CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

backend-api-review

Review API endpoints for authentication, authorization, input validation, and secure error handling.

Quality

80%

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 ./.agents/skills/backend-api-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 tight, well-organized checklist that is maximally token-efficient and clearly sequenced for a read-only review task. Its main weakness is actionability: it tells Claude what to check but not how to check it, with no examples of vulnerable patterns or expected output.

Suggestions

Add one concrete example per check of what to look for (e.g., 'authenticated: session token validated by middleware on every route, not just at login') so each step is verifiable rather than a topic heading.

Briefly state the expected output of the review (e.g., findings ranked by severity with file/line references) so Claude knows what to produce after running the checklist.

DimensionReasoningScore

Conciseness

The body is a lean 5-step checklist ('Confirm the caller is authenticated.', 'Validate client-controlled input.') with zero padding and no explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

The steps name concrete security concerns ('CSRF and privilege escalation risks', 'internal information in errors'), but each is a high-level directive with no specifics on how to verify it — missing key details such as vulnerable patterns to look for, examples, or what constitutes a pass/fail. It exceeds anchor 2 ('minimal concrete guidance') because there are five distinct, named checks, but is incomplete.

3 / 5

Workflow Clarity

This is a simple, single-purpose skill (review an endpoint) under 50 lines with a clearly sequenced, unambiguous numbered checklist ordered by request-processing stage (auth → permissions → input → errors → admin mutations). Reviewing is read-only, so the destructive/batch validation cap does not apply, and it qualifies for 5 under the simple-skill scoring note.

5 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained, and well-organized (title, one-line setup, numbered list); no bundle files (references/, scripts/, assets/) exist and none are needed, matching the rubric's provision that short skills with well-organized sections score 5.

5 / 5

Total

18

/

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 concise, third-person description with a clear 'what' and good domain keyword coverage, but it entirely lacks a 'when to use' trigger clause. Adding explicit usage triggers and a few natural synonyms would move it into the top tier.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g., 'Use when reviewing or auditing backend API endpoints, REST routes, or handlers for security issues.'

Include natural synonyms users would say, such as 'API security', 'auth', 'REST endpoints', or 'endpoint audit', to broaden trigger coverage.

Optionally name the deliverable (e.g., 'produces a findings report ranked by severity') to sharpen the 'what' and further distinguish it from generic code-review skills.

DimensionReasoningScore

Specificity

The description lists four concrete review areas ('authentication, authorization, input validation, and secure error handling'), matching 'several specific actions; minor gaps in coverage'. It is not 5 because it uses a single generic action verb ('Review') applied to focus areas rather than multiple distinct concrete actions, and not 3 because it covers four specific concerns rather than 1-2.

4 / 5

Completeness

It clearly answers 'what' ('Review API endpoints for authentication, authorization, input validation, and secure error handling') but contains no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines — an exact match for anchor 3's example pattern.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say when requesting an API review ('API endpoints', 'authentication', 'authorization', 'input validation'), matching 'good keyword coverage; a few natural terms missing'. It falls short of 5 because common variations like 'auth', 'API security', 'REST', or 'backend' are absent, and exceeds 3 ('Works with PDF files' level) because multiple relevant natural terms are present.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (security review of API endpoints) with specific focus areas, so it is 'mostly distinct; minor overlap risk' — chiefly with general security-review or code-review skills. It is more specific than anchor 3's 'Works with document files' example and does not reach 5's 'minimal conflict risk' given that overlap.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

deesumblip/admin-console

Path

.agents/skills/backend-api-review/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.