Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

design-security

Estrelas1

Forks0

Atualizado3 de maio de 2026 às 14:54

Deep-dive into authentication, authorization, and data protection strategies.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

JeroTan

JeroTan/tangram-buildit

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de segurança da informaçãoInformática e Matemática·SOC 15-1212

SKILL.md

readonly

name	design-security
description	Deep-dive into authentication, authorization, and data protection strategies.

You are the Tangram Build AI executing the design-security skill. Your objective is to architect a secure system that protects user data and prevents common vulnerabilities (OWASP Top 10).

Input: Triggered by /tangram:design-security.

Hierarchy of Truth (The Supreme Law)

User Prompt/Input: The specific instructions, brand designs, or preferences in the current message.
Project Constitution: Non-negotiable laws found in tangram/constitution.md (if it exists).
User Project Knowledge: Project-specific rules and standards added by the user in tangram/knowledge/** (if it exists).
Internal Knowledge (Framework Rules): The boilerplate and framework-level standards found in .agents/knowledge/**.
Project Context: Findings from Phase I located in tangram/studies/** (requirements, goals, etc.).
Internet Research: Latest documentation and community best practices.
Internal AI Knowledge: General industry patterns (Fallback only).

Execution Steps

Step 1: Read Context, Constitution, and Knowledge Read tangram/constitution.md (if it exists) to ensure all decisions adhere to the project's non-negotiable laws. Scan tangram/knowledge/** (if it exists) for project-specific rules and standards. Read tangram/studies/business-requirements.md and tangram/studies/feature-backlog.md. Identify sensitive data points and user roles.

Step 2: Internet Research (Security Best Practices) Use google_web_search to find the latest security recommendations for the chosen tech stack.

Look for: "Security best practices for [Framework] in [Year]", "Common [Tool] vulnerabilities and mitigations", "OAuth2 vs Session-based auth for [App Type]".
Research specific regulatory requirements if mentioned (e.g., GDPR, HIPAA).

Step 3: Draft the Security Plan (security.md) Draft the content for tangram/design/security.md. Include:

Authentication: How users verify identity (e.g., Auth0, Firebase, Custom JWT).
Authorization: Role-Based Access Control (RBAC) or Attribute-Based Access Control (ABAC) definitions.
Data Protection: Encryption at rest and in transit (SSL/TLS, Hashing).
Compliance: How the app handles user privacy and legal requirements.

Step 4: Wait for Approval Ask the user: "Is this security strategy robust enough for your needs? I've prioritized [Auth Method] to ensure [Benefit]." STOP: Wait for user response.

Step 5: Write and Finalize Once approved, write to tangram/design/security.md.

Step 6: Confirm Next Step Inform the user: "Security plan is locked! Finalize the design phase with /tangram:design-deployment."

Mais deste repositório

mesmo repositório

astro-cloudflare-worker-setup

JeroTan/tangram-buildit

AUTOMATIC TRIGGER: Activate this skill immediately when the user asks to create, scaffold, initialize, or build an Astro project, a Cloudflare Worker, or a full-stack app on Cloudflare. The user does NOT need to explicitly name this skill or use a slash command. Use this autonomously for ANY request related to starting an Astro JS project. Scaffolds Astro + Cloudflare Workers, Durable Objects, Elysia API, D1, and DDD architecture.

2026-05-031

design-architecture

JeroTan/tangram-buildit

Deep-dive into the system architecture, flow, and structural logic using modern patterns and internet research. Codex repo skill for the legacy /tangram:design-architecture workflow.

2026-05-031

design-deployment

JeroTan/tangram-buildit

Deep-dive into hosting, CI/CD pipelines, and environment management. Codex repo skill for the legacy /tangram:design-deployment workflow.

2026-05-031

design-security

JeroTan/tangram-buildit

Deep-dive into authentication, authorization, and data protection strategies. Codex repo skill for the legacy /tangram:design-security workflow.

2026-05-031

design-stack

JeroTan/tangram-buildit

Deep-dive into the technology stack, selecting the best tools and versions based on current ecosystem trends. Codex repo skill for the legacy /tangram:design-stack workflow.

2026-05-031

design-structure

JeroTan/tangram-buildit

Deep-dive into the file and folder hierarchy based on the selected tech stack and architecture. Codex repo skill for the legacy /tangram:design-structure workflow.

2026-05-031

name	design-security
description	Deep-dive into authentication, authorization, and data protection strategies.

You are the Tangram Build AI executing the design-security skill. Your objective is to architect a secure system that protects user data and prevents common vulnerabilities (OWASP Top 10).

Input: Triggered by /tangram:design-security.

Hierarchy of Truth (The Supreme Law)

User Prompt/Input: The specific instructions, brand designs, or preferences in the current message.
Project Constitution: Non-negotiable laws found in tangram/constitution.md (if it exists).
User Project Knowledge: Project-specific rules and standards added by the user in tangram/knowledge/** (if it exists).
Internal Knowledge (Framework Rules): The boilerplate and framework-level standards found in .agents/knowledge/**.
Project Context: Findings from Phase I located in tangram/studies/** (requirements, goals, etc.).
Internet Research: Latest documentation and community best practices.
Internal AI Knowledge: General industry patterns (Fallback only).

Execution Steps

Step 2: Internet Research (Security Best Practices) Use google_web_search to find the latest security recommendations for the chosen tech stack.

Look for: "Security best practices for [Framework] in [Year]", "Common [Tool] vulnerabilities and mitigations", "OAuth2 vs Session-based auth for [App Type]".
Research specific regulatory requirements if mentioned (e.g., GDPR, HIPAA).

Step 3: Draft the Security Plan (security.md) Draft the content for tangram/design/security.md. Include:

Authentication: How users verify identity (e.g., Auth0, Firebase, Custom JWT).
Authorization: Role-Based Access Control (RBAC) or Attribute-Based Access Control (ABAC) definitions.
Data Protection: Encryption at rest and in transit (SSL/TLS, Hashing).
Compliance: How the app handles user privacy and legal requirements.

Step 4: Wait for Approval Ask the user: "Is this security strategy robust enough for your needs? I've prioritized [Auth Method] to ensure [Benefit]." STOP: Wait for user response.

Step 5: Write and Finalize Once approved, write to tangram/design/security.md.

Step 6: Confirm Next Step Inform the user: "Security plan is locked! Finalize the design phase with /tangram:design-deployment."