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'.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

20%

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

The body reads as generic template filler: it describes the skill conceptually and repeats boilerplate sections without concrete, executable guidance or any links to the bundled assets and scripts that actually carry the value. Most of the generic sections could be cut in favor of referencing the real bundle materials.

Suggestions

Cut boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Resources) that add no skill-specific value, and replace them with concrete steps that call the bundled scripts (e.g. how to run prompt_optimizer.py or cost_estimator.py).

Link the existing bundle files inline — point to assets/example_prompts.md for examples and assets/optimization_report_template.md for output structure — so the overview acts as a hub over one-level-deep references.

Add a concrete validation/checkpoint step to the workflow, such as verifying the optimized prompt preserves the original intent before presenting it, to lift workflow clarity above a 2.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate Claude already knows ('The skill produces structured output relevant to the task', 'Invoke this skill when the trigger conditions are met'), matching the verbose/padded anchor rather than lean instruction.	1 / 3
Actionability	It describes what the skill does ('The skill will: 1. Analyze... 2. Rewrite... 3. Provide...') instead of giving executable guidance, and never invokes the bundled scripts or shows commands, so it describes rather than instructs.	1 / 3
Workflow Clarity	'How It Works' provides a three-step sequence (Analyze, Rewrite, Suggest) but it is high-level with no validation checkpoints or error-recovery feedback, matching the steps-present-but-checkpoints-missing anchor.	2 / 3
Progressive Disclosure	The body has clear section headers, but none of the provided bundle files (example_prompts.md, optimization_report_template.md, prompt_template.json, or the scripts) are referenced or linked, and 'Resources' is just generic placeholders, so navigation to existing materials is not signaled.	2 / 3
	Total	6 / 12 Passed

Description

77%

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 is functionally complete with concrete actions and explicit trigger guidance, but is marred by a broken opening clause ('Execute this skill optimizes prompts') and a truncated word ('conci...'), and its trigger terms are narrower than natural usage. Tightening the grammar and broadening trigger coverage would lift it further.

Suggestions

Fix the malformed opening ('Execute this skill optimizes prompts...') into clean third-person prose and complete the truncated 'conci...' to 'concise'.

Broaden trigger terms to include natural variations users actually say, such as 'shorten this prompt', 'reduce token usage', 'make this prompt cheaper', or 'concise prompt'.

Replace the generic 'performance'/'speed up' triggers with prompt-specific phrasing to reduce overlap with unrelated performance-tuning skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt' — matching the highest anchor for naming several specific actions.	3 / 3
Completeness	It answers both what (optimizes/analyzes/rewrites prompts) and when, with an explicit 'Use when optimizing performance. Trigger with phrases like...' clause, satisfying the highest completeness anchor.	3 / 3
Trigger Term Quality	It offers natural triggers ('optimize', 'performance', 'speed up') but misses common variations users would also say for this task such as 'shorten', 'reduce tokens', or 'concise', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	'optimize' points to a distinct niche, but 'performance' and 'speed up' are generic terms that could plausibly fire for unrelated performance skills, so overlap risk remains.	2 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 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.