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

41%

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

Quality

Content

42%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 content is admirably concise but offers only abstract guidance with no concrete, executable steps, and its single progressive-disclosure reference points to a missing file. It reads as a placeholder rather than a working skill body.

Suggestions

Replace vague directives with concrete guidance: specific prompt-rewrite patterns, an example before/after prompt, or an executable checklist.

Either create the referenced 'resources/implementation-playbook.md' or remove the broken reference and inline the essential patterns.

Add an explicit validation/verification checkpoint (e.g. 'After rewriting, test the prompt against 2-3 representative inputs and confirm the output meets the stated constraints before returning it').

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows ('Clarify goals, constraints, and required inputs' is terse and directive), matching the 'lean and efficient' anchor.	3 / 3
Actionability	The instructions are abstract directives ('Apply relevant best practices and validate outcomes', 'Provide actionable steps and verification') with no concrete code, commands, or worked examples, matching the 'vague or abstract' anchor.	1 / 3
Workflow Clarity	Steps are listed in a sequence but they are generic and lack validation checkpoints or feedback loops; the single 'validate outcomes' mention is implicit rather than an explicit checkpoint, matching the 'steps listed but validation gaps' anchor.	2 / 3
Progressive Disclosure	The body references 'resources/implementation-playbook.md' in both Instructions and Resources, but no resources/ directory (or references/scripts/assets) exists, so the navigation points to a non-existent file and provides no usable bundle structure.	1 / 3
	Total	7 / 12 Passed

Description

40%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 names a clear domain but stays vague on concrete actions and omits any explicit use-when trigger guidance, weakening both completeness and trigger discoverability. It is also written in second person, which the guidelines penalize.

Suggestions

Rephrase in third person and list concrete actions, e.g. 'Optimizes and refines prompts for LLMs using constitutional AI, chain-of-thought, and model-specific techniques; rewrites, debugs, and restructures prompts.'

Add an explicit trigger clause such as 'Use when the user wants to improve, refine, or troubleshoot prompts for an LLM.'

Complete the truncated final word ('optimizati') so the description is not cut off.

Dimension	Reasoning	Score
Specificity	The description uses vague language ('crafting effective prompts', 'specializing in') with no concrete actions enumerated; it is also written in second person ('You are an expert prompt engineer'), which per the guidelines reduces specificity by one, landing at 1.	1 / 3
Completeness	It states what the skill does but provides no explicit 'Use when...' trigger clause, so per the guideline an absent trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces some relevant keywords users might say ('prompts', 'LLMs', 'prompt engineer') but misses common natural variations like 'improve my prompt', 'refine prompts', or 'make my prompt better', so it sits at the middle anchor.	2 / 3
Distinctiveness Conflict Risk	The prompt-engineering niche is fairly specific, but without explicit triggers it could still overlap with general coding or writing skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/llm-application-dev-prompt-optimize/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.