trading-wisdom

Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

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/trading-wisdom/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 skill encodes genuinely useful, Claude-unknown trading patterns, but presents them as a repetitive, unstructured data dump with no decision workflow, validation steps, or file-based progressive disclosure. It reads as raw observer output rather than a curated skill.

Suggestions

Collapse the redundant Winning Strategies and Patterns to Avoid entries into a deduplicated set of decision rules, moving raw per-pattern data into a reference file.

Add an explicit decision workflow with sequenced steps and validation checkpoints (e.g., 1. classify market regime, 2. apply regime rule, 3. validate risk parameters, 4. execute or abstain).

Split bulk pattern data into references/ files (e.g., PATTERNS.md, AVOID.md) and keep SKILL.md as a concise overview that links out one level deep.

Dimension	Reasoning	Score
Conciseness	The body is a 389-line data dump with heavy redundancy (the zero-trade insight restated ~6 times, many near-duplicate SMA/MACD entries) and pervasive metadata padding, which is noticeably verbose.	2 / 5
Actionability	It offers specific numeric guidance (0.85-0.95 confidence thresholds, 2% equity risk, 2:1 reward, 120-200 trade ranges), but provides no executable code, commands, or a concrete decision procedure, so guidance is concrete yet incomplete.	3 / 5
Workflow Clarity	There is no sequenced decision workflow or validation checkpoints for these risky trading operations, only lists of patterns to follow or avoid, so the sequence is missing and validation is absent.	2 / 5
Progressive Disclosure	Everything is inlined into one monolithic file with no references; the 40+ strategy entries and 50+ avoid entries clearly belong in separate files, leaving minimal effective structure.	2 / 5
	Total	9 / 20 Passed

Description

58%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 cleanly answers what the skill does and includes an explicit 'Use when' clause, but the trigger is overly broad and the capabilities are described generically rather than concretely. It is functional but would benefit from sharper trigger phrasing and named actions.

Suggestions

Replace 'any trading decision' with concrete trigger situations (e.g., 'Use when deciding whether to enter, hold, or close crypto positions, or when assessing market regime').

List concrete actions the skill performs (e.g., 'applies regime-based trade frequency rules, risk validation thresholds, and loss-cutting heuristics') instead of the generic 'apply institutional knowledge'.

Add natural synonyms and asset-class terms users would say (e.g., 'crypto trading', 'position sizing', 'risk management') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('trading insights') and one action ('apply institutional knowledge'), but the action is generic rather than a concrete list of capabilities, matching the anchor for naming the domain with minimal concrete actions.	3 / 5
Completeness	It states both what (core trading insights from Agent Arena) and when ('Use when making any trading decision'), but the 'when' is overly broad rather than tied to concrete trigger phrases, so it does not reach a 5.	4 / 5
Trigger Term Quality	Includes the natural phrase 'making any trading decision', but lacks synonyms and broader trigger variations, so coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	The Agent Arena framing gives it a niche, but the 'any trading decision' trigger is broad enough to overlap with other trading or finance skills, leaving moderate conflict risk.	3 / 5
	Total	13 / 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/trading-wisdom/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.