optimizing-prompts
Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci... Use when optimizing performance. Trigger with phrases like 'optimize', 'performance', or 'speed up'.
33
29%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/packages/ai-ml-engineering-pack/skills/optimizing-prompts/SKILL.mdQuality
Discovery
59%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 covers the basics of what the skill does and includes an explicit 'Use when' clause, but suffers from overly generic trigger terms that would cause frequent false matches with unrelated optimization skills. The truncation ('more conci...') suggests a formatting issue, and the trigger phrases like 'optimize' and 'performance' are far too broad to reliably select this skill over others. The opening 'Execute this skill' is awkward phrasing that doesn't follow standard third-person voice conventions.
Suggestions
Replace generic trigger terms ('optimize', 'performance', 'speed up') with domain-specific ones like 'optimize prompt', 'reduce tokens', 'prompt engineering', 'shorten prompt', 'token usage', 'API costs'.
Fix the truncated description and remove the 'Execute this skill' prefix; use clean third-person voice like 'Optimizes LLM prompts by removing redundancy and simplifying language to reduce token usage and API costs.'
Add more distinctive scope boundaries in the 'Use when' clause, e.g., 'Use when the user wants to optimize, shorten, or reduce the cost of LLM prompts or system instructions. Not for code optimization or general performance tuning.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (prompt optimization for LLMs) and lists some actions (analyzes the prompt, identifies areas for simplification and redundancy removal, rewrites the prompt), but the truncation ('more conci...') cuts off detail and the actions are somewhat generic rather than listing multiple distinct concrete capabilities. | 2 / 3 |
Completeness | The description explicitly answers both 'what does this do' (optimizes prompts for LLMs to reduce token usage, lower costs, improve performance by analyzing and rewriting) AND 'when should Claude use it' with a 'Use when...' clause and explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'optimize', 'performance', 'token usage', 'lower costs', and 'prompts', but the trigger terms listed ('optimize', 'performance', 'speed up') are overly generic and could match many unrelated skills. Missing natural terms like 'reduce tokens', 'prompt engineering', 'shorten prompt', 'cheaper API calls'. | 2 / 3 |
Distinctiveness Conflict Risk | The trigger terms 'optimize', 'performance', and 'speed up' are extremely generic and would conflict with many other skills (code optimization, database performance, image optimization, etc.). The description doesn't sufficiently narrow the scope to prompt optimization specifically in its trigger guidance. | 1 / 3 |
Total | 8 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely generic boilerplate with no actionable, specific content for prompt optimization. It explains what it does in abstract terms rather than providing concrete techniques, rules, patterns, or executable examples. Multiple sections (Prerequisites, Instructions, Output, Error Handling, Resources) are placeholder text with no real content.
Suggestions
Replace the abstract 'How It Works' section with concrete, specific prompt optimization techniques (e.g., remove filler words, consolidate redundant instructions, use structured output formats) with before/after examples showing token counts.
Remove all generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Resources) that contain no skill-specific information.
Add a concrete checklist or decision tree for prompt optimization: specific patterns to look for (redundancy, over-qualification, unnecessary politeness) with executable transformation rules.
Provide real, measurable examples with actual token counts showing the reduction, rather than narrative descriptions of what 'the skill will' do.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with content Claude already knows. The 'Overview' restates the title, 'How It Works' describes obvious steps, and sections like 'Prerequisites', 'Instructions', 'Output', 'Error Handling', and 'Resources' are generic boilerplate with no actionable specifics. The entire skill could be reduced to a fraction of its size. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific techniques for prompt optimization. The examples merely describe what 'the skill will' do in vague narrative form rather than providing actual optimization rules, patterns, or executable steps. Sections like 'Instructions' and 'Error Handling' are completely generic placeholders. | 1 / 3 |
Workflow Clarity | The 'How It Works' section lists three abstract steps (analyze, rewrite, suggest) with no concrete methodology, no validation checkpoints, and no feedback loops. The 'Instructions' section is a generic 4-step placeholder that could apply to any skill. There is no clear, actionable workflow for actually performing prompt optimization. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no bundle files, no references to external resources, and no meaningful structure. Multiple sections contain generic filler content that adds no value. The 'Integration' and 'Resources' sections reference things that don't exist in the bundle. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
4801da6
- 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.