prompt-optimizer

Prompt 工程技能 - 优化交易策略提示词、LLM 指令、系统提示

1.52x

Quality

45%

Does it follow best practices?

Impact

87%

1.52x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/prompt-optimizer/SKILL.md

Quality

Discovery

32%

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 identifies a specific niche (prompt engineering for trading strategies) but suffers from missing explicit trigger guidance ('Use when...'), which significantly limits Claude's ability to know when to select this skill. The Chinese-language description provides some domain keywords but lacks comprehensive action verbs and natural user trigger terms.

Suggestions

Add an explicit 'Use when...' clause specifying triggers like 'when user asks to write, optimize, or debug prompts for trading bots, algorithmic trading, or financial AI systems'

Include more concrete action verbs such as 'writes', 'debugs', 'tests', 'refines', 'evaluates' to clarify what operations this skill performs

Add common user trigger terms in both Chinese and English, such as 'prompt优化', 'AI提示词', 'prompt debugging', 'trading bot prompts'

Dimension	Reasoning	Score
Specificity	Names the domain (prompt engineering) and lists some actions (优化交易策略提示词、LLM 指令、系统提示 - optimizing trading strategy prompts, LLM instructions, system prompts), but lacks comprehensive concrete actions like 'write', 'debug', 'test', or 'refine'.	2 / 3
Completeness	Only describes 'what' (prompt engineering for trading strategies) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains some relevant keywords like 'Prompt 工程', 'LLM 指令', '系统提示', and '交易策略提示词', but missing common variations users might say like 'prompt writing', 'prompt optimization', 'AI prompts', or English equivalents.	2 / 3
Distinctiveness Conflict Risk	The combination of 'prompt engineering' with '交易策略' (trading strategy) provides some specificity, but 'LLM 指令' and '系统提示' are generic enough to potentially overlap with general prompt engineering or coding assistance skills.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

The skill provides highly actionable prompt engineering guidance with excellent executable examples and templates for quantitative trading. However, it suffers from being overly long and monolithic, lacking proper content organization across files. The workflow sections would benefit from explicit validation steps for testing prompt effectiveness.

Suggestions

Split detailed prompt templates (market analysis, risk assessment, strategy optimization) into separate reference files like TEMPLATES.md or EXAMPLES.md

Add explicit validation checkpoints to the prompt testing workflow, e.g., 'If accuracy < 80%, review examples and retry'

Condense the introductory sections and remove explanatory text that Claude already understands about prompt engineering concepts

Add a quick-start section at the top with the most essential pattern (CO-STAR framework) before diving into detailed templates

Dimension	Reasoning	Score
Conciseness	The skill contains useful content but is verbose with extensive template examples that could be condensed. Some explanatory text like '此技能指导 Claude 使用经过验证的 Prompt 工程技巧' is unnecessary padding.	2 / 3
Actionability	Provides fully executable Python code examples, complete prompt templates with JSON output schemas, and copy-paste ready examples for market analysis, risk assessment, and strategy optimization.	3 / 3
Workflow Clarity	Multi-step processes are listed (Chain of Thought, optimization steps) but lack explicit validation checkpoints. The testing section mentions test_prompt() but doesn't show how to validate prompt outputs or handle failures.	2 / 3
Progressive Disclosure	This is a monolithic 400+ line document with no references to external files. Content like the detailed prompt templates, JSON schemas, and best practices sections could be split into separate reference files for better organization.	1 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Lingjie-chen/MT5
Commit: 3069d33

Reviewed: 26 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.