auth0-custom-domains
Use when setting up, troubleshooting, managing, removing, or checking the health of an Auth0 custom authentication domain (e.g. login.example.com), OR when diagnosing an error (400/403/404/409/429) from the /custom-domains Management API — especially Free-tier 403s (credit card on file, not a plan upgrade), self-managed cert 403s, PATCH-type 400s, `operation_not_supported` on `relying_party_identifier`, and 409 domain-already-exists. Handles CNAME creation in the user's DNS provider (Cloudflare, AWS Route 53, Azure DNS automated; other registrars guided), verification polling, Multiple Custom Domains (MCD), default-domain selection, TLS policy, client-IP header, per-domain passkey relying party identifier, and domain metadata.
94
92%
Does it follow best practices?
Impact
98%
1.71xAverage score across 3 eval scenarios
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 exceptionally well-crafted skill description that clearly defines its scope, provides rich trigger terms covering both common and edge-case scenarios, and explicitly states when it should be used. The description is dense with specific, actionable details — from exact error codes to named DNS providers — making it highly distinguishable and easy for Claude to select appropriately. The only minor concern is that the description is quite long, but the density is justified by the complexity of the domain.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists numerous specific concrete actions: setting up, troubleshooting, managing, removing, checking health of Auth0 custom domains, diagnosing specific error codes (400/403/404/409/429), CNAME creation, verification polling, MCD, default-domain selection, TLS policy, client-IP header, per-domain passkey relying party identifier, and domain metadata. | 3 / 3 |
Completeness | Explicitly answers both 'what' (handles CNAME creation, verification polling, MCD, TLS policy, error diagnosis, etc.) and 'when' with a clear 'Use when...' clause covering setup, troubleshooting, managing, removing, checking health, and diagnosing specific API errors. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'custom domain', 'login.example.com', specific error codes (400/403/404/409/429), 'custom-domains Management API', 'Free-tier 403', 'CNAME', DNS provider names (Cloudflare, AWS Route 53, Azure DNS), 'TLS policy', 'passkey relying party identifier', and 'domain-already-exists'. These are highly specific terms a user troubleshooting Auth0 custom domains would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely distinct niche — Auth0 custom authentication domains with specific API endpoints, error codes, and DNS provider integrations. Very unlikely to conflict with other skills due to the highly specialized domain and detailed trigger conditions. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that excels at progressive disclosure and actionability, with a well-designed capability-routing architecture and an especially valuable error-code triage table that prevents common misdiagnosis. The workflow is clear with appropriate safety checks for destructive operations. The main weakness is moderate verbosity — the meta-commentary about the skill's design philosophy and interaction style guidance could be trimmed without losing clarity.
Suggestions
Trim the 'Overview' section that explains the capability-based design rationale — Claude doesn't need to understand why the skill is structured this way, just how to use it.
Condense the 'Interaction style' section; the examples of how to ask questions are overly prescriptive for Claude and could be reduced to 1-2 bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-organized and avoids explaining basic concepts Claude already knows, but it's verbose in places — the 'Overview' section explaining the capability-based design philosophy and the detailed 'Interaction style' section with examples of how to ask questions add tokens without proportional value. The Key Concepts table is borderline; some entries (like CNAME Record) explain things Claude knows, though the Auth0-specific context justifies most entries. | 2 / 3 |
Actionability | The error-code triage table provides highly specific, actionable diagnoses with exact fixes (e.g., 'Fix at Dashboard → Tenant Settings → Billing'). Prerequisites include concrete commands (`auth0 tenants list`, `aws sts get-caller-identity`, `claude mcp add ...`). The capabilities table clearly routes to specific reference files with defined flows. While the main file delegates detailed steps to reference files, the content present is concrete and executable. | 3 / 3 |
Workflow Clarity | The skill has a clear routing workflow: error-code triage first, then capability selection, then follow the reference file. Prerequisites include explicit validation steps (confirm active tenant before first CLI command, require explicit confirmation for mutating calls). The tenant-check workflow has a clear sequence with error recovery ('If it's wrong, stop and have the user run...'). The capability-based design with safety checks and hand-offs is well-sequenced. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md serves as a clear lobby/overview with well-signaled one-level-deep references to capability files, provider files, API reference, and advanced topics. The References section is comprehensive with clear descriptions. The Common Mistakes table links to canonical treatments in specific capability files. Navigation is intuitive with the capabilities table pointing to specific reference paths. | 3 / 3 |
Total | 11 / 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.