CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudbase-mcp

CloudBase MCP reference. Use when connecting local or remote MCP, calling tools from the shell with mcporter, reading tool schemas, choosing the domestic or international endpoint, setting site, region, cloud mode, or plugin flags, or contributing a fix to the open-source MCP server, skills, or CLI.

Quality

91%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 well-engineered reference skill: concrete commands and exact API call shapes make it fully actionable, the diagnostic workflow has explicit validation checkpoints and recovery loops, and detail is properly deferred to clearly signaled one-level-deep references. Only conciseness falls slightly short due to a handful of trimmable framing sentences.

DimensionReasoningScore

Conciseness

The body is dense with CloudBase-specific facts (endpoints, env vars, auth file paths, error codes) and explains nothing Claude already knows, but a few setup sentences could be trimmed ('Four different failures look alike from the outside and need different fixes', 'This is the usual path'), leaving it efficient rather than fully lean.

4 / 5

Actionability

Guidance is copy-paste ready throughout: executable commands ('npx mcporter list | grep cloudbase', 'npx mcporter call cloudbase.queryEnv action=list --output json'), a complete mcporter.json snippet, and exact tool-call shapes ('auth(action="status")', 'queryFunctions(action="getFunctionUploadUrl")') covering the common cases.

5 / 5

Workflow Clarity

The readiness check is a numbered four-step triage with a state-to-call-to-'Fixed looks like' table, explicit validation gates ('require auth_status: "READY" plus the expected current_env_id before any cloud write'), and recovery loops (reconnect then verify the tool appears; set_env then verify the env matches), fully matching the top anchor.

5 / 5

Progressive Disclosure

References are one level deep and clearly signaled with when-to-read guidance ('Read that file before login, environment binding, or manageEnv'; 'Read references/issue-report.md first'), bulk detail is appropriately split into references/issue-report.md and sibling files, and the inline content is decision rules — an easy-to-navigate overview structure.

5 / 5

Total

19

/

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 description with an explicit, detailed 'Use when...' clause and concrete domain-specific trigger terms in third-person voice. The main weakness is that the body's troubleshooting and issue-reporting functions are absent from both the capability list and the triggers, leaving two dimensions just short of comprehensive.

DimensionReasoningScore

Specificity

The description enumerates many concrete activities ('connecting local or remote MCP', 'calling tools from the shell with mcporter', 'reading tool schemas', 'choosing the domestic or international endpoint', 'setting site, region, cloud mode, or plugin flags'), but the body's substantial troubleshooting/issue-reporting scope is not covered, leaving minor gaps rather than comprehensive coverage.

4 / 5

Completeness

'CloudBase MCP reference' states the what, and an explicit 'Use when...' clause with multiple concrete trigger phrases (mcporter calls, endpoint choice, site/region/cloud-mode/plugin flags, contributing fixes) clearly answers the when, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrasings like 'local or remote MCP', 'mcporter', 'tool schemas', 'domestic or international endpoint', and 'contributing a fix' match what users would actually say, but common utterances for the body's troubleshooting functions ('tool failed', 'auth error') are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (CloudBase MCP via mcporter, endpoints, and MCP server contribution) with distinct triggers; only trivial overlap exists with the sibling CLI skill through the 'contributing a fix to... CLI' phrase, keeping conflict risk minimal.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

TencentCloudBase/CloudBase-AI-Toolkit

Path

config/.claude/skills/cloudbase-mcp/SKILL.md

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.