makers-migration

Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions. Use when the user wants to adapt a standard agent project to run on EdgeOne Makers, convert Express/Next.js API routes to Makers handlers, or add platform capabilities (context.tools, context.sandbox, context.store). Do NOT trigger for new agent projects (use makers-agents instead).

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured migration guide: decision-tree routing, concrete before/after tables and executable code, numbered steps, and a verification checklist, with detailed before/after material correctly offloaded to one-level-deep reference files that are present in the bundle.

Dimension	Reasoning	Score
Conciseness	Lean, table-driven before/after content with no padding or explanation of concepts Claude already knows; tokens are spent on platform-specific conventions and executable patterns rather than prose. Minor redundancy between §1 and §6 (both cover Express/Next.js → Makers) keeps it just shy of flawless but well within the 'lean and efficient' anchor.	3 / 3
Actionability	Provides fully executable before/after code blocks, specific numbered migration steps, and concrete API names (e.g. context.tools.toLangChainTools, context.store.langgraphCheckpointer, createSSEResponse) — copy-paste ready across Node and Python variants.	3 / 3
Workflow Clarity	A top-level decision tree routes by language/framework to numbered per-framework steps, a shared pre-migration checklist sequences global changes, and §8 supplies an explicit post-migration verification checklist as a validation checkpoint for this structurally destructive operation.	3 / 3
Progressive Disclosure	SKILL.md is an overview with per-framework summaries and clearly signaled one-level-deep references ('Detailed before/after: [references/...]'); all six referenced files (api-route, crewai, langgraph, deepagents, openai-agents, claude-agent-sdk) exist in ./references/, so navigation is real and shallow.	3 / 3
	Total	12 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities, gives an explicit 'Use when' trigger, enumerates the relevant source frameworks, and proactively disambiguates from a sibling skill. Voice is correctly third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Migrate existing AI agent projects', 'adapt a standard agent project to run on EdgeOne Makers', 'convert Express/Next.js API routes to Makers handlers', 'add platform capabilities (context.tools, context.sandbox, context.store)' — and names the specific source frameworks (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI).	3 / 3
Completeness	Explicitly answers both what ('Migrate existing AI agent projects ... to EdgeOne Makers platform conventions') and when via an explicit 'Use when the user wants to ...' clause, plus a 'Do NOT trigger for new agent projects' exclusion.	3 / 3
Trigger Term Quality	Uses natural developer-facing terms a user would actually say — framework names ('LangGraph', 'CrewAI', 'OpenAI Agents SDK'), 'Express/Next.js API routes', 'migrate', 'agent project' — with good coverage of the common variants rather than opaque jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (migrating existing projects to EdgeOne Makers) with distinct triggers and an explicit disambiguation against the sibling new-project skill ('use makers-agents instead'), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 12 suspicious	Warning

	Total	15 / 16 Passed

Repository: TencentEdgeOne/edgeone-makers-tools
Path: skills/makers-migration/SKILL.md
Commit: 77de93b

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.