CtrlK
BlogDocsLog inGet started
Tessl Logo

building-api-authentication

Build secure API authentication systems with OAuth2, JWT, API keys, and session management. Use when implementing secure authentication flows. Trigger with phrases like "build authentication", "add API auth", or "secure the API".

64

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 ./plugins/api-development/api-authentication-builder/skills/building-api-authentication/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is a well-structured overview with genuine progressive disclosure to real reference files, but it leans on descriptive instructions over executable code and lacks explicit validation checkpoints for its security-sensitive steps, capping conciseness, actionability, and workflow clarity at 2.

Suggestions

Move the inline Error Handling table and Examples into the existing references/errors.md and references/examples.md, keeping only a one-line pointer in SKILL.md to cut duplicate tokens.

Add a small executable code snippet (e.g. a jwt.verify middleware) directly in the body so the skill is copy-paste ready, not just descriptive.

Insert an explicit validation checkpoint after the destructive steps (e.g. 'After rotating refresh tokens / revoking keys: run tests/auth/ and only proceed on pass') to lift workflow clarity to 3.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes competence (e.g. 'sign with RS256 or HS256'), but the nine-step Instruction list mixes high-level directives with specifics, and the inline Error Handling table plus Examples duplicate material already in references/errors.md and references/examples.md, adding tokens Claude could skip.

2 / 3

Actionability

It gives concrete details (claim names, token TTLs, headers, rate-limit thresholds) but no executable code or copy-paste commands in SKILL.md itself — all actual code lives in references/examples.md, so the body instructs rather than delivers runnable artifacts.

2 / 3

Workflow Clarity

Steps are clearly sequenced (1–9), but the instructions gloss over validation checkpoints: step 9 mentions writing tests but there is no validate-then-proceed loop for the destructive security changes (key rotation, session invalidation), so checkpoints are implicit per the rubric's cap at 2.

2 / 3

Progressive Disclosure

The body is an overview that points one level deep to real, clearly signaled references — implementation.md, errors.md, examples.md all exist under references/ — and the Output/Resources sections map artifacts to paths without nested indirection.

3 / 3

Total

9

/

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.

The description is concise, concrete, and complete: it names specific auth mechanisms, gives explicit 'Use when' guidance with natural trigger phrases, and occupies a clear niche. Voice is appropriately third person.

DimensionReasoningScore

Specificity

Lists multiple concrete mechanisms — 'OAuth2, JWT, API keys, and session management' — naming specific authentication schemes rather than vague actions.

3 / 3

Completeness

Clearly answers both what ('Build secure API authentication systems with OAuth2, JWT, API keys, and session management') and when ('Use when implementing secure authentication flows').

3 / 3

Trigger Term Quality

Explicit natural triggers ('build authentication', 'add API auth', 'secure the API') match phrases a user would actually say, alongside the concrete auth terms.

3 / 3

Distinctiveness Conflict Risk

The API-authentication niche and explicit auth-specific triggers are clearly distinct from general coding skills and unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.