risk-management
Risk management rules learned from competition outcomes. Use when sizing positions or setting stop-losses.
57
37%
Does it follow best practices?
Impact
90%
0.98xAverage 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/risk-management/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 is functional with a clear 'Use when' clause and some specific trigger terms, but it lacks detail about what the rules actually entail and could benefit from more concrete capability descriptions. The domain is reasonably distinct but the vague reference to 'rules learned from competition outcomes' doesn't help Claude understand the skill's actual content.
Suggestions
Expand the specificity by listing concrete rules or actions, e.g., 'Applies position sizing formulas, calculates optimal stop-loss levels, enforces maximum drawdown limits'.
Add more natural trigger terms users might say, such as 'risk/reward ratio', 'max drawdown', 'portfolio allocation', 'risk per trade', or 'money management'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (risk management) and mentions two specific actions (sizing positions, setting stop-losses), but doesn't list concrete capabilities beyond that. 'Rules learned from competition outcomes' is vague about what those rules actually are. | 2 / 3 |
Completeness | Clearly answers both 'what' (risk management rules from competition outcomes) and 'when' (use when sizing positions or setting stop-losses) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant natural keywords like 'position sizing', 'stop-losses', and 'risk management' that users might say, but misses common variations like 'risk/reward', 'drawdown', 'portfolio risk', 'max loss', or 'risk per trade'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'competition outcomes' and specific trading risk concepts (position sizing, stop-losses) provides some distinctiveness, but 'risk management' is broad enough to potentially overlap with other finance or trading-related skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a raw data dump of statistical observations from trading competitions, presented with extreme redundancy (many near-duplicate rules) and no actionable implementation guidance. It lacks executable code, clear decision workflows, and concrete instructions for how Claude should actually apply these rules when sizing positions or setting stop-losses. The content would benefit enormously from deduplication, consolidation into clear actionable rules, and addition of concrete implementation steps.
Suggestions
Deduplicate the rules table by consolidating similar entries (e.g., merge the 6 variants of 'Close losing positions proactively' into one rule with aggregated statistics), reducing the table from 40 rows to ~10-12 distinct rules.
Add a concrete workflow for trade entry: e.g., '1. Identify market regime (trending/flat/choppy) → 2. Set max trade frequency based on regime → 3. Calculate position size (max 2% equity risk) → 4. Validate risk/reward ratio ≥ 2:1 → 5. Set stop-loss at [specific calculation] → 6. Execute only if all checks pass.'
Provide executable code or pseudocode for key calculations like position sizing (e.g., `position_size = (equity * 0.02) / (entry_price - stop_loss_price)`) and stop-loss placement.
Remove the 'Top Risk Rules' expanded section which duplicates the table data, or replace the table with the expanded section — don't include both.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose with massive redundancy. The 40-row table repeats near-identical rules (e.g., 'Close losing positions proactively' appears 6 times, 'Position sizing at 25% equity limit' appears 4 times, 'Validate risk per trade explicitly' appears 4 times). The 'Top Risk Rules' section then repeats the same information from the table in expanded form. This could be condensed to perhaps 20% of its current size by deduplicating and consolidating. | 1 / 3 |
Actionability | The skill provides statistical observations about past trades but lacks concrete, executable guidance. There are no code examples, no specific commands, no algorithms for position sizing calculations, and no clear instructions on how to implement these rules. The 'General Guidelines' section is vague ('use stop-losses on every position' without specifying how to calculate stop-loss levels). It describes patterns rather than instructing actions. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequenced process for applying these risk management rules. The skill doesn't define when to check which rules, how to combine conflicting signals, or what validation steps to take before executing a trade. For a skill involving financial risk (destructive operations on capital), the absence of any feedback loops or decision trees is a significant gap. | 1 / 3 |
Progressive Disclosure | The content has some structural organization with sections (Core Principles table, Top Risk Rules details, General Guidelines, Confidence Guide), but the massive table and repeated detail sections create a monolithic feel. There are no references to external files, which is acceptable given no bundle, but the inline content desperately needs consolidation or splitting. The confidence guide at the end is a useful organizational element. | 2 / 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
25d5403
- 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.