cloudbase-agent

Build and deploy AI agents with CloudBase Agent SDK (TypeScript & Python). Implements the AG-UI protocol for streaming agent-UI communication. Use when deploying agent servers, using LangGraph/LangChain/CrewAI adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients. Supports both TypeScript (@cloudbase/agent-server) and Python (cloudbase-agent-server via FastAPI).

Quality

81%

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

71%Weight 40%Scale 1-5

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

The body is an admirably lean router with a clear sequenced workflow, but its core value depends on referenced language skill files (ts/skill.md, py/skill.md) that are not present in this environment, weakening actionability and progressive disclosure.

Suggestions

Ensure the referenced bundle files ts/skill.md and py/skill.md ship with the skill, or add an explicit fallback path for when they are missing.

Add a brief note on how to handle the case where the chosen language skill file is absent (mirroring the existing sibling-skill guidance), so the workflow has a complete validation/recovery checkpoint.

Consider including a minimal inline fallback (e.g., a one-line quick start per language) so the skill remains actionable when the referenced files are unavailable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a routing table, two short steps, and a warning, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	The routing steps and language-detection table are concrete, but the core executable instruction is 'read ts/skill.md / py/skill.md', and those referenced files are not present in this environment, leaving the guidance incomplete rather than copy-paste executable.	3 / 5
Workflow Clarity	A clear two-step sequence with an explicit checkpoint ('MUST read the file; do NOT proceed until you have read it') is present; minor gap is the lack of explicit handling when the referenced file is absent (only the sibling note covers a related case).	4 / 5
Progressive Disclosure	Detail is appropriately split one level deep into ts/skill.md and py/skill.md with clearly signaled links, but those referenced bundle files are missing from the environment, so the disclosed structure cannot actually be navigated, capping the score at 3.	3 / 5
	Total	15 / 20 Passed

Description

91%Weight 40%Scale 1-5

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

The description is strong: concrete capabilities, rich natural trigger terms, and an explicit 'Use when...' clause answer both what and when clearly. It is a well-differentiated, comprehensive router description.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions (build/deploy agent servers, use LangGraph/LangChain/CrewAI adapters, build custom adapters, understand AG-UI events, build UI clients) plus concrete package names, with only minor coverage gaps.	4 / 5
Completeness	It explicitly states what the skill does (build/deploy agents with the CloudBase Agent SDK implementing AG-UI) and provides an explicit 'Use when...' clause with multiple concrete trigger scenarios.	5 / 5
Trigger Term Quality	Comprehensive natural terms including framework names (LangGraph/LangChain/CrewAI), AG-UI protocol events, web/mini-program UI clients, and package identifiers cover synonyms and specific tooling users would actually say.	5 / 5
Distinctiveness Conflict Risk	The CloudBase Agent SDK and AG-UI protocol framing carves a clear niche with distinct triggers, with only minor overlap risk against generic agent-deployment skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: plugin/cloudbase/skills/cloudbase-agent/SKILL.md
Commit: f07c33c

Reviewed: 4 days 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.