risk-management

Risk management rules learned from competition outcomes. Use when sizing positions or setting stop-losses.

0.98x

Quality

33%

Does it follow best practices?

Impact

90%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./data/skills-md/0xhubed/agent-trading-arena/risk-management/SKILL.md

Quality

Content

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 pattern observations rather than an actionable skill document. It suffers from extreme redundancy (near-identical rules repeated many times), lacks any executable code or concrete implementation steps, and provides no clear workflow for applying the rules. The statistical observations could be valuable but need to be distilled into concise, actionable guidance with clear decision processes.

Suggestions

Deduplicate the rules table by consolidating similar rules (e.g., merge the 6 variants of 'Close losing positions proactively' into one rule with the best-supported parameters), reducing the table to ~10-15 unique rules.

Add a concrete workflow section with steps like: '1. Check market regime (trending/choppy) → 2. Set max trade frequency from regime table → 3. Calculate position size: `size = equity * 0.02 / stop_distance` → 4. Validate risk limits before entry → 5. Set stop-loss at calculated level'.

Replace the 'General Guidelines' section with specific, parameterized rules (e.g., 'Stop-loss = entry_price ± ATR(14) * 1.5' or equivalent concrete formulas) that Claude can directly implement.

Remove the 'Top Risk Rules' expanded section entirely since it duplicates the table, or replace the table with a concise summary and keep only the top 5 rules with actionable implementation details.

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). The 'Top Risk Rules' section then re-states the same information from the table in expanded form. This could be condensed to perhaps 20% of its current size.	1 / 3
Actionability	The skill provides observations and statistics but almost no executable guidance. There are no code snippets, no concrete commands, no specific formulas for position sizing, 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 them). 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 content is a data dump of statistical observations without any step-by-step process for how to size a position, set a stop-loss, or validate a trade. For a skill involving destructive financial operations (position sizing, trade execution), the complete absence of validation checkpoints or decision flowcharts is a significant gap.	1 / 3
Progressive Disclosure	The content is a monolithic wall of repetitive data with no structure that aids navigation. The massive table, the expanded top rules, and the general guidelines are all at the same level with no clear hierarchy. There are no references to supporting files, and the content that could be separated (e.g., detailed per-rule statistics) is all inline.	1 / 3
	Total	4 / 12 Passed

Description

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 identifiable domain, but lacks specificity about what the rules actually entail beyond position sizing and stop-losses. The competition provenance is interesting but vague—it doesn't clarify what kind of competition or what specific insights were derived. Trigger term coverage is adequate but could be broader to capture more user query variations.

Suggestions

Add more specific concrete actions, e.g., 'Applies max drawdown limits, calculates position sizes based on account risk percentage, sets trailing stop-losses' to improve specificity.

Expand trigger terms to include common variations like 'risk/reward ratio', 'max loss', 'drawdown', 'portfolio risk', 'risk per trade' to improve matching.

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 provenance adds some uniqueness but the triggers themselves are fairly broad within trading contexts.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: c7b7905

Reviewed: about 6 hours ago

Table of Contents

Discovery Implementation Validation

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.