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).

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/cloudbase-agent/SKILL.md

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

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 concise, well-structured language router, but its core action depends on ts/skill.md and py/skill.md which are not present in the bundle, weakening actionability and progressive disclosure.

Suggestions

Ship the referenced ts/skill.md and py/skill.md bundle files so the router's primary instruction (read the language-specific file) can actually be followed.

Tighten the redundant ⚠️ IMPORTANT block — it restates Step 2's "read the file before generating code" instruction and can be merged.

Add an explicit checkpoint confirming the language decision (and the TypeScript-default rule) before branching to the language-specific file, making the workflow validation-complete.

DimensionReasoningScore

Conciseness

Lean routing table plus two routing bullets with only minor redundancy (the ⚠️ block restates Step 2's instruction to read the file first); mostly assumes Claude's competence.

4 / 5

Actionability

Concrete routing signals and explicit "read ts/skill.md / py/skill.md" links are given, but those referenced files are absent from the bundle, so the executable target is missing in this environment.

3 / 5

Workflow Clarity

Clear two-step sequence (determine language → read the matching skill file) with an unambiguous default-to-TypeScript rule; no destructive/batch ops so the validation cap does not apply, though a checkpoint for the default-enforcement is only implicit.

4 / 5

Progressive Disclosure

Structure is good and one-level-deep references are clearly signaled, but scoring against the actual bundle shows ts/skill.md and py/skill.md do not exist, so navigation is broken rather than well-placed.

3 / 5

Total

14

/

20

Passed

Description

92%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 specific, well-scoped description that clearly states capabilities and concrete use-when triggers in third person. Only minor room for more synonyms/extensions in trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Build and deploy AI agents", "Implements the AG-UI protocol for streaming agent-UI communication") plus named adapters and exact package identifiers (@cloudbase/agent-server, cloudbase-agent-server), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both the "what" (build/deploy agents with the CloudBase Agent SDK implementing AG-UI) and the "when" ("Use when deploying agent servers, using ... adapters, building custom adapters, understanding AG-UI protocol events, or building ... UI clients").

5 / 5

Trigger Term Quality

Strong natural phrases ("deploying agent servers", "LangGraph/LangChain/CrewAI adapters", "web/mini-program UI clients") but lacks some common synonyms and file extensions, falling just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (CloudBase Agent SDK, AG-UI protocol) with distinct, specific triggers (named adapters, mini-program clients) and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.