trading-wisdom
Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.
27
8%
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
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 vague and lacks concrete actions, relying on buzzwords like 'institutional knowledge' and 'core trading insights' without specifying what the skill actually does. The trigger scope is far too broad ('any trading decision'), making it both unhelpful for skill selection and likely to conflict with other trading-related skills.
Suggestions
Replace vague language with specific concrete actions the skill performs, e.g., 'Applies position sizing rules, risk management thresholds, and market regime detection strategies learned from Agent Arena competition.'
Narrow the 'Use when' clause to specific scenarios rather than 'any trading decision', e.g., 'Use when evaluating trade entries/exits, sizing positions, or assessing market conditions.'
Add natural trigger terms users would actually say, such as 'risk management', 'position sizing', 'trade signals', 'market analysis', or whatever specific capabilities the skill 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 'when' clause ('Use when making any trading decision'), but the 'what' is so vague that the completeness is undermined. The 'when' clause is present but overly broad. | 2 / 3 |
Trigger Term Quality | The trigger terms are overly generic ('trading decision', 'institutional knowledge') and unlikely to match natural user queries. Terms like 'Agent Arena competition' are highly specific jargon that users wouldn't naturally say, while 'trading decision' is too broad. | 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 |
Implementation
0%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 is extremely verbose with massive redundancy (the same insight about zero-trade strategies or overtrading appears 5-10 times with slight variations), provides no executable guidance or decision framework, and lacks any workflow structure. The content would benefit enormously from consolidation into a concise set of principles with a clear decision tree.
Suggestions
Consolidate the ~30 redundant patterns into 5-7 distinct, concise principles (e.g., 'In non-trending markets, minimize trade frequency' instead of 12 variations of the same observation)
Add a concrete decision workflow: e.g., '1. Identify market regime (bull/bear/flat) → 2. Select strategy based on regime → 3. Apply position sizing rules → 4. Validate entry criteria → 5. Set exit conditions'
Move detailed pattern data (agent names, specific PnL figures, sample counts) to a separate PATTERNS.md reference file, keeping only the synthesized rules in SKILL.md
Replace the observation-style entries with actionable if/then rules, e.g., 'IF market regime is moderate bull AND no strong directional conviction THEN hold zero positions' rather than describing what happened historically
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with massive repetition. Many patterns say essentially the same thing (e.g., multiple near-identical 'zero-trade strategy preserves capital' entries, multiple 'extreme overtrading leads to losses' entries). The content could be condensed to ~20% of its size without losing information. Agent-specific details (llama4_scout, skill_aware_oss) are implementation artifacts that waste tokens. | 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 trees or algorithms to follow. It reads as a post-mortem analysis rather than actionable instructions for making trading decisions. | 1 / 3 |
Workflow Clarity | There is no workflow, decision process, or sequenced steps. The skill is a flat list of observations with no clear procedure for how to apply these insights when making a trading decision. No validation checkpoints or decision framework is provided. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All 206 patterns are dumped inline with no hierarchy or organization beyond 'Winning Strategies' and 'Patterns to Avoid'. Many entries are truncated in their headers, making navigation difficult. The content desperately needs summarization with details in separate files. | 1 / 3 |
Total | 4 / 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
f772de4
- 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.