risk-management

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

0.98x

Quality

47%

Does it follow best practices?

Impact

90%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

32%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an auto-generated data dump of redundant risk rules with concrete but thin actionable guidelines and no progressive disclosure or validation workflow. It would benefit substantially from de-duplication, moving the rule table to a reference file, and adding an explicit validation step.

Suggestions

De-duplicate the rule table and move the bulk statistics into a separate reference file (e.g. references/rules.md), keeping only the top actionable rules inline in SKILL.md.

Add an explicit pre-trade validation workflow with a checkpoint (e.g. 'Validate risk per trade within limits → only then place the order → re-check after fill'), since the skill governs destructive real-money operations.

Quarantine time-sensitive fields (Last updated, First identified dates, sample counts) in a clearly marked metadata/deprecated section so they do not consume token budget on every read.

Dimension	Reasoning	Score
Conciseness	A 40-row table of truncated, near-duplicate rules plus a 'Top Risk Rules' section that re-states several table entries is noticeably padded, and time-sensitive dates ('Last updated', 'First identified') add token cost without being quarantined in a deprecated section.	2 / 5
Actionability	The General Guidelines give concrete directives ('Never risk more than 2% of equity', 'Use stop-losses on every position', '25% equity limit'), but the bulk of the body is observational statistics rather than executable instructions, leaving key application steps implicit.	3 / 5
Workflow Clarity	There is no sequenced multi-step workflow and no validation checkpoints; for a trading/risk skill involving effectively destructive (real-money) operations, the absence of any validate-then-proceed feedback loop caps clarity low.	2 / 5
Progressive Disclosure	All content is inlined in SKILL.md with no references; the large rules table is exactly the kind of bulk data that belongs in a separate file, and there are no signaled one-level-deep references to navigate to.	2 / 5
	Total	9 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 concise and answers both what and when with a clear trigger clause, but it lists only two actions and lacks synonyms for broader trigger coverage. It is distinct within the trading domain.

Dimension	Reasoning	Score
Specificity	Names the domain ('Risk management rules learned from competition outcomes') and two concrete actions ('sizing positions', 'setting stop-losses'), but coverage is not comprehensive — only two actions are listed.	3 / 5
Completeness	Clearly states what ('Risk management rules learned from competition outcomes') and an explicit 'when' ('Use when sizing positions or setting stop-losses'), though the trigger could list more concrete phrases.	4 / 5
Trigger Term Quality	'sizing positions' and 'stop-losses' are natural terms a trader would say, but common synonyms and variations (position sizing, risk per trade, drawdown, risk/reward) are missing.	3 / 5
Distinctiveness Conflict Risk	Trading risk management with stop-loss/position-sizing triggers is a clear niche with minimal conflict risk, though it could overlap slightly with general trading skills.	4 / 5
	Total	14 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Path: data/skills-md/0xhubed/agent-trading-arena/risk-management/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.