risk-management
Risk management rules learned from competition outcomes. Use when sizing positions or setting stop-losses.
55
33%
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 depth in describing what the rules actually entail and could benefit from more concrete capabilities and broader trigger term coverage. The mention of 'competition outcomes' adds some distinctiveness but also introduces vagueness about the actual content.
Suggestions
Expand the specific capabilities beyond just 'sizing positions' and 'setting stop-losses' — e.g., 'Defines max drawdown limits, calculates position sizes based on account risk percentage, sets trailing stop-losses, and manages risk/reward ratios.'
Add more natural trigger terms users might say, such as 'risk per trade', 'drawdown', 'risk/reward ratio', 'max loss', or 'portfolio risk'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (risk management) and mentions two specific actions (sizing positions, setting stop-losses), but doesn't list comprehensive concrete capabilities beyond those two. 'Rules learned from competition outcomes' is vague about what the 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 competition-derived risk management angle is somewhat distinctive, but 'risk management' and 'position sizing' could overlap with general trading or portfolio management skills. The competition context helps but isn't strongly differentiating. | 2 / 3 |
Total | 9 / 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 essentially a raw data dump of statistical observations from trading competitions, not an actionable skill. It lacks concrete implementation guidance (no code, no formulas, no decision trees), contains massive redundancy between the summary table and the expanded rules section, and provides no workflow for how Claude should actually apply these rules when making position sizing or stop-loss decisions. The content would benefit from a complete restructuring focused on actionable decision-making rather than statistical reporting.
Suggestions
Replace the 40-row data table with a concise set of 5-7 deduplicated, actionable rules (e.g., 'In flat/choppy markets, limit to ≤10 trades per 24h' rather than listing multiple overlapping observations), and move the full statistical backing to a separate REFERENCE.md file.
Add a concrete workflow with executable examples: e.g., a step-by-step process for position sizing calculation with code (`max_position = equity * 0.02 / stop_distance`) and a decision tree for trade frequency based on detected market regime.
Include explicit validation checkpoints before trade execution, such as a checklist Claude should verify (risk per trade ≤ 2%, portfolio exposure check, market regime classification) with specific thresholds and formulas.
Remove the redundancy between the summary table and the 'Top Risk Rules' expanded section—either consolidate into one format or clearly differentiate their purposes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose with a massive table of 40 rules, many of which are near-duplicates (e.g., multiple entries for 'Close losing positions proactively', 'Position sizing at 25% equity limit', 'Trade frequency should adapt'). The truncated rule descriptions in the table are unhelpful, and the same rules are then repeated in expanded form in 'Top Risk Rules'. This wastes significant tokens on redundant information. | 1 / 3 |
Actionability | The skill provides statistical observations about past trades but lacks concrete, executable guidance. There are no code examples, specific commands, or step-by-step instructions for how to actually implement position sizing or stop-loss calculations. Rules like 'Trade frequency should adapt to market regime' describe correlations but don't tell Claude what to do. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps for risk management decisions. The content is a data dump of statistical patterns without any process for how to apply them when sizing a position or setting a stop-loss. No validation checkpoints or decision trees are provided for the inherently risky domain of trade execution. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of data with no references to external files and poor organization. The full 40-row table could be in a separate reference file, with SKILL.md containing only the top actionable rules and a clear decision framework. The 'Top Risk Rules' section redundantly repeats data already in the table. | 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.