Adoption

Agent Skills are supported by leading AI development tools.

VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory VS Code Gemini CLI GitHub Goose Amp Cursor Claude Code Letta OpenCode Claude OpenAI Codex Factory

chemistrywow31/Team Topology Analysis

Name: Team Topology Analysis
Author: chemistrywow31

.agents/skills/team-topology-analysis/SKILL.md

npx skillsauth add chemistrywow31/A-Team Team Topology Analysis

Clean

TrivyContainer and dependency vulnerability scanner

Clean

SemgrepStatic code analysis for vulnerabilities

Clean

mcp-scan (Snyk)Model Context Protocol security validation

Skipped

Snyk (dep)Open source security scanning

Skipped

Socket.devSupply chain security analysis

Skipped

VirusTotalMulti-engine malware detection

Skipped

CrowdStrikeAdvanced threat intelligence

Skipped

OSV-ScannerOpen Source Vulnerability database check

Skipped

OWASP Dep-Check

Team Topology Analysis

Description

Use this skill to judge whether a proposed team graph is clean, bottlenecked, or over-coordinated.

Users

.codex/agents/discovery/role-designer.md

Topology Patterns

Pipeline

A -> B -> C

Good for strict stage-by-stage work. Risk: one blocked node stalls the chain.

Hub And Spoke

Coordinator -> specialists

Good for coordinator-driven parallel work. Risk: the coordinator becomes a bottleneck.

Hybrid

Coordinator -> stage group -> review -> stage group

Usually the best default for non-trivial teams.

Codex Multi-Agent Considerations

parallel agents must own different files
the coordinator must define when to spawn_agent
follow-up work must be explicit enough for send_input
join points must be documented so wait happens only at real synchronization boundaries

Quality Checkpoints

every agent has at least one upstream or downstream connection
the coordinator is central but not overloaded
no meaningless circular dependency exists
parallel work is backed by non-overlapping file ownership

Example

Input

前端、後端、QA 三個角色都要直接改同一份 API schema。

Output

拓撲有衝突；應指定單一 schema owner，其他角色只讀或透過 reviewer/coordinator 提出變更。

chemistrywow31/Team Topology Analysis

.agents/skills/team-topology-analysis/SKILL.md

Evaluate whether a proposed agent graph supports safe handoffs and useful parallel work

43 stars

data-ai

Updated Apr 15, 2026

$ install --global

skillsauth

npx skillsauth add chemistrywow31/A-Team Team Topology Analysis

Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.

Security Scan Results

3 of 9 scanners reported clean

Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.

Scanners Passed

Scanners in report

Clean

TrivyContainer and dependency vulnerability scanner

95%

Clean

SemgrepStatic code analysis for vulnerabilities

95%

Clean

mcp-scan (Snyk)Model Context Protocol security validation

95%

Skipped

Snyk (dep)Open source security scanning

50%

Skipped

Socket.devSupply chain security analysis

50%

Skipped

VirusTotalMulti-engine malware detection

50%

Skipped

CrowdStrikeAdvanced threat intelligence

50%

Skipped

OSV-ScannerOpen Source Vulnerability database check

50%

Skipped

OWASP Dep-Check

50%

Last scanned: Apr 15, 2026, 9:01 PM33.9s1 file scanned

SKILL.md

name:: Team Topology Analysis
description:: Evaluate whether a proposed agent graph supports safe handoffs and useful parallel work

Team Topology Analysis

Description

Use this skill to judge whether a proposed team graph is clean, bottlenecked, or over-coordinated.

Users

.codex/agents/discovery/role-designer.md

Topology Patterns

Pipeline

A -> B -> C

Good for strict stage-by-stage work. Risk: one blocked node stalls the chain.

Hub And Spoke

Coordinator -> specialists

Good for coordinator-driven parallel work. Risk: the coordinator becomes a bottleneck.

Hybrid

Coordinator -> stage group -> review -> stage group

Usually the best default for non-trivial teams.

Codex Multi-Agent Considerations

parallel agents must own different files
the coordinator must define when to spawn_agent
follow-up work must be explicit enough for send_input
join points must be documented so wait happens only at real synchronization boundaries

Quality Checkpoints

every agent has at least one upstream or downstream connection
the coordinator is central but not overloaded
no meaningless circular dependency exists
parallel work is backed by non-overlapping file ownership

Example

Input

前端、後端、QA 三個角色都要直接改同一份 API schema。

Output

拓撲有衝突；應指定單一 schema owner，其他角色只讀或透過 reviewer/coordinator 提出變更。

Related Skills