auth0-branding
Use when you want to (1) brand an Auth0 tenant's Universal Login to match a website or brand assets (colors, logo, fonts, page layout, text); (2) manually update one or more branding values (logos, colors, fonts, borders, backgrounds, text strings, or the page template) without extraction; (3) rewrite login text to match a voice and tone; (4) reset branding to Auth0 defaults; or (5) check whether a tenant is set up for branding to take effect end-to-end. Does not cover Advanced Customizations for Universal Login (ACUL); use the `acul-screen-generator` skill for that.
69
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly enumerates five specific use cases with rich trigger terms, explicitly states when to use it via a 'Use when' clause, and proactively delineates its boundary by excluding ACUL and redirecting to the appropriate skill. The only minor note is that it leads with 'Use when' without first stating what the skill does in a declarative sentence, but the use-case enumeration effectively serves that purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: branding Auth0 Universal Login, updating logos/colors/fonts/borders/backgrounds/text/templates, rewriting login text for voice and tone, resetting to defaults, and checking tenant setup. Very detailed and actionable. | 3 / 3 |
Completeness | The description opens with an explicit 'Use when' clause covering five distinct trigger scenarios, clearly answering both 'what does this do' and 'when should Claude use it'. It also includes a negative boundary ('Does not cover ACUL') with a redirect to the correct skill. | 3 / 3 |
Trigger Term Quality | Includes highly relevant natural keywords users would say: 'Auth0', 'Universal Login', 'branding', 'colors', 'logo', 'fonts', 'page layout', 'backgrounds', 'borders', 'voice and tone', 'tenant', 'reset branding', 'defaults'. Also explicitly distinguishes from ACUL with a cross-reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Auth0 tenant Universal Login branding, with explicit exclusion of ACUL and a pointer to the alternative skill. This clear niche and boundary makes conflict with other skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-architected skill with excellent progressive disclosure and workflow clarity — it clearly routes between 5 capabilities, enforces safety gates (tenant confirmation, destructive-path backups, WCAG checks), and delegates detail to well-organized reference files. Its main weaknesses are moderate verbosity in meta-instructions (prompt style, plan mode) and limited inline actionability since most executable guidance lives in reference files that weren't provided for evaluation. The Common Mistakes table is a strong practical addition.
Suggestions
Add at least one inline executable code example (e.g., a complete cURL call for PATCH /branding/themes/default or a CLI command sequence for the simplest capability) so the skill body is actionable without requiring reference file lookups.
Tighten the 'Prompt style' and 'Plan mode' sections — these contain important behavioral instructions but could be reduced by ~30% without losing clarity (e.g., consolidate the plan-mode bullet lists, reduce the prompt-style rationale text).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured and avoids explaining basic concepts Claude already knows, but it's quite lengthy with some sections that could be tightened — the 'Prompt style' section is verbose with meta-instructions about when to use pickers vs free text, and the 'Plan mode' section is detailed but could be more concise. The capabilities table and key concepts are efficient. | 2 / 3 |
Actionability | The skill provides concrete CLI commands (auth0 tenants list, auth0 test login) and references specific API endpoints and patterns (GET/PATCH /branding/themes/default), but the actual executable guidance is deferred to reference files (capability-brand.md, api.md, examples.md) which are not provided. The Common Mistakes table is actionable, but the main capabilities lack inline executable examples. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints: active-tenant confirmation before writes, WCAG contrast warnings, template-tag validation, merge-before-PUT for custom text, scope pre-checks for destructive operations, and a post-apply browser verification step. The plan mode section clearly delineates what's allowed vs deferred. Feedback loops are present (e.g., Capability 4's backup gate, review prompts that allow inline edits). | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md serves as a clear overview with well-signaled one-level-deep references to 9 reference files covering each capability, API details, examples, and advanced topics. Each capability has a brief description inline and a clear pointer to its dedicated reference file. Related skills and external docs are cleanly organized. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- Repository
- auth0/agent-skills
- Commit
bdf0dc2
- 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.