llm-application-dev-prompt-optimize

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Quality

30%

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 ./skills/llm-application-dev-prompt-optimize/SKILL.md

The canonical home for this skill is llm-application-dev-prompt-optimize in rmyndharis/antigravity-skills

Quality

Content

25%Scale 1-5

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

This skill is essentially a hollow wrapper with no actionable content. It provides vague, abstract instructions ('apply best practices', 'validate outcomes') without any concrete techniques, examples, or templates for prompt engineering. The claimed statistics are unsourced and the core content is deferred entirely to a resource file that doesn't exist in the bundle.

Suggestions

Add concrete prompt engineering techniques with before/after examples (e.g., show a basic prompt transformed into an optimized one using chain-of-thought or few-shot patterns).

Replace vague instructions like 'Apply relevant best practices' with specific, actionable steps such as 'Add a role preamble', 'Include 2-3 few-shot examples', 'Add output format constraints'.

Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the essential patterns and examples directly in the SKILL.md.

Remove the unsourced statistics ('improve accuracy by 40%') and the tautological 'Use/Do not use' sections to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary framing ('You are an expert prompt engineer...') and vague statistics ('improve accuracy by 40%') that don't add actionable value. The 'Use this skill when' / 'Do not use this skill when' sections are largely tautological. However, it's relatively short overall.	3 / 5
Actionability	The instructions are entirely vague and abstract: 'Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes.' There are no concrete examples, no executable code, no specific techniques, no templates, and no actual prompt engineering patterns. The skill delegates everything to a resource file that isn't provided.	1 / 5
Workflow Clarity	There is a rough sequence implied (clarify goals → apply practices → validate), but steps are poorly defined with no specifics on what validation looks like, no checkpoints, and no concrete process. The '$ARGUMENTS' placeholder is unexplained.	2 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable structure, but no bundle files are provided so the reference is unverifiable. The SKILL.md itself contains almost no substantive content to serve as a useful overview — it's essentially an empty shell pointing to a missing file.	2 / 5
	Total	8 / 20 Passed

Description

36%Scale 1-5

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 truncated and incomplete, cutting off mid-word at 'optimizati'. It uses second-person voice ('You are') which violates the third-person requirement. While it names the domain of prompt engineering and lists some techniques, it lacks concrete actions, a 'when to use' clause, and natural trigger terms that users would employ.

Suggestions

Complete the truncated description and rewrite in third person (e.g., 'Crafts and refines prompts for LLMs using chain-of-thought, few-shot examples, and system prompt design').

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user asks to write, improve, or debug a prompt, system instruction, or LLM input'.

Include concrete actions the skill performs (e.g., 'generates system prompts, restructures instructions, adds few-shot examples, evaluates prompt effectiveness') rather than just listing technique names.

Dimension	Reasoning	Score
Specificity	Names the domain ('prompt engineering') and mentions techniques like 'constitutional AI, chain-of-thought reasoning, and model-specific optimization,' but these are technique names rather than concrete actions the skill performs. No verbs describing what it actually does (e.g., 'generates prompts', 'refines instructions').	2 / 5
Completeness	The description provides a vague 'what' (crafting effective prompts for LLMs) but has no 'when' clause at all. Additionally, the description appears truncated mid-word ('optimizati'), suggesting it is incomplete. The missing 'Use when...' clause caps this at 3, and the truncation and vagueness bring it to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'prompt engineer', 'prompts', 'LLMs', 'chain-of-thought reasoning', and 'constitutional AI'. However, it misses common natural user phrases like 'write a prompt', 'improve my prompt', 'prompt design', 'system prompt', or 'instructions for AI'.	3 / 5
Distinctiveness Conflict Risk	The domain of 'prompt engineering' is somewhat specific, but the description is broad enough that it could overlap with any skill related to LLM usage, AI assistance, or writing tasks. The mention of specific techniques like 'constitutional AI' adds some distinctiveness but not enough to clearly carve out a niche.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/llm-application-dev-prompt-optimize/SKILL.md
Commit: 57c135b

Reviewed: 4 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.