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).

72

Quality

91%

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

82%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 that is highly actionable and concise, with clear sequencing and good progressive-disclosure intent. The main weaknesses are minor redundancy in the warning paragraph and the fact that the referenced language-specific files are not present in this environment.

Suggestions

Remove the redundant re-statement of 'read the corresponding skill file' in the ⚠️ IMPORTANT block, keeping only the non-duplicate guardrail ('Do NOT proceed with code generation until you have read it').

Add a one-line explicit checkpoint after Step 1 (e.g., 'Confirm the detected language matches the user's intent before reading the file') to strengthen the workflow feedback loop.

Co-locate the referenced ts/skill.md and py/skill.md (or note their canonical install path) so the one-level-deep references do not dead-end in stripped-down environments.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (a decision table plus two file pointers), but the '⚠️ IMPORTANT' paragraph re-emphasizes 'read the corresponding skill file' already stated in Step 2 — a minor redundancy that could be trimmed.

4 / 5

Actionability

For an instruction-only router, guidance is fully actionable: a concrete signal→language decision table, explicit file paths to read ('Read ts/skill.md' / 'Read py/skill.md'), and an enforced default (TypeScript when no signal). Absence of code is appropriate for a routing skill.

5 / 5

Workflow Clarity

Clear two-step sequence (determine language → read language file) with a real guardrail ('Do NOT proceed with any code generation until you have read it') and a missing-file checkpoint; minor gap is the lack of an explicit 'verify language choice' feedback loop.

4 / 5

Progressive Disclosure

Well-designed one-level-deep split (SKILL.md overview → ts/skill.md / py/skill.md) with clearly signaled markdown links and a sibling-skills note; however, the referenced ts/ and py/ bundle files are absent in this environment, so navigation hits a dead end that only a graceful fallback handles.

4 / 5

Total

17

/

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, third-person description that states concrete capabilities and an explicit 'Use when...' clause with multiple natural trigger terms. It is specific to the CloudBase/AG-UI niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build and deploy AI agents', 'Implements the AG-UI protocol for streaming agent-UI communication', 'deploying agent servers', 'using LangGraph/LangChain/CrewAI adapters', 'building custom adapters', 'understanding AG-UI protocol events', 'building web/mini-program UI clients' — with comprehensive coverage; not merely a domain label.

5 / 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') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms a user would actually say are well covered, including framework names ('LangGraph/LangChain/CrewAI'), 'agent servers', 'AG-UI protocol events', 'web/mini-program UI clients', plus package identifiers; comprehensive including synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Clear niche tied to CloudBase Agent SDK / AG-UI protocol with named adapters and language runtimes; distinct triggers make overlap with unrelated 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.