CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auth-web-cloudbase

CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

Quality

75%

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 ./connectors/cloudbase-intl/skills/references/auth-web-cloudbase/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 strong, highly actionable integration guide: complete copy-paste v3 auth snippets, explicit provider/publishable-key validation steps, and a completion checklist. Its main weakness is token efficiency — the same session, anonymous-login, and verifyOtp warnings are repeated across four or more sections, and consolidating them would tighten the skill without losing coverage.

Suggestions

Consolidate the repeated accessKey/getLoginState/getSession session warnings into a single authoritative section (e.g. under the auth gate) and reference it from the other spots instead of restating the full explanation each time.

State the anonymous-login caveat once in the cookbook's anonymous sign-in entry and drop the repeated 'disabled by default, denied AI model permissions' phrasing from the other four locations.

Move the extended Supabase-compatibility comparison and the longest gotcha narratives into references/extended-guide.md to slim the SKILL.md overview.

DimensionReasoningScore

Conciseness

All content is CloudBase-specific API knowledge Claude cannot infer, but the same critical warnings are repeated many times: the accessKey/getLoginState/session point appears in four sections, the anonymous-login caveat in roughly five, and the data.verifyOtp-callback-vs-standalone point in four. Anchor 3 fits — mostly efficient but could be tightened substantially by deduplicating; it is not 2 because none of it explains concepts Claude already knows.

3 / 5

Actionability

Fully executable, copy-paste-ready snippets cover every common flow — password sign-in, signUp + data.verifyOtp, OTP sign-in, forgot password (resetPasswordForEmail + updateUser), getSession route guard, onAuthStateChange, signOut — plus concrete MCP calls like queryAppAuth(action="getPublishableKey") and manageAppAuth(action="patchLoginStrategy", ...). Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

A clear overall sequence exists (verify providers via auth-tool → obtain and persist publishable key → init SDK → implement flows → auth gate before user-scoped data → Completion Bar checklist) with explicit pre-flight validation (listProviders On: "TRUE", SMTP check, getLoginConfig). It is not 5 because the steps are scattered and duplicated across 'Common mistakes', the parameter map, and the cookbook, and there is no explicit validate → fix → retry feedback loop.

4 / 5

Progressive Disclosure

A single, well-signaled, one-level-deep reference (references/extended-guide.md, verified to exist) is linked both in an 'Extended guide' section and a reference index, and section headers organize the body. It is not 5 because the ~230-line SKILL.md inlines substantial gotcha and parameter detail that could partly live in the extended guide, keeping the overview from being lean.

4 / 5

Total

16

/

20

Passed

Description

65%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.

The description carves out a distinct, well-disambiguated niche and carries good natural keywords, but its capability statement stays generic and it lacks an explicit 'Use when...' trigger clause, capping completeness. Adding concrete named capabilities (password/OTP/OAuth sign-in, sign-up with verification, session guards) and an explicit trigger phrase would lift the mid dimensions.

Suggestions

Add an explicit 'Use when...' clause naming user-facing triggers, e.g. 'Use when building login, registration, session handling, or protected routes in a web app with @cloudbase/js-sdk'.

Replace the generic 'Web authentication solutions with multiple login methods and complete user management' with concrete named capabilities such as password sign-in, OTP sign-in/sign-up with verification codes, forgot-password flows, and session-based route guards.

Include common user synonyms (sign in, sign up, register, session, OAuth) alongside 'login' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('CloudBase Web Authentication Quick Guide for frontend integration') and a couple of actions ('multiple login methods', 'complete user management'), but these are generic rather than a list of specific concrete actions. It is not 4 because it never enumerates concrete capabilities like sign-in, sign-up, session handling, or OTP flows.

3 / 5

Completeness

The 'what' is reasonably clear ('Provides concise and practical Web authentication solutions with multiple login methods and complete user management'), but the only 'when' guidance is 'after auth-tool has already been checked', which is sequencing relative to a sibling skill, not an explicit user-need trigger clause. Per the rubric guidelines, a missing 'Use when...' clause or equivalent caps completeness at 3.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: 'CloudBase', 'Web', 'Authentication', 'login', 'user management', 'frontend integration'. It is not 5 because common synonyms a user would naturally say are missing ('sign in', 'sign up', 'register', 'session', 'OAuth', '@cloudbase/js-sdk').

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: 'CloudBase Web Authentication... frontend integration' distinguishes it from mini-program/native/server-side auth, and the explicit 'after auth-tool has already been checked' clause disambiguates from the sibling provider-setup skill. Minimal conflict risk.

5 / 5

Total

15

/

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

connectors/cloudbase-intl/skills/references/auth-web-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.