coding-directives

caddy-security repository coding standards and implementation directives for Go/Caddy code, including Caddy module boundaries, security app lifecycle, authenticate/authorize plugin behavior, Caddyfile parser patterns, authcrunch integration, runtime replacement and secrets handling, errors, logging, imports, comments, tests, and fixtures. Use when creating, modifying, or reviewing application code in this repository or when deciding coding patterns for Caddyfile directives, Caddy modules, authcrunch config mapping, HTTP handlers, or Go tests.

Quality

90%

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

80%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.

A well-written, concise, and highly actionable coding-standards body that assumes competence and references real APIs, files, and commands. Its main weaknesses are the lack of explicit validation feedback loops and the absence of progressive disclosure into reference files.

Suggestions

Add an explicit validate-to-fix-to-retry loop for the riskier workflows, e.g. after running the narrow test or 'make license', state what to do on failure and when to re-run before proceeding.

Split the longer detail blocks (Caddyfile parser patterns and the test/fixture conventions) into reference files under references/ and link to them from SKILL.md so the overview stays lean.

Add a short ordered checklist for the test/fixture update workflow (edit -> update fixtures -> run narrow test -> broaden) with an explicit pass/fail gate before broadening.

Dimension	Reasoning	Score
Conciseness	The body is lean directive prose that assumes Claude's competence—it does not explain what Caddy modules or PDFs are, and each section is dense with actionable rules rather than padding.	3 / 3
Actionability	Guidance is concrete and specific throughout, naming real identifiers and commands (d.RemainingArgs(), d.ArgErr(), util.FindReplace, cfgutil.EncodeArgs, caddyfile_*_test.go, <prefix>_resolved.json, gofmt, make license), so Claude knows exactly what to do.	3 / 3
Workflow Clarity	The skill is directive-based rather than a sequenced workflow; it has light checkpoints ('run the narrow relevant test first, then broaden', 'inspect the resulting diff') but no explicit validate-to-fix-to-retry feedback loop for batch/destructive operations.	2 / 3
Progressive Disclosure	Sections are well organized, but the ~160-line document is monolithic with all detail inline and no bundle references to split out; at this length the simple-skill section-organization exemption does not apply.	2 / 3
	Total	10 / 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.

A strong, third-person description that explicitly covers both capability and trigger conditions with concrete, domain-specific terms. It is densely enumerated but every term maps to a real concern in the target repository.

Dimension	Reasoning	Score
Specificity	The description enumerates many specific concrete areas ('Caddy module boundaries, security app lifecycle, authenticate/authorize plugin behavior, Caddyfile parser patterns, authcrunch integration, runtime replacement and secrets handling'), naming exact components rather than vague categories.	3 / 3
Completeness	It states both what the skill provides ('caddy-security repository coding standards and implementation directives...') and an explicit 'Use when...' trigger clause, satisfying the what-and-when requirement.	3 / 3
Trigger Term Quality	The 'Use when' clause surfaces natural terms a contributor would actually say ('creating, modifying, or reviewing application code', 'Caddyfile directives', 'Caddy modules', 'authcrunch config mapping', 'HTTP handlers', 'Go tests') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	It is tightly scoped to the caddy-security repository and its specific modules/plugins, giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: greenpau/caddy-security
Path: .codex/skills/coding-directives/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.