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.

60

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 ./config/source/skills/auth-web-cloudbase/SKILL.md

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

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 skill: executable copy-paste code for every auth flow, concrete MCP verification steps, an explicit ordering contract with the sibling provider-setup skill, and a completion checklist. Its main weaknesses are significant verbatim repetition of the same three warnings across four sections and a workflow spread across multiple sections rather than one consolidated sequence with feedback loops.

Suggestions

Consolidate each repeated warning (accessKey ≠ session / gateway 401, verifyOtp callback vs standalone, getSession vs deprecated getLoginState) into one canonical section and use one-line back-references elsewhere.

Move the Supabase compatibility comparison and the longest gotcha bullets into references/extended-guide.md to reduce body tokens.

Present one numbered end-to-end flow (verify provider → get/persist key → init → implement → Completion Bar) so the sequence and its validation checkpoints read as a single track.

DimensionReasoningScore

Conciseness

Most content is high-value, non-obvious SDK knowledge (verifyOtp callback form, misleading getLoginState uid, gateway 401 semantics), but the same critical warnings are repeated nearly verbatim three to four times — the accessKey/session/401 warning appears in Common mistakes, the Parameter map, Quick Start comments, and the cookbook, and the verifyOtp-callback warning likewise recurs across sections. That is more than the 'minor instances' of anchor 4; consolidating each warning to one canonical location with brief back-references would tighten it without losing clarity.

3 / 5

Actionability

The cookbook provides copy-paste-ready executable snippets for every flow (password sign-in, signUp + data.verifyOtp, OTP sign-in, forgot password, getSession guard, onAuthStateChange, signOut, auth gate) plus concrete MCP commands like queryAppAuth(action="listProviders") and manageAppAuth(action="patchLoginStrategy", patch={usernamePassword: true}), with a default UI contract and a Completion Bar checklist. Code covers the common cases completely and branches on error first.

5 / 5

Workflow Clarity

Sequencing is explicit via the Activation Contract (auth-tool-cloudbase first, then this skill), ordered prerequisites (getPublishableKey → ensurePublishableKey → persist to .env.local), MCP provider verification before writing code, and a Completion Bar checklist that gates task completion. It falls short of anchor 5 because the full workflow is distributed across four sections rather than one sequence with explicit validate→fix→retry feedback loops, leaving minor checkpoint gaps.

4 / 5

Progressive Disclosure

The bundle is well structured: a real one-level-deep reference (references/extended-guide.md, verified to exist) clearly signaled from the body and listed in a reference index, with the body staying at overview + cookbook altitude (~229 lines vs the 500-line limit). Minor gaps keep it from anchor 5: some long gotcha bullets and the Supabase comparison block could live in the reference, and the reference partially duplicates body cookbook content (login methods).

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 is specific to a clear niche (CloudBase Web auth for frontend integration) with good trigger keywords and excellent distinctiveness, but it lacks an explicit 'Use when...' trigger clause and its capability list stays at the level of generic claims ('solutions', 'complete user management') rather than concrete named actions. It reads as above-average but not top-tier.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs a web login page, registration flow, session handling, or protected routes with @cloudbase/js-sdk.'

Replace generic claims ('Web authentication solutions', 'complete user management') with concrete named capabilities such as 'password/OTP/OAuth sign-in, sign-up with verification codes, session guards, and user management'.

Include natural synonym terms users say ('sign in', 'log in', 'register', 'login page', 'auth') to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ('CloudBase Web Authentication', 'frontend integration') and a couple of capability areas ('multiple login methods', 'complete user management'), but these read as generic capability claims rather than several specific concrete actions — no named methods (password/OTP/OAuth), session handling, or route guards. It matches 'Names domain and 1-2 concrete actions, but not comprehensive' more than the anchor 4 example that lists several distinct executable actions; it is clearly above anchor 2, which only names a domain with minimal actions.

3 / 5

Completeness

The 'what' is stated ('Provides concise and practical Web authentication solutions with multiple login methods and complete user management'), but there is no 'Use when...' clause or equivalent user-task trigger guidance — the only 'when'-like phrase is a sequencing condition ('after auth-tool has already been checked'), which does not tell the model when a task calls for this skill. Per the guideline that missing explicit trigger guidance caps completeness at 3, this cannot score 4 even though the what/when split is otherwise present.

3 / 5

Trigger Term Quality

Natural phrases a user would say are present: 'CloudBase', 'Web', 'Authentication', 'login methods', 'user management', 'frontend integration'. Coverage is good but a few natural terms are missing — no 'sign in/sign up', 'register', 'session', or '@cloudbase/js-sdk'/'web auth' variations, so it sits between anchor 3 ('some relevant keywords, missing variations') and anchor 5 (comprehensive with synonyms), closer to anchor 4.

4 / 5

Distinctiveness Conflict Risk

'CloudBase Web Authentication Quick Guide for frontend integration' carves out a clear niche with distinct triggers, and the explicit sequencing against 'auth-tool' disambiguates its nearest sibling skill. Minimal conflict risk — no overlap with generic auth or document skills.

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

config/source/skills/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.