prompt-optimize
Optimize Prompts With Guided Engineering
Weak prompts create vague outputs and repeated revision loops. This skill guides Claude, Codex, and Claude Code through structured prompt design, safety checks, and final prompt delivery.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "prompt-optimize" from https://skillstore.io/skills/yyh211-prompt-optimize.md and its manifest at https://skillstore.io/api/skills/yyh211-prompt-optimize/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "prompt-optimize". Create a prompt for summarizing meeting notes.
Expected outcome:
The skill recommends a structured summary with decisions, action owners, open questions, and a short rationale for each section.
Using "prompt-optimize". Improve my public chatbot prompt for safety.
Expected outcome:
The skill suggests role boundaries, instruction separation, refusal rules, and checks for malicious user input.
Using "prompt-optimize". Review this advanced creative writing prompt.
Expected outcome:
The skill identifies strong elements, proposes a deeper reasoning stage, and waits for approval before drafting changes.
Security Audit
SafeThe shell backtick detections are false positives from Markdown code fences containing dialogue examples, not executable Ruby or shell code. The entropy heuristic is also a false positive caused by multilingual Markdown content, not binary, encrypted, or obfuscated content. No semantic evidence of data exfiltration, override claims, or malicious prompt injection was found.
Risk Factors
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/yyh211-prompt-optimize/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/yyh211-prompt-optimize?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/yyh211-prompt-optimize?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/yyh211-prompt-optimize/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/yyh211-prompt-optimize.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
YYH211. (2026). prompt-optimize security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/yyh211-prompt-optimize/audits/7BibTeX citation
@techreport{yyh211-yyh211-prompt-optimize-2026,
author = {YYH211},
title = {prompt-optimize security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/yyh211-prompt-optimize/audits/7},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "prompt-optimize security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "YYH211"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/yyh211-prompt-optimize/audits/7"
identifiers:
- type: other
value: "skillstore:yyh211-prompt-optimize:audit:7"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Design Customer Support Bots
Create role instructions, refusal rules, and response formats for public support assistants.
Improve Creative Generation Prompts
Turn broad creative requests into structured workflows for names, slogans, and campaign ideas.
Review Agent System Instructions
Assess mature instructions and propose architecture upgrades without rewriting before approval.
Try These Prompts
Optimize this prompt for clearer results. Ask me any important questions before rewriting it: [paste prompt].
Create a prompt for this task: [describe task]. Recommend the best structure, explain why, then draft the final prompt.
Improve this public-facing AI role with safety boundaries, injection resistance, and refusal behavior: [paste role].
Review this mature system instruction as a prompt engineering peer. Identify strengths, risks, and one high-leverage improvement path: [paste instruction].
Best Practices
- Share the audience, task, input examples, and success criteria before asking for the final prompt.
- Confirm the proposed prompt architecture before requesting a complete rewrite.
- Include safety boundaries for public, sensitive, or user-input-heavy workflows.
Avoid
- Requesting a generic prompt without task context or expected output.
- Using advanced prompt methods when a simple instruction is enough.
- Removing guardrails to make a public assistant more permissive.