research-engineer
Strengthen Research-Grade Engineering Workflows
Complex engineering tasks often fail when assumptions, complexity, or verification are weak. This skill guides Claude, Codex, and Claude Code toward rigorous analysis, implementation standards, and proof-oriented review.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "research-engineer" from https://skillstore.io/skills/sickn33-research-engineer.md and its manifest at https://skillstore.io/api/skills/sickn33-research-engineer/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.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 "research-engineer". Analyze a naive recursive Fibonacci function.
Expected outcome:
Explains exponential time complexity, derives the recurrence, and recommends a logarithmic matrix exponentiation approach.
Using "research-engineer". Choose a language for a safety-critical service.
Expected outcome:
Compares Rust and Ada, explains safety properties, and recommends verification and testing requirements.
Using "research-engineer". Review a proposal to parse HTML with regular expressions.
Expected outcome:
Rejects the approach, explains the language-theory mismatch, and recommends a dedicated parser.
Security Audit
High RiskAll seven static external-command findings are false positives caused by markdown inline code or fenced examples in SKILL.md. A semantic review found prompt-injection style role override language that may conflict with higher-priority assistant instructions.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (7)
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/sickn33-research-engineer/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-research-engineer?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-research-engineer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-research-engineer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-research-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
sickn33. (2026). research-engineer security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-research-engineer/audits/4BibTeX citation
@techreport{sickn33-sickn33-research-engineer-2026,
author = {sickn33},
title = {research-engineer security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/sickn33-research-engineer/audits/4},
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: "research-engineer security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-research-engineer/audits/4"
identifiers:
- type: other
value: "skillstore:sickn33-research-engineer:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Validate Algorithm Choices
Review proposed algorithms for complexity, correctness, and implementation risks before coding starts.
Plan Systems Implementations
Choose suitable languages, concurrency models, and verification methods for performance-sensitive software.
Review Technical Designs
Identify weak assumptions, missing tests, and invalid abstractions in engineering proposals.
Try These Prompts
Analyze this proposed approach for [problem]. Identify flawed assumptions, complexity bounds, and a safer implementation path.
Given these constraints, recommend the best language, libraries, and verification approach. Explain tradeoffs and rejected options.
Design an implementation for [system]. Include invariants, failure modes, tests, and proof obligations before code generation.
Evaluate this architecture for correctness, concurrency hazards, asymptotic limits, and benchmarking gaps. Prioritize defects by severity.
Best Practices
- Provide exact constraints, expected inputs, and failure cases.
- Ask for complexity analysis and verification criteria before implementation.
- Pair generated recommendations with benchmarks or tests when possible.
Avoid
- Using the skill for casual brainstorming that needs a gentle tone.
- Requesting production code without target platform details.
- Accepting theoretical claims without independent tests or review.