trading-wisdom

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

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

The body is a verbose, auto-generated catalog of trading observations with no executable guidance, no decision workflow, and no progressive disclosure, scoring at the floor across all content dimensions.

Suggestions

Distill the 200+ entries into a small set of regime-conditioned decision rules and move the raw pattern log to a bundled reference file linked from SKILL.md.

Add a concrete decision workflow (assess regime -> choose trade frequency -> size position -> validate) with explicit checkpoints instead of listing observations.

Remove redundant near-duplicate entries and drop per-entry timestamp/sample metadata from the main body to cut token load.

Dimension	Reasoning	Score
Conciseness	The body is a ~390-line dump of repetitive, near-duplicate pattern entries (e.g. multiple 'Zero-trade strategy preserves capital' and 'Index fund strategy' listings) padded with time-sensitive metadata (dates, confidence %, sample counts), matching the verbose/padded anchor.	1 / 3
Actionability	It contains no executable code, commands, or specific decision rules; it describes empirical observations ('Zero-trade strategy in moderate bull markets preserves capital') rather than instructing Claude what to do, matching the 'describes rather than instructs' anchor.	1 / 3
Workflow Clarity	There is no multi-step process, sequencing, or validation checkpoints for applying these patterns to a trading decision; the content is a flat catalog with no workflow, so it does not reach even the steps-present anchor.	1 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire 206-pattern knowledge base is crammed inline as a monolithic wall of text with no file references or navigation, matching the monolithic-text anchor.	1 / 3
	Total	4 / 12 Passed

Description

57%

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 has an explicit trigger and a clear, distinctive niche, but its capabilities are stated abstractly ('apply institutional knowledge') rather than as concrete actions, leaving specificity and completeness at the mid anchor.

Suggestions

Replace 'apply institutional knowledge' with concrete actions the skill performs, e.g. 'identify market regime, select trade frequency, and decide when to stay flat'.

Broaden trigger coverage beyond 'any trading decision' to natural phrases users would say, such as 'placing trades', 'sizing positions', or 'deciding whether to trade'.

Dimension	Reasoning	Score
Specificity	Names the trading domain ('Core trading insights learned from Agent Arena competition') but the only action phrased is 'apply institutional knowledge', which is vague rather than a list of concrete actions, so it lands at the domain-named-but-incomplete anchor rather than 3.	2 / 3
Completeness	It has an explicit 'Use when...' clause and states a function, but the 'what' is vague ('apply institutional knowledge') rather than clearly concrete, so it does not clearly answer both what and when at the top anchor.	2 / 3
Trigger Term Quality	The natural trigger 'making any trading decision' is relevant, but coverage is thin with no common variations (e.g. 'placing a trade', 'position sizing', 'market regime'), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific ('trading decision' / 'Agent Arena competition') with a distinct trigger unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days 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.