agent-trading-predictor

Agent skill for trading-predictor - invoke with $agent-trading-predictor

3.27x

Quality

31%

Does it follow best practices?

Impact

95%

3.27x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-trading-predictor/SKILL.md

Quality

Content

42%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 content is a verbose, buzzword-heavy monolith with concrete MCP code examples but undefined helper functions and no validation checkpoints in its trading workflows. It would benefit from trimming marketing language, making examples executable, and splitting large reference sections into bundle files.

Suggestions

Cut marketing language ('cutting-edge', 'pinnacle', 'exploits temporal computational advantages') and explanatory padding to respect Claude's intelligence and the context budget.

Make code examples executable by defining or stubbing the referenced helpers (connect_market_feeds, calculate_temporal_lead, portfolioRiskMatrix, marketSignalVector) or replace them with real tool calls.

Add explicit validation/feedback-loop steps to the Daily Trading Cycle and Crisis Management workflows (e.g. verify signal, confirm risk limits, validate execution result before proceeding).

Dimension	Reasoning	Score
Conciseness	The body is padded with buzzword-heavy framing ('cutting-edge financial AI', 'pinnacle of algorithmic trading technology', 'exploits temporal computational advantages') and long bullet lists that add little executable value, fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	It provides concrete MCP tool calls with real parameters, but several examples rely on undefined helpers (connect_market_feeds, calculate_temporal_lead, portfolioRiskMatrix), so they are illustrative rather than fully executable, matching 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	Numbered workflows (Daily Trading Cycle, Crisis Management) exist but lack validation checkpoints or feedback loops; because trading execution is a destructive/batch operation, the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one ~250-line file with section headers, but API reference, strategies, and risk frameworks that should live in separate files are all inline, matching 'some structure but could be better organized; content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

20%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 boilerplate that merely labels the skill and tells the model how to invoke it, without stating what it actually does or when to use it. It fails on specificity, trigger quality, completeness, and distinctiveness.

Suggestions

Replace the boilerplate with a concrete capability statement, e.g. 'Predicts and executes financial trades using sublinear temporal-advantage algorithms for high-frequency, latency-arbitrage, and portfolio-optimization tasks.'

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user requests high-frequency trading strategies, latency arbitrage analysis, or real-time portfolio risk optimization.'

Include natural trigger terms users would actually say (trades, market prediction, arbitrage, portfolio optimization) rather than only the internal skill name.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for trading-predictor - invoke with $agent-trading-predictor' names only the domain and contains zero concrete actions or capabilities, matching the 'Entirely vague; no concrete actions' anchor.	1 / 5
Completeness	It offers a vague 'what' (an agent skill for trading-predictor) and no 'when'/trigger guidance at all, matching 'Has a vague what and no when'; the missing 'Use when...' clause also caps completeness at 3, and this is below that.	2 / 5
Trigger Term Quality	The only keyword is the literal skill name '$agent-trading-predictor'; there are no natural phrases a user would say (e.g. 'predict trades', 'market analysis'), fitting 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	The templated 'Agent skill for X - invoke with $X' phrasing is generic boilerplate reused across many agent skills, giving it high overlap risk, matching 'Very broad; high overlap risk'.	2 / 5
	Total	7 / 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: ruvnet/ruflo
Path: .agents/skills/agent-trading-predictor/SKILL.md
Commit: fa13ee4

Reviewed: about 4 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.