CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

configuration-http-integrations

Mount authenticate and authorize handlers, separate portal and protected routes, align auth URLs, and preserve trusted proxy metadata. Use for path conflicts, split hosts, public JWKS, and route ordering.

Quality

85%

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

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 well-organized, information-dense reference with executable Caddyfile examples, explicit anti-pattern warnings, and genuinely useful one-level-deep references that hold the detail they promise. It scores uniformly at 4 rather than 5 because of small residual gaps: peripheral host-default and naming content inline, prose-only split-host guidance, and validation steps given as test names rather than runnable commands.

Suggestions

Trim or relocate the "Caddy Host Defaults" material (header size limits, dot/underscore header spellings) and the portal-naming style guidance into a reference file, since they are peripheral to route wiring.

Replace validation test names with runnable commands (e.g., the exact go test invocation) and add a brief fix-and-recheck step for the mount-validation flow.

Add a concrete split-host Caddyfile example showing the access-cookie domain/path coordination currently described only in prose.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific constraints and never explains concepts Claude already knows, but peripheral passages such as the "Caddy Host Defaults" header-limit details and the naming-convention paragraphs ("Avoid `authentication portal portal`") could be trimmed or moved to a reference. This fits 'efficient; minor instances of over-explanation' rather than the lean-every-token-counts level.

4 / 5

Actionability

Multiple copy-paste-ready Caddyfile route blocks cover the common cases (same-host, split-host, public JWKS, both syntax forms), but split-host cookie coordination is prose-only without an example and the Validation section names tests ("TestAuthnMountCaddyfile") rather than runnable commands. This places it at 'mostly executable; minor gaps', just below fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

Sections are logically sequenced (Route Roles, patterns, edge cases, Syntax, Directive Order, Validation, Acceptance criteria) and validation is explicit with named tests plus an acceptance checklist, but there are no verbatim commands and no fix-and-retry feedback loop. This matches 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

Both referenced files (references/edge-trust.md, references/portal-mounts.md) exist, are one level deep, and are well signaled with descriptive link text including working anchors. The body is nonetheless ~320 lines and carries inline detail (host defaults, refresh/native-client routing) that could partly be split into references, so it falls short of the 'clear overview' top anchor.

4 / 5

Total

16

/

20

Passed

Description

92%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 a strong, third-person, two-sentence statement that covers both what the skill does and when to use it with concrete domain triggers. Its only weakness is keyword breadth: a few natural user phrasings (e.g., "Caddyfile", "login portal") are not present. It is highly specific and clearly distinguishable from neighboring skills.

DimensionReasoningScore

Specificity

"Mount authenticate and authorize handlers, separate portal and protected routes, align auth URLs, and preserve trusted proxy metadata" lists four distinct, concrete, domain-specific actions with no coverage gaps, matching the comprehensive-coverage anchor rather than the 'minor gaps' level below.

5 / 5

Completeness

The opening clause explicitly states what the skill does and "Use for path conflicts, split hosts, public JWKS, and route ordering" is an explicit when-clause with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Use for path conflicts, split hosts, public JWKS, and route ordering" gives good natural domain keywords, but common phrasings a user might say such as "Caddyfile", "login portal", or "redirect loop" are absent, fitting the 'good coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

Terms like "public JWKS" and "authenticate and authorize handlers" carve out a clear caddy-security routing niche, making accidental triggering by generic web-server or auth skills very unlikely.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 missing, 3 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

greenpau/caddy-security

Path

.codex/skills/configuration-http-integrations/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.