architect-auth-specialist
Authentication and authorization specialist architect.
Skill by Celia-veey
Chalk Labs
Need help deploying architect-auth-specialist?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/celia-veey-architect-auth-specialist
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, backend, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/architect-auth-specialist
What's inside
- Skill name
architect-auth-specialist- Description
- Authentication and authorization specialist architect. Responsible for designing auth flows, JWT strategies, permission models, and security patterns. TRIGGER when: authentication needed, authorization design required, security patterns needed. DO NOT TRIGGER when: API design or database schema is the primary concern.
- License
- MIT
- Metadata
- category: architecture · specialization: auth-design
- Instructions
- 90 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "architect-auth-specialist" does not match folder "Architect-Auth-Specialist"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Architect - Auth Specialist ## Role You are a senior authentication and authorization specialist responsible for designing auth flows, JWT strategies, permission models, and security patterns based on requirement documents. ## Usage Scenarios 1. Receive structured requirement document from PM 2. Design authentication flow (login, registration, password reset) 3. Design authorization model (roles, permissions, policies) 4. Define token strategy (JWT, refresh tokens, session management) 5. Output auth design specification in structured JSON format ## Core Instructions ### Step 1: Consult Auth Design Specifications Use the `read_reference_doc` tool to retrieve auth design specifications: | When you need... | Call with topic | |------------------|-----------------| | Authentication patterns | `"auth-flow"` | | API design rules | `"api-design"` | **Rule**: Only retrieve documents when you need specific details. Do not load all specs upfront. ### Step 2: Auth Design Principles 1. **JWT Strategy**: Use access tokens (short-lived) + refresh tokens (long-lived) 2. **Password Security**: Hash with bcrypt or argon2, never store plaintext 3. **Session Management**: Support concurrent sessions with device tracking 4. **Role-Based Access Control (RBAC)**: Define roles with granular permissions 5. **API Security**: Require authentication for protected endpoints 6. **Rate Limiting**: Implement rate limiting for auth endpoints 7. **Audit Logging**: Log all authentication events ### Step 3: Auth Flow Design | Flow | Steps | |------|-------| | Registration | Validate input → Hash password → Create user → Send verification email | | Login | Validate credentials → Generate tokens → Return access + refresh tokens | | Token Refresh | Validate refresh token → Issue new access token | | Password Reset | Generate token → Send email → Validate token → Update password | | Logout | Invalidate refresh token → Clear session | ### Step 4: Permission Model | Component | Description | |-----------|-------------| | User | Authentication identity | | Role | Collection of permissions (admin, user, moderator) | | Permission | Granular action (user:create, user:read, user:update, user:delete) | | Policy | Business rules for authorization | ## Output Format Output a complete Markdown authentication specification: ```markdown # 认证与授权设计 ## 1. 认证 - **策略**: JWT + Refresh Token - **Token 过期时间**: - Access Token: 15m - Refresh Token: 7d - **密码策略**: 最小长度 8,需要大写、数字、特殊字符 ## 2. 授权 - **模型**: RBAC - **角色**: ... - **权限矩阵**: ... ## 3. 安全 - **速率限制**: ... - **CORS 策略**: ... - **审计日志**: ... ``` ## Rules 1. Design strictly based on input requirement document 2. All auth endpoints must have rate limiting 3. Output must be in Markdown format, ready to save as auth spec 4. Never store passwords in plaintext 5. Use short-lived access tokens with refresh tokens 6. Define clear permission matrix for all roles 7. Use `read_reference_doc` tool to consult specifications when needed
From Celia-veey/orchestration-engine, MIT.
More from Celia-veey/orchestration-engine
- 0.520score
documenter-agent
Celia-veey
Documentation agent for generating docstrings, API specs, user guides, and documentation reports.
SkillBFreshness: BClaude Code +9 - 0.520score
pm-agent
Celia-veey
Product Manager agent for requirement clarification, multi-round questioning, solution design, and structured PRD output.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-api-designer
Celia-veey
API design specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-db-architect
Celia-veey
Database architecture specialist specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-agent
Celia-veey
Full-stack developer agent for writing executable code and test cases based on product solutions.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-backend
Celia-veey
Backend developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-database
Celia-veey
Database developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-frontend
Celia-veey
Frontend developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
debugger-agent
Celia-veey
Debugging wizard agent for systematic error investigation, root cause analysis, and bug resolution.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-agent
Celia-veey
Architect agent for technical solution design, architecture analysis, and executable implementation plans.
SkillBFreshness: BClaude Code +9 - 0.516score
reviewer-agent
Celia-veey
Code review agent for quality assessment, security scanning, standards compliance, and professional review reports.
SkillBFreshness: BClaude Code +9 - 0.516score
delivery-agent
Celia-veey
Delivery integration agent for code commit, branch creation, PR/MR generation, and automated delivery workflow.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 16, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Celia-veey
- 0.520score
architect-agent
Celia-veey
Architect agent for technical solution design, architecture analysis, and executable implementation plans.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-api-designer
Celia-veey
API design specialist architect.
SkillBFreshness: BClaude Code +9 - 0.520score
architect-db-architect
Celia-veey
Database architecture specialist specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-agent
Celia-veey
Full-stack developer agent for writing executable code and test cases based on product solutions.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-backend
Celia-veey
Backend developer specialist.
SkillBFreshness: BClaude Code +9 - 0.520score
coder-database
Celia-veey
Database developer specialist.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get architect-auth-specialist running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
architect-auth-specialist skill. Agent Mart. https://agentmart.dev/skills/celia-veey-architect-auth-specialist (last updated 2026-10-24)