CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A clean, concise language-router body with a clear two-step workflow and an explicit proceed-gate, but its substance is entirely deferred to ts/skill.md and py/skill.md, which are not present in the bundle. This leaves the body non-actionable for the skill's core purpose and breaks the referenced navigation.

Suggestions

Ensure ts/skill.md and py/skill.md ship in the bundle so the router's referenced navigation resolves to real files.

Add a minimal inline quick-start snippet (e.g. one server-bootstrap line per language) so the body is actionable even before the referenced file is read.

Collapse the '⚠️ IMPORTANT' block into Step 2 to remove the restated read-the-file redundancy.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no concept over-explanation, but the '⚠️ IMPORTANT' block restates Step 2's read-the-file directive, a minor redundancy that could be trimmed.

4 / 5

Actionability

Routing guidance is concrete (a decision table and explicit 'Read ts/skill.md' / 'Read py/skill.md' directives), but the body contains no executable code or commands for the skill's stated build/deploy purpose — all actual guidance is deferred to the referenced files.

3 / 5

Workflow Clarity

A clear two-step sequence (determine language → read the corresponding file) with an explicit gate ('Do NOT proceed with any code generation until you have read it'), though there is no validation/feedback loop — acceptable since routing is non-destructive.

4 / 5

Progressive Disclosure

Structure and signaling are good (one-level-deep links to ts/skill.md and py/skill.md), but those referenced language files are absent from the bundle, so the navigation the overview points to leads to dead ends.

3 / 5

Total

14

/

20

Passed

Description

100%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.

A strong, well-constructed description in third-person voice that explicitly states capabilities and provides concrete 'Use when' trigger guidance with named frameworks and packages. It is concise yet comprehensive with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build and deploy AI agents', 'Implements the AG-UI protocol for streaming agent-UI communication', 'using LangGraph/LangChain/CrewAI adapters, building custom adapters', 'building web/mini-program UI clients' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (build/deploy agents, implement AG-UI protocol) and 'when' via a concrete 'Use when deploying agent servers, using ... adapters, building custom adapters, understanding ... events, or building ... UI clients' clause.

5 / 5

Trigger Term Quality

Covers natural terms a user would say ('AI agents', 'agent servers', 'LangGraph', 'LangChain', 'CrewAI', 'AG-UI protocol events', 'web/mini-program UI clients') plus synonyms for both languages and both SDK package names (@cloudbase/agent-server, cloudbase-agent-server).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear CloudBase Agent SDK / AG-UI protocol niche with named adapters and package identifiers, making conflict with generic agent skills minimal.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.