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.

56

Quality

70%

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/.claude/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

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.

A highly actionable, SDK-specific guide with executable code for every auth flow and explicit validation gates (MCP provider checks, Completion Bar). Its main weakness is heavy redundancy — the session/accessKey, anonymous-login, and verifyOtp warnings are each repeated many times across Common mistakes, Parameter map, Quick Start, and the cookbook — and a duplicated Prerequisites section, costing significant tokens without adding information.

Suggestions

State each critical warning exactly once in the cookbook (its natural home) and reference it with one-line pointers from Common mistakes and Parameter map — the accessKey/session, anonymous-login, getSession(), and verifyOtp rules are currently each repeated 3–6 times, and deduplicating them would cut roughly a third of the file.

Merge the duplicated Prerequisites content: the Overview section lists "**Prerequisites**: CloudBase environment ID (env)" and "(region)" and then a full "## Prerequisites" section follows immediately with overlapping MCP steps.

Fold the overlapping "Common mistakes / gotchas" and "Parameter map" bullets into a single section (or move the long per-parameter prose into references/extended-guide.md), since many bullets (signUp-username conditional, publishable key handling) state the same rule in both places.

DimensionReasoningScore

Conciseness

The body states the same critical warnings many times over: the "accessKey alone does not create a gateway-authenticated session" / anonymous-login-disabled warning appears in Common mistakes ("Assuming publishable accessKey alone is enough for NoSQL CRUD"), again in the note "anonymous login is disabled by default", again in the Parameter map ("accessKey alone does not create a gateway-authenticated session"), in Quick Start comments ("accessKey alone ≠ a login session"), in the cookbook ("Anonymous sign-in — demo-only, not a default"), and in the auth-gate rule; the getSession-vs-getLoginState and verifyOtp-callback warnings are similarly each repeated 3–4 times. This matches anchor 2 ("Noticeably verbose; several unnecessary explanations or padded sections") — the content is SDK-specific and novel (no basic-concept teaching), but roughly a third of the file is duplicate padding that could be stated once. It is above anchor 1 because nothing explains concepts Claude already knows, and not anchor 3 because the duplication is structural (whole bullets duplicated across sections), not minor tightening.

2 / 5

Actionability

The cookbook gives copy-paste-ready executable code for every common case — `auth.signInWithPassword({ username, password })`, `auth.signUp({ email, password })` + `data.verifyOtp({ token: code })`, `auth.resetPasswordForEmail(email)` + `data.updateUser({ nonce, password })`, `auth.getSession()`, `auth.onAuthStateChange(...)`, `auth.signOut()`, and the auth-gate snippet — plus concrete MCP commands (`queryAppAuth(action="getPublishableKey")`, `manageAppAuth(action="patchLoginStrategy", patch={ usernamePassword: true })`). This matches anchor 5 ("Fully executable; copy-paste ready code or commands; specific examples cover the common cases") — not anchor 4 because there are no missing key details; even error-recovery signatures ("messageId is required", gateway 401) are given for diagnosis.

5 / 5

Workflow Clarity

A clear sequence exists via the Activation Contract ("activate auth-tool-cloudbase before auth-web-cloudbase") → Prerequisites (provider and publishable-key checks via MCP before frontend code) → Quick Start init → cookbook flows → the "Completion Bar" checklist, and error signatures double as feedback loops ("seeing that error means the callback form was skipped"). This fits anchor 4 ("Clear sequence with most checkpoints present; minor validation gaps") rather than 5 because the sequence is distributed across five sections instead of one coherent procedure — the reader must stitch the ordering together, and the middle steps' checkpoints are implicit in scattered gotchas rather than explicit per-step validations.

4 / 5

Progressive Disclosure

Structure is good: the body is headered (Activation Contract, Quick Start, cookbook, Completion Bar), and bulk detail is split into one well-signaled, one-level-deep reference — "read [extended-guide.md](references/extended-guide.md)" — which exists, is internally organized (Login Methods / User Management / User Type / Complete Example), and is additionally surfaced in a "Reference index" section. This matches anchor 4 ("Good structure; most content is appropriately placed; references mostly clear; minor organization gaps") — not 5 because only one reference file exists and a fair amount of inline content (repeated warnings and parameter-map bullets) could itself live in or be deduplicated toward the extended guide.

4 / 5

Total

15

/

20

Passed

Description

61%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 correctly identifies a niche (CloudBase Web auth, frontend, post-tool-check) with usable natural keywords, but it opens with pipeline-ordering prose instead of an explicit "Use when..." trigger and pads the capability statement with generic filler ("concise and practical... solutions"). Adding a trigger clause and naming the concrete login flows would lift completeness and specificity.

Suggestions

Add an explicit "Use when..." trigger clause naming user-facing situations, e.g. "Use when the user needs a Web login page, registration, sign-in, or session handling built with @cloudbase/js-sdk".

Replace the filler "Provides concise and practical Web authentication solutions" with named concrete actions (password/OTP/OAuth sign-in, verification-code registration, session guards for protected routes) to raise specificity.

Include natural trigger synonyms users would actually say — "sign in", "sign-in", "registration", "session" — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("CloudBase Web Authentication Quick Guide") and 1–2 concrete capabilities ("multiple login methods and complete user management", "frontend integration"), but "Provides concise and practical Web authentication solutions" is generic filler rather than a concrete action. This matches anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") — it falls short of anchor 4's "lists several specific actions" because no specific login methods, session handling, or route-guard actions are named, and exceeds anchor 2 because the domain and capabilities are concrete, not minimal.

3 / 5

Completeness

The "what" is clear ("Provides... Web authentication solutions with multiple login methods and complete user management"), but the only "when"-like phrase is "after auth-tool has already been checked" — a pipeline precondition about sibling-skill ordering, not an explicit user-facing trigger (no "Use when..." clause or equivalent). Per the guideline that a missing 'Use when...' clause caps completeness at 3, this matches anchor 3 ("Has a clear 'what' but 'when' is missing or only weakly implied") rather than anchor 4's "both what and when".

3 / 5

Trigger Term Quality

Good natural-keyword coverage: "CloudBase", "Web", "Authentication", "login methods", "user management", "frontend integration" are terms a user needing this skill would plausibly say. This fits anchor 4 ("Good keyword coverage; a few natural terms missing") — not anchor 5 because common variations like "sign in", "registration", "session", or the SDK name "@cloudbase/js-sdk" are absent, and not anchor 3 because coverage goes beyond a single domain keyword.

4 / 5

Distinctiveness Conflict Risk

The "CloudBase Web" + "frontend integration after auth-tool has already been checked" scoping carves a clear niche and explicitly disambiguates from the setup-side sibling skill. This matches anchor 4 ("Mostly distinct; minor overlap risk with closely related skills") — there is residual overlap risk with the closely related auth-tool-cloudbase and any mini-program/native auth siblings sharing "CloudBase authentication" triggers, so it does not reach anchor 5's "minimal conflict risk", but it is well above the generic overlap of anchors 2–3.

4 / 5

Total

14

/

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/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.