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).

65

Quality

80%

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

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

67%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 a well-designed language router: lean, concrete, and clearly sequenced, with a sensible default and a strong read-before-code gate. Its critical flaw is structural — both referenced skill files are absent from the bundle, so progressive disclosure fails at the first hop.

Suggestions

Ship ts/skill.md and py/skill.md alongside SKILL.md — both routing targets the body instructs Claude to read are missing, leaving the router pointing at nothing.

Extend the Step 1 table with a precedence rule for conflicting signals (e.g., the user mentions both TypeScript and Python), mirroring the existing 'No clear signal → TypeScript' default.

De-duplicate the TypeScript-default rule and the MUST-read instruction (each is stated twice); one statement of each is sufficient.

DimensionReasoningScore

Conciseness

The ~30-line router body is lean and assumes Claude's competence (no concept explanations, no padding), but the TypeScript default is stated twice (paragraph and table row) and the ⚠️ paragraph repeats Step 2's read-the-file instruction. Efficient overall — these are minor instances that could be trimmed, keeping it below a 5.

4 / 5

Actionability

Concrete, executable routing guidance: an exact signal-to-language table, an explicit default rule, and precise file paths (ts/skill.md, py/skill.md) with a MUST-read gate. Not a 5 because the primary routing targets are missing from the bundle (verified: neither ts/skill.md nor py/skill.md exists), so the guidance cannot actually be executed as shipped here; not a 3 because what is written is specific and unambiguous rather than pseudocode.

4 / 5

Workflow Clarity

Steps 1–2 are clearly sequenced with an explicit default and a hard checkpoint ("Do NOT proceed with any code generation until you have read it"), appropriate for a single-purpose routing skill. Minor gaps: the conflicting-signals case (user mentions both TypeScript and Python) has no precedence rule, and no fallback is given for a missing ts/py file (only for sibling skills).

4 / 5

Progressive Disclosure

The design intent is correct — a lean router pointing one level deep to per-language skill files — but the actual bundle contains no references/, scripts/, or assets/ directories, and neither referenced path (ts/skill.md, py/skill.md) exists, so the router points at nothing. Scored against the actual bundle structure per the guidelines; the missing targets leave disclosure broken in practice despite the clear signaling, which is worse than the "references present but not clearly signaled" anchor at 3.

2 / 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 strong description: concrete capabilities, an explicit multi-condition "Use when" clause, named packages/frameworks, and third-person voice throughout. The only gap is a handful of natural trigger phrasings around UI/frontend work.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Build and deploy AI agents", "deploying agent servers", "using LangGraph/LangChain/CrewAI adapters", "building custom adapters", "building web/mini-program UI clients" — plus concrete package names for both languages (@cloudbase/agent-server, cloudbase-agent-server via FastAPI).

5 / 5

Completeness

Explicitly answers both: the "what" ("Build and deploy AI agents with CloudBase Agent SDK... Implements the AG-UI protocol for streaming agent-UI communication") and the "when" via a concrete "Use when..." clause enumerating five trigger conditions.

5 / 5

Trigger Term Quality

Good coverage of natural terms users would say ("deploy agent servers", "LangGraph/LangChain/CrewAI adapters", "AG-UI protocol events", "web/mini-program UI clients", "FastAPI"), but a few natural phrasings such as "build an agent UI/frontend" or "stream agent events to a client" are absent. Not a 5 because the anchor expects comprehensive synonym coverage, and not a 3 because the present keywords are specific and varied rather than generic.

4 / 5

Distinctiveness Conflict Risk

Clear niche — the CloudBase Agent SDK and AG-UI protocol with named adapters and packages — with distinct triggers; minimal risk of firing for a generic agent or deployment skill.

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.

Validation — 14 / 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.