market-regimes
Market regime detection and regime-specific trading strategies. Use when analyzing market conditions to select appropriate strategy.
61
41%
Does it follow best practices?
Impact
100%
1.56xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xhubed/agent-trading-arena/market-regimes/SKILL.mdQuality
Discovery
67%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 covers the basic what and when, earning full marks on completeness, but lacks specificity in the concrete actions performed and the trigger terms that would help distinguish it from other trading-related skills. It would benefit from listing specific regime types, strategies, and more natural user keywords.
Suggestions
Add specific concrete actions such as 'Identifies bull, bear, and sideways regimes using volatility and trend indicators, then selects momentum or mean-reversion strategies accordingly.'
Expand trigger terms to include natural user phrases like 'bull market', 'bear market', 'volatility regime', 'trend detection', 'market state', or 'regime switching'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (market regime detection, trading strategies) and some actions (analyzing market conditions, selecting strategy), but doesn't list specific concrete actions like what types of regimes are detected, what strategies are applied, or what outputs are produced. | 2 / 3 |
Completeness | Explicitly answers both 'what' (market regime detection and regime-specific trading strategies) and 'when' ('Use when analyzing market conditions to select appropriate strategy'), satisfying the requirement for a 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'market regime', 'trading strategies', and 'market conditions', but misses common user variations such as 'bull/bear market', 'volatility regime', 'trend detection', 'mean reversion', 'momentum', or 'market state'. | 2 / 3 |
Distinctiveness Conflict Risk | While 'market regime detection' is fairly specific, the phrase 'trading strategies' and 'analyzing market conditions' are broad enough to potentially overlap with other trading or market analysis skills. More specific triggers (e.g., regime types, specific indicators) would reduce conflict risk. | 2 / 3 |
Total | 9 / 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 of 32 market regime observations that suffers from extreme redundancy, poor organization, and lack of actionable structure. The same regime types appear multiple times with overlapping advice that could be consolidated into 5-6 distinct entries. While it contains some useful empirical observations (specific PnL data, trade frequency correlations), the lack of a clear decision framework, executable detection logic, and proper content organization makes it difficult to use effectively.
Suggestions
Consolidate duplicate regime entries (e.g., merge all 'Moderate Bull' entries into one with synthesized advice and ranked sub-recommendations) to reduce from 32 entries to ~6 distinct regimes.
Add a concrete regime detection workflow with specific criteria (e.g., 'If all assets move <0.1% → Low Volatility Mixed; if 3+ assets up >2% → Trending Up') as a decision tree or lookup table.
Replace the vague 4-step 'How to Use' section with an actionable flowchart: detect regime → look up strategy → apply specific parameters (trade frequency, position sizing, asset selection) → monitor with specific regime-change triggers.
Move detailed historical observations to a separate REGIME_HISTORY.md file and keep SKILL.md as a concise lookup table with one consolidated entry per regime type.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. There are 32 patterns listed but many are near-duplicates (e.g., 8+ 'Moderate Bull' entries and 10+ 'Trending Up' entries with overlapping advice). The same insights (reduce trading frequency, asset selection matters, zero-trade preserves capital) are repeated many times with slight variations. This could be condensed to ~5-6 regime entries with consolidated advice. | 1 / 3 |
Actionability | The advice is somewhat concrete (specific trade frequencies, specific assets, specific PnL examples) but lacks executable code, commands, or structured decision logic. It describes what worked historically rather than providing a clear actionable framework (e.g., no code for regime detection, no specific entry/exit rules, no API calls). | 2 / 3 |
Workflow Clarity | The 4-step 'How to Use' section is extremely vague ('Identify the current market regime using price action and volatility' - how exactly?). There are no validation checkpoints, no feedback loops for regime change detection, and no clear decision tree for selecting among the many overlapping entries for the same regime type. | 1 / 3 |
Progressive Disclosure | Monolithic wall of 32 pattern entries with no organization beyond flat listing. Duplicate regime names (multiple 'Moderate Bull', 'Trending Up') are not consolidated. No references to external files for detailed strategies, no table of contents, and no clear hierarchy. The confidence guide at the bottom is helpful but insufficient to organize this volume of content. | 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
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.