메뉴
GPT as security advisor and architectural critic. Sends code or decisions to GPT for independent second opinion. Strong in security audits, code review, and finding logical flaws. Don't use for routine coding or simple tasks.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Machine learning model training with HuggingFace. Fine-tuning LLMs, dataset creation, GPU selection, training monitoring. Use for training custom models. Don't use for using pre-trained models via API.
Estimates project cost at market rates. Scans codebase, counts APIs, integrations, and complexity. Shows what the project would cost without AI. Use for pitches and ROI demonstrations.
Marketing and conversion optimization. Landing page CRO, copywriting, positioning, GTM strategy, A/B testing. Don't use for product development or technical decisions.
Product management frameworks. PRD writing, user stories, OKRs, roadmap, TAM/SAM/SOM analysis, competitive research. Don't use for technical implementation.
Scraping specific platforms with ready connectors. Google Maps businesses, Twitter trends, YouTube subtitles, Instagram/TikTok content. Use for platform-specific data collection.
Data analysis from external services. Connects to Google Sheets, Notion, HubSpot via Composio. Builds charts, runs queries, generates insights. Don't use for database queries.
| name | gpt-advisor |
| description | GPT as security advisor and architectural critic. Sends code or decisions to GPT for independent second opinion. Strong in security audits, code review, and finding logical flaws. Don't use for routine coding or simple tasks. |
| disable-model-invocation | true |
| model | sonnet |
| effort | medium |
| allowed-tools | Read, Grep, Glob, Bash |
| argument-hint | ["topic-or-file"] |
GPT acts as an INDEPENDENT advisor to the GODMODE orchestrator. NOT an executor. Does NOT write code. Gives OPINIONS and finds WEAKNESSES.
Send code → ask GPT to find vulnerabilities. GPT is strong at: SQL injection, auth bypass, data exposure, race conditions.
Prompt template:
You are a senior security engineer. Review this code for vulnerabilities.
Focus on: OWASP Top 10, authentication flaws, data exposure, injection attacks.
For each issue: severity, file:line, exploit scenario, fix.
Code: [paste code]
Send architecture decision → ask GPT to find flaws.
Prompt template:
You are a senior software architect. Critique this architecture decision.
Find: scalability issues, single points of failure, over-engineering, missing components.
Decision: [paste decision]
Context: [paste context]
When /dispute is running, GPT provides independent opinion.
Prompt template:
You are an independent technical expert.
Topic: [topic]
Position A argues: [summary]
Position B argues: [summary]
Give your independent analysis. Where do you agree/disagree with each?
What did both miss?