entries that could be categorized, summarized, or split into referenced files. There's no hierarchy or navigation to help find relevant information quickly.	1 / 3
	Total	4 / 12 Passed

Description

17%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too vague and abstract to be useful for skill selection. It fails to specify what concrete actions or insights the skill provides, relying on buzzwords like 'institutional knowledge' and 'core trading insights.' The overly broad trigger ('any trading decision') would cause conflicts with other trading-related skills and provides no meaningful differentiation.

Suggestions

Replace 'core trading insights' with specific concrete actions the skill performs, e.g., 'Applies position sizing rules, risk management thresholds, and entry/exit signal patterns learned from Agent Arena competition.'

Narrow the 'Use when' clause to specific scenarios instead of 'any trading decision', e.g., 'Use when evaluating trade entries, setting stop-losses, sizing positions, or reviewing portfolio risk.'

Add distinct trigger terms that users would naturally say, such as 'risk management', 'position sizing', 'stop-loss', 'trade signals', or whatever specific capabilities the skill actually provides.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'core trading insights' and 'institutional knowledge' without listing any concrete actions. It does not specify what the skill actually does (e.g., analyze positions, calculate risk, generate signals).	1 / 3
Completeness	It has a weak 'what' (trading insights) and does include a 'Use when' clause ('making any trading decision'), but the 'what' is so vague that the completeness is undermined. The 'Use when' clause is present but overly broad.	2 / 3
Trigger Term Quality	The trigger terms are overly generic ('trading decision', 'institutional knowledge') and lack natural keywords a user would say. Terms like 'Agent Arena competition' are too niche and specific to a context rather than user intent.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — 'any trading decision' would conflict with virtually any other trading-related skill. There is no clear niche or distinct trigger that separates this from other trading skills.	1 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: c7b7905

Reviewed: about 4 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.