CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auth-nodejs-cloudbase

CloudBase Node SDK auth guide for server-side identity, user lookup, and custom login tickets. This skill should be used when Node.js code must read caller identity, inspect end users, or bridge an existing user system into CloudBase; not when configuring providers or building client login UI.

63

Quality

79%

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 ./plugin/cloudbase/skills/auth-nodejs-cloudbase/SKILL.md
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 technically solid, copy-oriented body with canonical API signatures, executable scenarios, and a clear agent workflow. Its weaknesses are structural: triplicated routing guidance, repeated init boilerplate in every scenario, an import/require mixing flaw that blocks true copy-paste readiness, and a fully monolithic file that never uses progressive disclosure.

Suggestions

Consolidate the 'Activation Contract', 'When to use this skill', and 'Summary' sections into a single routing section — they repeat the same use/don't-use guidance nearly verbatim, and state the SDK init block once instead of repeating it in all 9 scenarios.

Fix the module-system inconsistency in the code examples: scenarios mix `import tcb from "@cloudbase/node-sdk"` with `require(path.join(...))` and `exports.main`, which fails as both ESM and CommonJS — pick one module style (or show the credentials load in a CommonJS-consistent snippet) so examples are truly copy-paste ready.

Split the 'Node Auth APIs covered by this skill' signature list and the scenario library into references/ files (e.g. references/api.md and references/scenarios.md) and keep SKILL.md as a lean overview with one-level-deep, clearly signaled links.

DimensionReasoningScore

Conciseness

The API list, scenarios, and best-practice sections are lean and free of basic-concept padding, but the routing/trigger guidance is stated three times ('Activation Contract', 'When to use this skill', and 'Summary'), and the SDK init block is repeated in every one of the 9 scenarios. Mostly efficient but noticeably could be tightened — anchor 3, not 4 because the duplication goes beyond minor over-explanation, and not 2 because the technical core earns its tokens.

3 / 5

Actionability

Every scenario ships a complete code block with real SDK method names and parameter shapes (getUserInfo, getEndUserInfo, queryUserInfo with concrete platform values, createTicket with refresh/expire options), plus concrete constraints for customUserId. It falls short of fully copy-paste-ready because examples mix 'import' with require(...) and exports.main in the same file, which is not executable as either pure ESM or CommonJS — anchor 4, not 5.

4 / 5

Workflow Clarity

'How to use this skill' provides a clear 5-step numbered sequence (clarify runtime and responsibility, confirm env/SDK, pick scenario by responsibility, follow SDK shapes exactly, fall back to official docs when unsure), and scenarios demonstrate try/catch error handling. Minor validation gaps only — no explicit verification checkpoints — placing it at anchor 4; the destructive/batch cap does not apply since operations are reads and ticket issuance.

4 / 5

Progressive Disclosure

Section headers are clear and navigation within the file is easy, but all ~440 lines are monolithic in SKILL.md with no bundle files at all: the 'Node Auth APIs covered' reference block and the 9-scenario pattern library are content that could be split into references/ files. This matches anchor 3 ('content that should be separate is inline') rather than 4, since nothing is offloaded and the one-level-deep reference structure is absent.

3 / 5

Total

14

/

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: third-person, concrete, with explicit 'what' and 'when' clauses and a negative boundary that separates it from sibling skills. The only improvement space is broader natural trigger vocabulary (package name, cloud-function phrasing).

DimensionReasoningScore

Specificity

Names the domain plus three concrete actions ('read caller identity, inspect end users, or bridge an existing user system into CloudBase'), matching the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because finer capabilities (e.g. querying by login identifier, client IP retrieval) are not enumerated, and it exceeds 3 since more than 1-2 actions are given.

4 / 5

Completeness

Explicitly answers both: what ('CloudBase Node SDK auth guide for server-side identity, user lookup, and custom login tickets') and when ('This skill should be used when Node.js code must read caller identity, inspect end users, or bridge an existing user system into CloudBase'), with concrete trigger phrases plus a negative boundary clause. This matches the anchor-5 example pattern of what + when with concrete triggers.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'Node.js code', 'server-side', 'caller identity', 'user lookup', 'custom login tickets', 'user system'. A few natural terms users would plausibly say are absent (e.g. '@cloudbase/node-sdk', 'cloud function', 'who is calling'), so it sits at anchor 4 rather than the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

The explicit exclusion ('not when configuring providers or building client login UI') carves out a clear Node-only server-side identity niche, minimizing conflict with the sibling provider-setup, web-login, and raw-HTTP skills. Clear niche with distinct triggers, matching anchor 5.

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

plugin/cloudbase/skills/auth-nodejs-cloudbase/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.