Skip to main content
reopt Handbook
reopt Handbook
Enterprise Project Architecture

Monorepo Foundation

Monorepo ArchitectureWorkspace DesignShared PackagesTurbo Pipeline

Apps and Delivery

Next.js PatternsVercel DeploymentCI/CD PipelineTesting Strategy

Agents and Operations

Agentic DevelopmentSkills EcosystemSecurity GovernanceMonitoring and Incident

Appendix

TemplatesReferencesUpdatesVerification
Handbook›Enterprise Project Architecture›Skills Ecosystem
한국어English

Skills Ecosystem

Build reusable agent skills, commands, and documents for repeated engineering workflows.

Key takeaways

  • A skills ecosystem turns repeated work into reusable instructions shared by agents and humans for repository-specific tasks.
  • Vercel Skills v1.1 replaced the deprecated npx add-skill flow with the npx skills CLI (find, add, update).
  • Good skill candidates are concrete recurring workflows: new app setup, UI component docs, SEO audit, SDK install, release verification, incident triage.
  • Write skills for a concrete workflow with trigger phrases, prefer scripts or templates for mechanical steps, and record verification commands and expected outputs.
  • Treat external skills as supply-chain inputs: verify the source, review SKILL.md, avoid global installation in production, and require owner approval before updates.

A skills ecosystem turns repeated work into reusable instructions. It gives agents and humans a shared way to perform repository-specific tasks without rediscovering the same process.

Vercel Skills v1.1 replaced the deprecated npx add-skill flow with the npx skills CLI.

npx skills find
npx skills add vercel/turborepo
npx skills add vercel-labs/agent-skills
npx skills update

Skill Candidates

WorkflowSkill value
New app setupRepeat workspace, config, deploy, and verification steps
UI component docsPreserve MDX and registry structure
SEO auditStandardize page, metadata, and indexing checks
SDK installationApply package-specific setup safely
Release verificationRun the same pre-release checklist
Incident triageCollect logs, affected services, and rollback options

Skill Design Rules

  • Write for a concrete workflow, not a broad topic.
  • Include trigger phrases so the skill is used at the right time.
  • Prefer scripts or templates for mechanical steps.
  • Keep instructions current with repository structure.
  • Record verification commands and expected outputs.
  • Install skills through pull requests and review skill diffs before updates.

Ecosystem Governance

ItemOwner decision
Skill ownerWho updates the instruction
Review cadenceWhen the skill is tested or revised
ScopeWhich apps or packages it may affect
SafetyWhat actions require human approval

Quality Signal

A skill is useful when it reduces repeated explanation, prevents common mistakes, and still leaves room for engineering judgment.

Treat external skills as supply-chain inputs. Verify the source, review SKILL.md, avoid global installation for production projects, and require owner approval for new or updated skills.

Related docs

Custom commands and skills

Claude Code Command Master · Choose the commands for custom commands and skills and follow their availability rules and concrete examples.

Cmd. /skills

Codex Command Master · Browse and apply local skills for task-specific behavior.

Skills and Slash Commands

Claude Code Complete Guide · Package repeatable Claude Code workflows into reusable commands and skills.

From Docs to Skills, Plugins, and MCP

Agentic Documentation · Split rules, workflows, distribution units, and external context into the right agent surface.

Skills and Custom Commands

Claude Code Command Master · How to design reusable Claude Code skills and slash commands for team workflows.

Agentic Development

Use AI agents in enterprise development with context packs, scoped tasks, and review gates.

Security Governance

Manage secrets, access, dependencies, permissions, and approval rules in enterprise projects.

On this page

Skill CandidatesSkill Design RulesEcosystem GovernanceQuality Signal