CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

configuration-crypto

Configure portal/policy JWT keys, named access signers, strict access-token profiles, token names and lifetimes, discovery, rotation, and System API encryption keys.

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-crypto/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.

A strong, project-grounded configuration reference: executable Caddyfile examples with explicit do/don't rules, the complete directive grammar, real troubleshooting patterns, and well-signaled one-level-deep references that verifiably exist. The main improvement opportunities are trimming repeated state/rotation caveats and offloading the deepest detail (Ed25519 labels, PS256 specifics, fixtures inventory) into the existing reference files.

Suggestions

Consolidate the repeated key-volatility/state caveat (stated in both "Mental Model" and "Defaults") into one place and cross-reference it.

Move the Ed25519 label/reimport semantics and the detailed Fixtures test inventory into a reference file, keeping only the orienting pointers in SKILL.md.

Add one explicit validation step (e.g., how to adapt/provision the config and confirm key loading) to close the workflow's implicit checkpoint gap.

DimensionReasoningScore

Conciseness

The body is dense with project-specific facts Claude cannot know (directive grammar, KMS defaults, label semantics) and does not pad with generic explanations of JWT/PEM basics, so most tokens earn their place. It is not a 5: at 345 lines there are sections that could be trimmed — the volatility/state caveat recurs across "Mental Model" and "Defaults" ("Key persistence alone does not share session state", "Independent active instances still need deliberately coordinated keys"), and the Ed25519 reimport-label details and Fixtures inventory run long.

4 / 5

Actionability

Guidance is copy-paste ready and covers the common cases: the "Common Pairing" block is a complete working Caddyfile, "Supported Forms" gives the exact directive grammar, and "Env And Secrets" plus the cookie-mirroring example give full config snippets with explicit do/don't rules ("Do not configure a portal with only `verify` unless..."). This matches the 5 anchor (fully executable examples covering common cases); it is not a 4 because there are no pseudocode gaps or missing key details in the examples.

5 / 5

Workflow Clarity

As a configuration-reference skill it presents a clear progression (mental model → canonical pairing → grammar → defaults → material → resolution → discovery → troubleshooting), and the "Failure Patterns" section supplies diagnostic feedback loops for each failure mode. It falls short of the 5 anchor because there is no explicit end-to-end validation step (e.g., a command to adapt/provision and confirm the config), leaving checkpoints implicit rather than prescribed.

4 / 5

Progressive Disclosure

Bundle structure checks out: both referenced files exist (`references/access-signing.md`, 165 lines; `references/system-api-keys.md`, 42 lines), are exactly one level deep, and are clearly signaled with purpose statements ("Read [selected access signing](references/access-signing.md) for declarations, resolution, approved claims..."). It is not a 5 because the SKILL.md body is a full 345-line reference rather than an overview — dense material like Ed25519 label semantics, PS256 salt rules, and the multi-paragraph Fixtures inventory could live in reference files to slim the always-loaded context.

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 specific, well-scoped configuration description that names seven concrete capabilities in the crypto domain. Its main weakness is the complete absence of any 'when to use' trigger clause, which caps completeness and weakens its value for skill selection. Adding explicit use-when phrasing and natural synonyms (crypto directive, JWKS, signing keys) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when configuring `crypto` directives in the security block, JWT signing/verification keys, or JWKS discovery for portals and policies."

Include the natural terms users actually type — "crypto", "JWKS", "signing keys", "PEM/key files" — as trigger synonyms alongside the current vocabulary.

Sharpen the bare word "discovery" to "public signing-key (JWKS) discovery" so it reads as a concrete capability rather than a generic noun.

DimensionReasoningScore

Specificity

The description enumerates several concrete capabilities — "portal/policy JWT keys, named access signers, strict access-token profiles, token names and lifetimes, discovery, rotation, and System API encryption keys" — under the single action "Configure". It sits between anchor 4 and 5: the objects are specific and broad in coverage, but the action repertoire is one verb rather than the multiple varied concrete actions of the 5 anchor ("Extract text..., fill forms, merge documents"), and "discovery" alone is slightly underspecified.

4 / 5

Completeness

The "what" is clear and concrete (configure keys, signers, profiles, lifetimes, discovery, rotation), but there is no "Use when..." clause or any equivalent explicit trigger guidance — usage context is only weakly implied by the domain nouns. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3, which matches the anchor-3 example (clear what, missing/weakly implied when).

3 / 5

Trigger Term Quality

Good domain keyword coverage: "JWT keys", "access signers", "token names and lifetimes", "rotation", "encryption keys" are phrases a user configuring this system would naturally say. Not a 5 because the literal directive name users would type ("crypto"), and common synonyms like "JWKS", "signing keys", or "key files/PEM" are absent, leaving a few natural trigger terms missing per the anchor-4 example.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (JWT/crypto key material for portals and policies) that is mostly distinct from sibling authentication/authorization/secrets skills, with trigger terms like "JWT keys", "access signers", and "System API encryption keys" unlikely to fire the wrong skill. It is not a 5 because "token names and lifetimes", "discovery", and "rotation" overlap with adjacent configuration skills and are not uniquely owned here.

4 / 5

Total

15

/

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: 7 suspicious

Warning

referenced_paths_exist

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

Warning

Total

14

/

16

Passed

Repository

greenpau/caddy-security

Path

.codex/skills/configuration-crypto/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.