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).

68

Quality

84%

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

The canonical home for this skill is cloudbase-agent in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

81%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, well-structured language-router skill that efficiently routes to TypeScript or Python sub-skills with an explicit default and clear sequence. Its main weakness is that the actual executable depth lives entirely in referenced files that are not present in this environment.

Suggestions

Consolidate the Step 2 read-file instruction and the ⚠️ IMPORTANT block to remove the reiteration and tighten conciseness.

Ensure the referenced language files (ts/skill.md, py/skill.md) ship alongside SKILL.md so the router's one-level-deep links actually resolve in every install context.

Add a one-line fallback (e.g., a minimal inline quick-start) so the skill remains actionable even when the referenced sub-skill files are unavailable.

DimensionReasoningScore

Conciseness

Lean router body with a compact decision table and explicit file paths; the ⚠️ IMPORTANT block reiterates the read-file instruction already stated in Step 2, a minor instance of over-emphasis that could be trimmed, placing it just below the 5 anchor.

4 / 5

Actionability

Gives concrete, executable direction — a signal-to-language table and exact paths (ts/skill.md, py/skill.md) to read — with a clear default rule; minor gap is that the substantive executable content is delegated to the referenced language files rather than present inline.

4 / 5

Workflow Clarity

A simple two-step router (determine language → read the language-specific file) that is unambiguous and clearly sequenced with no destructive/batch operations requiring validation, satisfying the simple-skill exception at 5.

5 / 5

Progressive Disclosure

Exemplary one-level-deep structure — a thin overview router delegating to self-contained language files via clearly signaled markdown links — but the referenced files (ts/skill.md, py/skill.md) and the sibling skill are absent in this environment, a minor navigation gap that keeps it below 5 despite graceful missing-file handling.

4 / 5

Total

17

/

20

Passed

Description

87%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, third-person description that concretely states capabilities and provides explicit "Use when" trigger guidance with named libraries and protocols. It is highly distinct and complete, with only minor room to broaden trigger-term synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Build and deploy AI agents", "Implements the AG-UI protocol for streaming agent-UI communication", "building custom adapters", "building web/mini-program UI clients" — but the "Use when" list blends use-cases with capabilities, leaving minor coverage gaps versus the comprehensive anchor at 5.

4 / 5

Completeness

Explicitly answers both: what ("Build and deploy AI agents with CloudBase Agent SDK... Implements the AG-UI protocol") and when ("Use when deploying agent servers, using...adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients"), matching the concrete-trigger-phrases anchor at 5.

5 / 5

Trigger Term Quality

Good natural-term coverage with "deploying agent servers", "LangGraph/LangChain/CrewAI adapters", and "AG-UI protocol events" — terms a user would actually say — but a few common synonyms/variants are missing, falling just short of the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche tied to CloudBase Agent SDK, the AG-UI protocol, and named package identifiers (@cloudbase/agent-server, cloudbase-agent-server) with distinct triggers and minimal overlap risk, matching the 5 anchor.

5 / 5

Total

18

/

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.