CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

configuration-authorization

Configure authorization policies, ACLs, static claims enrichment, required external decisions, bypasses, identity headers, JWT verification, remote Basic/API-key auth, SQLite/Consul API keys, and direct OAuth without a portal.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/configuration-authorization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

An exceptionally strong configuration skill body: dense with non-obvious, project-specific behavior, full of executable Caddyfile and curl examples, and backed by real, purpose-labeled reference files plus fixture and acceptance-criteria sections that provide genuine validation checkpoints. The only improvements are structural — trimming or relocating the deepest behavioral prose into the existing reference layer.

DimensionReasoningScore

Conciseness

The prose is extremely dense with project-specific, non-derivable constraints ('quoted brace tokens must not terminate or open a policy', 'set redirect status accepts only 300 through 308') and contains essentially no explanation of concepts Claude already knows; only a few very deep behavioral passages (multi-pass path decoding limits, redirect-URL preservation mechanics) run long enough to trim or relocate, matching 'efficient; minor instances of over-explanation that could be trimmed'.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: complete Caddyfile blocks for policy shape, ACL shortcuts, explicit rules, set options, validation toggles, bypass and inject directives, portal-free API-key backends, plus concrete curl commands with headers for Basic and API-key testing, covering the common cases exactly as the 5 anchor requires.

5 / 5

Workflow Clarity

As a reference-style configuration skill it has a clear topic progression (shape → defaults → ACLs → policy options → credential backends → direct OAuth) and unusually strong validation guidance via named fixtures and an Acceptance criteria section ('Verify response behavior and downstream call counts, not just returned errors'); there is no ordered procedure, but none is strictly required, leaving minor rather than material gaps — matching anchor 4 rather than 5's explicit feedback-loop sequence.

4 / 5

Progressive Disclosure

All six bundled references exist and are one level deep, and every link is well signaled with a purpose statement ('Use the [static claims enrichment reference]... for claims enrichment static blocks, exact JSON values, identity bindings and ACL-only decisions'), with explicit routing to sibling skills for adjacent concerns; however, the 437-line body still inlines substantial deep behavioral semantics (path interpretation checks, redirect preservation internals) that could live in reference files, matching anchor 4's 'minor organization gaps' rather than anchor 5's lean overview.

4 / 5

Total

17

/

20

Passed

Description

66%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.

A highly specific, domain-dense description that clearly communicates what the skill configures, with strong natural keyword coverage and low conflict risk. Its main weakness is the complete absence of any 'Use when...' or equivalent trigger guidance, which caps completeness and weakens discoverability for users who describe their goal in everyday terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when configuring access control or authorization for routes in the Caddy security module, writing ACL or bypass rules, or setting up API-key/Basic auth for a gateway.'

Include a few natural synonyms users might say — 'access control', 'permissions', 'route protection' — so the description triggers on everyday phrasing, not just the product's own vocabulary.

Sharpen the boundary with sibling skills by signaling that JWT/crypto material setup belongs to the crypto skill and this skill owns policies, ACLs, and authorization decisions.

DimensionReasoningScore

Specificity

The description lists roughly ten concrete, named capabilities ('authorization policies, ACLs, static claims enrichment, required external decisions, bypasses, identity headers, JWT verification, remote Basic/API-key auth, SQLite/Consul API keys, and direct OAuth without a portal') with comprehensive domain coverage, but every item is the object of the single generic verb 'Configure', unlike the varied concrete actions ('extract', 'fill', 'merge', 'convert') in the 5 anchor — so it sits between anchors 4 and 5, noticeably above the midpoint.

4 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or any equivalent explicit trigger guidance; per the judging guideline a missing 'Use when' clause caps completeness at 3, and the 'when' is at best weakly implied by the domain vocabulary.

3 / 5

Trigger Term Quality

Good coverage of natural terms a user configuring this system would say ('authorization', 'ACLs', 'JWT', 'OAuth', 'API keys', 'bypasses'), but common synonyms such as 'access control', 'permissions', or the host gateway/system name are absent, so it falls short of the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Distinct niche markers ('claims enrichment static', 'SQLite/Consul API keys', 'direct OAuth without a portal') minimize conflict risk, but 'JWT verification' and 'remote Basic/API-key auth' overlap closely related sibling skills (e.g. crypto/authentication configuration), matching anchor 4's 'minor overlap risk with closely related skills' rather than anchor 5's minimal conflict risk.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 6 suspicious

Warning

Total

15

/

16

Passed

Repository

greenpau/caddy-security

Path

.codex/skills/configuration-authorization/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.