CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

configuration

Build or review caddy-security Caddyfiles and select focused configuration skills. Use for security app declarations and authenticate/authorize route wiring.

Quality

83%

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

86%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 content is an efficient, highly actionable router skill: a complete runnable example, a sequenced workflow with a validation checkpoint, explicit acceptance criteria, and clean one-level-deep disclosure into three real reference files and per-domain sibling skills. It stays lean by assuming competence and delegating detail. The only noticeable gaps are minor redundancy and the absence of an explicit error-recovery loop after the syntax check.

DimensionReasoningScore

Conciseness

The body is dense, contract-focused prose that assumes Claude's competence and explains no general concepts (no "what is Caddy/OAuth" padding); nearly every sentence carries project-specific rules. Minor redundancy exists (the SAML-provider vs SSO-app distinction is stated both in the Domain Map and again after it, and a few stacked clauses could be trimmed), fitting anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

The Common Shape section is a complete, copy-paste-ready Caddyfile using an env placeholder for secrets, followed by concrete optional matcher forms ("authenticate @portal with myportal at /auth"). Specific parser file names, fixture paths under testdata/caddyfile_adapt/, and exact directives ("--with", "order") cover the common cases, matching anchor 5.

5 / 5

Workflow Clarity

The 5-step Workflow is clearly sequenced (identify flow, follow domain routes, build smallest block, use env placeholders, check syntax) and step 5 is an explicit validation checkpoint against wrappers, upstream grammar, validators, and fixtures; the Acceptance criteria section acts as a checklist. However, there is no explicit validate-then-fix feedback loop for what to do when the syntax check fails, so it matches anchor 4 rather than anchor 5.

4 / 5

Progressive Disclosure

The body is a clear router overview: the Domain Map gives one-line navigation to each sibling domain skill with its owning parser files, and the three bundle references (references/syntax-maintenance.md, references/authcrunch-compatibility.md, references/operator-examples.md — all verified present) are one level deep and well-signaled with when-to-use conditions. Detailed syntax, compatibility, and operator examples are appropriately split out, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

75%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 solid, third-person, appropriately concise statement with an explicit "Use for..." trigger clause and module-specific terminology. It clearly communicates what the skill does and when to use it. The main gaps are missing natural synonyms (SSO, OAuth, OIDC, identity stores) in the trigger terms and slightly generic "Build or review Caddyfiles" phrasing that leaves minor conflict risk with sibling skills.

Suggestions

Expand the 'Use for...' clause with more concrete trigger phrases users would naturally say, e.g. 'Use when configuring caddy-security authentication portals, authorization policies, identity stores, OAuth/OIDC or SAML providers, or Caddyfile authenticate/authorize directives.'

Add natural synonyms and technical variations to the trigger terms, such as SSO, OAuth/OIDC, SAML, JWT, or identity stores, so users describing those flows in their own words still match.

Sharpen the opening action list to distinguish the router role from sibling configuration skills, e.g. 'Route caddy-security Caddyfile requests to the matching configuration domain skill; build or review complete security app declarations and authenticate/authorize route wiring.'

DimensionReasoningScore

Specificity

"Build or review caddy-security Caddyfiles and select focused configuration skills" names the domain and several concrete actions (build, review, select/route to focused skills). It exceeds the 1-2 actions of anchor 3 but is not comprehensively covered (e.g., no mention of validating or adapting configs), matching anchor 4.

4 / 5

Completeness

It answers both questions: the what ("Build or review caddy-security Caddyfiles and select focused configuration skills") and an explicit when ("Use for security app declarations and authenticate/authorize route wiring"). The when-clause is present but could be more explicit with concrete trigger phrases, matching anchor 4 rather than the fully concrete anchor 5 example.

4 / 5

Trigger Term Quality

Terms like "Caddyfiles", "security app declarations", and "authenticate/authorize route wiring" are natural phrases a user configuring this module would say. Coverage is good but misses common synonyms and variations users might mention, such as SSO, OAuth/OIDC, identity stores, or JWT, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (caddy-security specifically, with module-specific triggers like "authenticate/authorize route wiring"), but the skill is a router over many sibling configuration-* skills and the generic "Build or review Caddyfiles" phrasing creates minor overlap risk with closely related Caddy configuration skills, fitting anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

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: 21 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (assets/config/users.json), 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

greenpau/caddy-security

Path

.codex/skills/configuration/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.