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'.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill optimizing-prompts33
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/skillValidation for skill structure
Discovery
27%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 attempts to explain prompt optimization for LLMs but suffers from truncation and severely misaligned trigger terms. The generic triggers ('optimize', 'performance', 'speed up') would cause frequent conflicts with code/system optimization skills, while missing natural terms users would actually use when seeking prompt optimization help.
Suggestions
Replace generic triggers with domain-specific terms like 'prompt optimization', 'reduce tokens', 'token usage', 'prompt engineering', 'LLM prompt', 'shorten prompt'
Complete the truncated description to fully list all concrete actions the skill performs
Add distinctive qualifiers to prevent conflicts, e.g., 'Use when optimizing prompts or instructions for AI/LLM systems, NOT for code or application performance'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (prompt optimization for LLMs) and some actions (analyzes, identifies areas for simplification, rewrites), but the description is truncated ('conci...') and doesn't provide a complete list of concrete actions. | 2 / 3 |
Completeness | Has a 'what' (optimizes prompts for LLMs) and includes a 'Use when' clause, but the triggers are misaligned with the actual capability. 'Performance' and 'speed up' suggest code optimization, not prompt optimization, creating confusion. | 2 / 3 |
Trigger Term Quality | The trigger terms 'optimize', 'performance', and 'speed up' are overly generic and don't match what users would naturally say when wanting prompt optimization. Users would more likely say 'reduce tokens', 'shorten prompt', 'prompt engineering', or 'LLM prompt'. | 1 / 3 |
Distinctiveness Conflict Risk | The trigger terms 'optimize', 'performance', and 'speed up' would heavily conflict with code optimization, database optimization, or general performance tuning skills. The generic triggers make this highly likely to be incorrectly selected. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate and explains concepts Claude already understands. It lacks any concrete, actionable techniques for prompt optimization—no specific patterns, no token counting methods, no executable examples. The content describes what the skill does rather than teaching Claude how to do it.
Suggestions
Replace abstract descriptions with concrete optimization techniques (e.g., specific patterns for removing redundancy, token counting code, before/after examples with actual token counts)
Remove generic sections like 'Prerequisites', 'Instructions', 'Error Handling', and 'Resources' that provide no skill-specific value
Add executable code examples for measuring token reduction (e.g., using tiktoken library) and validating optimization quality
Consolidate the redundant Overview sections and eliminate explanations of what prompt optimization is—Claude already knows this
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with redundant sections (Overview repeated twice), explains obvious concepts Claude already knows (what prompt optimization is, basic error handling patterns), and includes generic boilerplate that adds no value. | 1 / 3 |
Actionability | No concrete code, commands, or executable guidance. The 'How It Works' section describes what the skill does abstractly rather than providing specific techniques, algorithms, or copy-paste ready examples for prompt optimization. | 1 / 3 |
Workflow Clarity | The examples show a 3-step process (analyze, rewrite, explain), but there are no validation checkpoints, no concrete metrics for measuring token reduction, and no feedback loops for iterating on optimization quality. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Content that could be split (examples, integration details, error handling) is all inline. References to 'prompt-architect' and 'llm-integration-expert' are mentioned but not linked. | 1 / 3 |
Total | 5 / 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.