configuration-http-integrations

caddy-security HTTP integration Caddyfile configuration. Use when creating, reviewing, or modifying route-level authenticate and authorize directives, portal and protected route separation, matcher forms, same-host or split-host auth wiring, auth URL routing and alignment, auth-path collisions such as upstream /auth routes, dedicated auth hosts with root-mounted portals, portal-owned path prefixes to avoid, or unnecessary global Caddy directive-order overrides.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is dense, actionable, and free of basic-concept padding, with clear scenario branches and a validation checkpoint. Its one weakness is progressive disclosure: everything is inline with no reference files to absorb detail.

Suggestions

Move the reserved portal-owned prefix list ("Avoid Portal-Owned Prefixes") into a references file (e.g. references/portal-owned-paths.md) and keep SKILL.md as a short overview pointing to it, reducing inline length.

Extract the repeated full Caddyfile deployment shapes (same-host, split-host, dedicated auth host) into a references/examples.md, leaving concise minimal snippets inline and signaling the fuller examples one level deep.

Add the exact validation command (or a scripts/ entry) for the adapt test rather than only referencing the testing-and-ci skill, so the workflow checkpoint is self-contained.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence — it never explains what Caddy, JWT, or reverse_proxy are — and every section supplies caddy-security-specific knowledge (portal-owned prefixes, dispatch substring checks) that Claude would not already know, so each token earns its place.	3 / 3
Actionability	Provides complete, copy-paste-ready Caddyfile blocks for each deployment shape (same-host, split-host, dedicated auth host, /xauth collision) plus concrete do/don't directive-order guidance, meeting the fully-executable anchor.	3 / 3
Workflow Clarity	Decision flows for portal path selection (/auth vs /xauth vs /) are clearly branched by scenario, and an explicit Validation checkpoint closes the workflow ("validate with the narrowest adapt-focused test from testing-and-ci").	3 / 3
Progressive Disclosure	Sections are well labeled, but all detail — including the long reserved-paths list and many full Caddyfile examples — lives inline in a single ~284-line SKILL.md with no bundle reference files to offload it into; the inline file pointers reference repo sources for context rather than splitting skill detail.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 a strong, third-person trigger clause that names concrete capabilities and an explicit "Use when" list tied to caddy-security HTTP integration specifics. It earns a top score on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "creating, reviewing, or modifying route-level authenticate and authorize directives, portal and protected route separation, matcher forms, same-host or split-host auth wiring" — rather than vague language, matching the "Lists multiple specific concrete actions" anchor.	3 / 3
Completeness	Explicitly states what ("caddy-security HTTP integration Caddyfile configuration") and when via a "Use when ..." clause enumerating concrete triggers, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Uses the natural domain terms a caddy-security user would actually say — "Caddyfile", "authenticate", "authorize", "portal", "auth URL", "directive-order" — with good coverage rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to caddy-security route-level HTTP integration with distinctive triggers (portal/authorize wiring, auth-path collisions), making it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing, 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: greenpau/caddy-security
Path: .codex/skills/configuration-http-integrations/SKILL.md
Commit: b96087f

Reviewed: 23 days ago

Table of Contents

Discovery Implementation Validation

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.