agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-trading-predictor43
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 95%
↑ 3.27xAgent success when using this skill
Validation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It functions only as a label and invocation instruction rather than a functional description. Claude would have no basis for selecting this skill appropriately since there's no information about capabilities, use cases, or trigger conditions.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Analyzes market data, generates trading signals, predicts price movements for stocks and cryptocurrencies')
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about stock predictions, market forecasts, trading recommendations, or price analysis')
Remove the invocation instruction from the description field - this belongs in usage documentation, not the selection-focused description
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for trading-predictor' is completely abstract and doesn't describe what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command, not functional information. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'trading-predictor' which is a technical/internal name, not natural language users would say. Missing terms like 'stock', 'market', 'predict', 'forecast', 'trade', etc. | 1 / 3 |
Distinctiveness Conflict Risk | While 'trading-predictor' sounds specific, the lack of any actual description means Claude cannot distinguish when to use this vs any other trading or prediction-related skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose and reads more like marketing material than actionable guidance. While it contains some useful MCP tool examples, the content is padded with unnecessary explanations, incomplete pseudocode, and lacks the validation checkpoints critical for financial trading operations. The document would benefit from aggressive trimming and restructuring into a concise overview with references to detailed documentation.
Suggestions
Reduce content by 80%: Remove marketing language, concept explanations, and keep only the essential MCP tool invocation patterns with one complete example per use case
Make code examples fully executable: Replace undefined functions like 'connect_market_feeds()' with actual implementations or remove them entirely
Add explicit validation checkpoints: For financial operations, include error handling, trade confirmation validation, and rollback procedures
Split into multiple files: Create separate RISK.md, INTEGRATION.md, and EXAMPLES.md files, keeping SKILL.md as a concise overview with clear navigation links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive marketing language ('cutting-edge', 'pinnacle of algorithmic trading technology'), unnecessary explanations of concepts Claude knows, and padded sections that don't add actionable value. The document is ~250 lines when it could be under 50. | 1 / 3 |
Actionability | Contains code examples with specific MCP tool calls, but many examples are pseudocode or incomplete (e.g., 'connect_market_feeds()', 'calculate_temporal_lead()' are undefined). The JavaScript examples show tool invocation patterns but lack complete, executable implementations. | 2 / 3 |
Workflow Clarity | Lists workflows like 'Daily Trading Cycle' and 'Crisis Management' but they are high-level descriptions without validation checkpoints or error handling. No feedback loops for failed trades or system errors despite dealing with high-risk financial operations. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including detailed integration patterns, risk frameworks, and performance metrics that should be split into separate reference documents. | 1 / 3 |
Total | 6 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.