CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-trading-predictor

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

46

3.27x
Quality

17%

Does it follow best practices?

Impact

95%

3.27x

Average score across 3 eval scenarios

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

27%

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 oversized, monolithic marketing-style document heavy on buzzwords and over-claims (e.g. beating light-speed data transmission). It offers some concrete MCP examples but no executable end-to-end workflow and no progressive disclosure structure.

Suggestions

Cut marketing prose and buzzword capability lists; keep only concrete, executable guidance so every token earns its place.

Add validation/verification checkpoints to the trading workflows (e.g. confirm advantage, sanity-check risk limits before execution) since trade execution is destructive.

Replace undefined pseudocode functions in the sandbox example with complete, runnable code or explicitly justify the placeholders.

Split the long body into well-signaled reference files (e.g. strategies, risk framework) and keep SKILL.md as a concise overview.

DimensionReasoningScore

Conciseness

The ~245-line body is padded with marketing prose ('cutting-edge financial AI', 'pinnacle of algorithmic trading technology') and buzzword capability lists that explain concepts rather than instruct, matching the verbose anchor.

1 / 3

Actionability

It includes concrete MCP tool calls with parameters (e.g. calculateLightTravel with distanceKm/matrixSize), but the Python sandbox example relies on undefined functions like connect_market_feeds() and generate_trading_signals(), leaving guidance incomplete.

2 / 3

Workflow Clarity

Numbered workflows (Daily Trading Cycle, Crisis Management) provide a sequence, but trade execution is a destructive/batch operation with no validation checkpoints or feedback loops, capping this at 2 per the rubric.

2 / 3

Progressive Disclosure

There are no bundle files and the entire skill is a monolithic wall of text with all content inline and no external references or navigation, matching the monolithic anchor.

1 / 3

Total

6

/

12

Passed

Description

7%

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 frontmatter description is boilerplate templated text that names the domain but provides no concrete capabilities, no natural trigger terms, and no usage guidance. It fails to tell a user or Claude when or why to invoke the skill.

Suggestions

Replace the templated description with concrete actions the skill performs (e.g., 'Predicts market movements and executes trades using sublinear temporal-advantage algorithms').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks for high-frequency trading analysis, latency arbitrage, or portfolio risk optimization').

Drop the 'invoke with $agent-trading-predictor' syntax from the description; keep the description focused on what the skill does and when to use it.

DimensionReasoningScore

Specificity

The description only states 'Agent skill for trading-predictor - invoke with $agent-trading-predictor', naming a domain but listing no concrete actions, mirroring the vague 'Helps with documents' anchor.

1 / 3

Completeness

It answers neither 'what does this do' (beyond 'Agent skill for...') nor 'when should Claude use it'; there is no 'Use when...' clause, so both what and when are missing/very weak.

1 / 3

Trigger Term Quality

The only keywords are the slug 'trading-predictor' and the invocation syntax '$agent-trading-predictor'; a user would never naturally say these, fitting the 'technical jargon / no natural keywords' anchor.

1 / 3

Distinctiveness Conflict Risk

It names a specific niche (trading prediction) so it is unlikely to trigger for unrelated skills, but the generic templated phrasing offers no distinct triggers, fitting the 'somewhat specific but could overlap' anchor.

2 / 3

Total

5

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
Reviewed

Table of Contents

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.