senior-prompt-engineer
Design Production LLM Prompts
Teams often struggle to turn prompt experiments into reliable AI products. This skill gives structured guidance for prompts, evaluations, RAG, and agent design.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "senior-prompt-engineer" from https://skillstore.io/skills/davila7-senior-prompt-engineer.md and its manifest at https://skillstore.io/api/skills/davila7-senior-prompt-engineer/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 "senior-prompt-engineer". A support chatbot prompt gives long answers and ignores escalation rules.
Expected outcome:
- The review identifies unclear role boundaries and missing escalation criteria.
- The revised prompt adds concise answer rules, escalation triggers, and quality checks.
- The evaluation plan tests answer length, policy compliance, and handoff accuracy.
Using "senior-prompt-engineer". A team wants to compare two RAG prompt versions before release.
Expected outcome:
- The output defines retrieval relevance, groundedness, refusal accuracy, and latency measures.
- It proposes representative test cases and a regression process for future prompt changes.
- It flags missing data governance and human review requirements.
Using "senior-prompt-engineer". An agent workflow needs review before production deployment.
Expected outcome:
- The review highlights weak failure handling, limited monitoring, and unclear tool permissions.
- It recommends explicit state transitions, audit logging, and guarded deployment steps.
- It separates immediate fixes from longer-term architecture improvements.
Security Audit
SafeThe static network reconnaissance findings are false positives from the phrase "Resource awareness" in performance guidance. The external command findings are Markdown fences or inline file references, with no hidden command execution, obfuscation, or prompt injection evidence 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/davila7-senior-prompt-engineer/audits/12?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/davila7-senior-prompt-engineer?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/davila7-senior-prompt-engineer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-senior-prompt-engineer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/davila7-senior-prompt-engineer.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
davila7. (2026). senior-prompt-engineer security audit report (audit version 12) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-senior-prompt-engineer/audits/12BibTeX citation
@techreport{davila7-davila7-senior-prompt-engineer-2026,
author = {davila7},
title = {senior-prompt-engineer security audit report (audit version 12)},
institution = {Skillstore},
year = {2026},
number = {12},
url = {https://skillstore.io/skills/davila7-senior-prompt-engineer/audits/12},
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: "senior-prompt-engineer security audit report (audit version 12)"
version: "unspecified"
type: report
authors:
- name: "davila7"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/davila7-senior-prompt-engineer/audits/12"
identifiers:
- type: other
value: "skillstore:davila7-senior-prompt-engineer:audit:12"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
alirezarezvani-senior-prompt-engineer
2026-08-21
davila7-senior-prompt-engineer
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Improve Product Prompts
Refine prompts for a customer-facing AI feature with clearer outputs and measurable quality checks.
Plan LLM Evaluations
Define evaluation workflows, quality metrics, and troubleshooting steps before shipping model changes.
Review Agent Architecture
Assess agent designs for reliability, monitoring, security controls, and operational readiness.
Try These Prompts
Review this prompt for clarity, missing context, and output structure. Suggest a revised version and explain each change.
Design a prompt that produces a stable structured response for this task. Include field definitions, validation rules, and failure handling.
Create an evaluation plan for this LLM workflow. Include success criteria, test cases, scoring guidance, and regression checks.
Review this agentic system design for reliability, observability, cost, security, and failure recovery. Prioritize risks and propose concrete improvements.
Best Practices
- Pair every prompt change with measurable evaluation criteria.
- Document expected outputs, failure cases, and escalation rules before deployment.
- Review agent tools, permissions, and logs before enabling production workflows.
Avoid
- Relying on vague role instructions instead of task-specific requirements.
- Shipping prompt changes without regression tests or baseline comparisons.
- Treating example deployment commands as ready for every environment.
Frequently Asked Questions
Who should use this skill?
Does it run model evaluations automatically?
Can it help with Claude and Claude Code workflows?
Does it require external services?
Is it suitable for regulated environments?
What should be checked before running example commands?
Developer Details
Author
davila7License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
b959ebfd1043a07c0c4378ab94ca4342cb0259f5
Maintenance freshness
7/20/2026
Usage
7 downloads · 194 views