prompt-optimization

Applies prompt repetition to improve accuracy for non-reasoning LLMs

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent-skills/prompt-optimization/SKILL.md

Quality

Content

50%

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

The content is well-sectioned and provides some concrete configuration, but it leans on theoretical explanation and redundancy, offers no executable agent workflow, and references a documentation file that does not exist in the bundle.

Suggestions

Create the referenced references/prompt-repetition.md or remove the dangling reference so progressive disclosure is honest.

Trim the theoretical "How It Works" explanation and de-duplicate the task lists shared between "When to Activate" and "Agent Instructions".

Provide an explicit, verifiable workflow or confirmation step so it is clear when/how prompt repetition has been applied.

Dimension	Reasoning	Score
Conciseness	The body is mostly organized and efficient, but includes theoretical explanation ("bidirectional attention within the parallelizable prefill stage") and redundant trigger lists repeated across "When to Activate" and "Agent Instructions" that could be tightened.	2 / 3
Actionability	It gives concrete env-var configuration and a before/after prompt example, but the core operation is automatic ("No action needed from you") with no executable code or commands for the agent to run.	2 / 3
Workflow Clarity	The single automatic action is stated, but guidance is scattered across multiple sections rather than a crisp sequence, and there is no verification that repetition was actually applied.	2 / 3
Progressive Disclosure	Sections are reasonably organized, but the body cites "references/prompt-repetition.md" for full documentation while no references/ directory exists, and all content is inline rather than appropriately split.	2 / 3
	Total	8 / 12 Passed

Description

35%

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 states a clear single action and target domain but relies on technical jargon rather than natural user triggers and omits any explicit "Use when" guidance. It is adequate but not exemplary.

Suggestions

Add a "Use when..." clause naming natural trigger phrases (e.g., running unit tests, linting, parsing structured data) so users and Claude know when to invoke it.

Replace jargon like "non-reasoning LLMs" with user-facing terms and include common variations.

List multiple concrete capabilities rather than the single action "Applies prompt repetition" to raise specificity.

Dimension	Reasoning	Score
Specificity	The phrase "Applies prompt repetition" names a concrete action and domain, but lists only a single action rather than the multiple specific actions the top anchor requires.	2 / 3
Completeness	It states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like "prompt repetition" and "non-reasoning LLMs" are technical jargon a user would not naturally say; there are no common natural-language variations present.	1 / 3
Distinctiveness Conflict Risk	The niche (repetition for non-reasoning models) is fairly specific, but the absence of explicit triggers means it could still overlap with other accuracy-improvement skills.	2 / 3
	Total	7 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: asklokesh/loki-mode
Path: agent-skills/prompt-optimization/SKILL.md
Commit: 08a09b1

Reviewed: about 13 hours 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.