trading-wisdom
Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.
42
Quality
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xhubed/agent-trading-arena/trading-wisdom/SKILL.mdQuality
Discovery
40%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 suffers from vague, buzzword-heavy language ('core insights', 'institutional knowledge') without explaining concrete capabilities. While it includes a 'Use when' clause, the trigger is overly broad ('any trading decision') and the description fails to specify what actions or analysis the skill actually performs.
Suggestions
Replace vague terms like 'core trading insights' and 'institutional knowledge' with specific actions (e.g., 'Analyzes market conditions, evaluates risk/reward ratios, identifies entry/exit points').
Add natural trigger terms users would actually say, such as 'buy', 'sell', 'trade', 'market analysis', 'position sizing', 'portfolio allocation'.
Specify what unique knowledge from Agent Arena is applied - what strategies, patterns, or decision frameworks does this skill provide?
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'core trading insights' and 'institutional knowledge' without specifying any concrete actions. It doesn't describe what the skill actually does - no verbs indicating specific capabilities. | 1 / 3 |
Completeness | Has a 'Use when' clause ('when making any trading decision'), but the 'what' portion is extremely weak - 'Core trading insights' doesn't explain what the skill actually does or provides. The when clause is present but overly broad. | 2 / 3 |
Trigger Term Quality | Contains 'trading decision' and 'Agent Arena competition' as keywords, but lacks natural variations users might say (e.g., 'buy', 'sell', 'market analysis', 'portfolio', 'stocks'). The trigger terms are somewhat relevant but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | 'Agent Arena competition' provides some distinctiveness, but 'trading decision' and 'institutional knowledge' are generic enough to potentially conflict with other trading or finance-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
14%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 that fails as actionable guidance. While it contains potentially valuable trading insights, the extreme verbosity (repetitive patterns saying the same thing), lack of workflow structure, and absence of clear decision rules make it difficult to use. The content needs aggressive deduplication, a clear decision framework, and proper organization with progressive disclosure.
Suggestions
Deduplicate patterns - consolidate the 4+ 'zero-trade preserves capital' entries into a single pattern with aggregated evidence
Add a decision workflow section: 'When making a trade decision: 1. Identify market regime 2. Check trade frequency threshold 3. Validate against anti-patterns 4. Apply confidence threshold'
Create a quick-reference summary (10-15 lines max) with the top 5 actionable rules, then link to detailed patterns in a separate PATTERNS.md file
Convert insights into executable decision rules, e.g., 'IF market_regime == moderate_bull AND trade_count > 50/day THEN reduce_frequency' rather than descriptive observations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with highly repetitive patterns. Many entries convey the same insight (e.g., 'zero-trade strategies preserve capital' appears 4+ times with minor variations). The content could be condensed to ~50 lines without losing actionable information. | 1 / 3 |
Actionability | Provides concrete insights and patterns with specific numbers (trade counts, PnL figures, confidence levels), but lacks executable code or specific commands. The guidance is descriptive rather than prescriptive - it tells what happened but doesn't provide clear decision rules or implementation steps. | 2 / 3 |
Workflow Clarity | No clear workflow or decision process is defined. The skill is a data dump of observations without sequenced steps for how to apply these learnings when making a trading decision. Missing: decision tree, validation checkpoints, or structured process for using these patterns. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files or structured navigation. All 206 patterns are dumped inline with no organization beyond 'Winning Strategies' vs 'Patterns to Avoid'. No quick-start section or summary that points to detailed materials. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%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
5342bca
- Reviewed
Table of Contents
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.