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

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/packages/ai-ml-engineering-pack/skills/optimizing-prompts/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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

The body is organized into clear sections and illustrates optimization with two before/after examples, but it is dominated by generic template boilerplate and offers no concrete optimization method, nor does it connect to the bundled assets and scripts that already exist.

Suggestions

Replace the boilerplate sections (Instructions, Output, Prerequisites, Resources, Error Handling) with the actual optimization heuristics or a runnable procedure.

Link the existing bundle from the overview — e.g., point to assets/example_prompts.md for more cases and scripts/prompt_optimizer.py for automation.

Add concrete decision criteria for when to apply each rewrite technique so the workflow is actionable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	Mostly structured but padded with generic boilerplate sections — 'The skill produces structured output relevant to the task', 'Project documentation', 'Required dependencies installed' — that add no skill-specific value.	2 / 3
Actionability	The before/after examples give a concrete pattern, but there is no executable technique, code, command, or specific heuristic for how to optimize; the Instructions section is pure abstraction ('Invoke this skill... provide necessary context').	2 / 3
Workflow Clarity	A sequence exists (Analyze → Rewrite → Suggest) and the task is benign so validation is not strictly required, but the steps remain abstract with no concrete checkpoints or decision criteria.	2 / 3
Progressive Disclosure	The body is well-sectioned, but it never references the provided bundle (assets/example_prompts.md, optimization_report_template.md, scripts/prompt_optimizer.py), leaving that material orphaned from the overview.	2 / 3
	Total	8 / 12 Passed

Description

77%Weight 40%Scale 1-3

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 what and when with explicit triggers and several concrete actions, but suffers from a broken opening ('Execute this skill optimizes'), a truncation artifact ('conci...'), and overly generic trigger terms that invite conflict.

Suggestions

Fix the malformed opening so it reads as a clean third-person capability statement (e.g., 'Optimizes prompts for large language models...').

Replace generic triggers like 'performance' and 'speed up' with prompt-specific phrases (e.g., 'reduce token usage', 'shorten this prompt', 'trim prompt cost').

Remove the stray 'conci...' truncation and tighten the description into one or two clear sentences.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'analyzes the prompt', 'identifies areas for simplification and redundancy removal', and 'rewrites the prompt to be more concise' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (optimizes/analyzes/rewrites prompts) and when ('Use when optimizing performance. Trigger with phrases like...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes relevant triggers ('optimize', 'performance', 'speed up') but coverage is thin and 'performance'/'speed up' are generic terms that apply to many skills, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'optimizes prompts' niche is distinct, but the generic triggers 'performance' and 'speed up' create overlap risk with code- or build-performance skills.	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
Path: plugins/packages/ai-ml-engineering-pack/skills/optimizing-prompts/SKILL.md
Commit: 0540a62

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.