CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

api-review

Reviews API routes for routing contracts, input schema validation (Zod), JSON error taxonomies, request/response models, pagination, authentication, recoverability, and HTTP status codes. Use during API code changes or integrations.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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-structured review checklist that is token-efficient and highly actionable, with correct HTTP semantics and concrete technology-specific checks. Its only gap is the absence of an example of the unified JSON error envelope it mandates.

DimensionReasoningScore

Conciseness

The body is lean imperative bullets with zero concept explanation ('Ensure all incoming requests... are validated using strict Zod schemas', 'Avoid passing DB model instances directly to the frontend'), fully assuming Claude's competence — every token earns its place.

5 / 5

Actionability

Concrete, specific guidance throughout (strict Zod on 'req.json(), query parameters, route segments', '401 Unauthorized vs 403 Forbidden', 'VALIDATION_FAILED, INTERNAL_ERROR', 'limit, offset / cursor'), but the mandated 'consistent JSON error envelopes' are described rather than exemplified, leaving a minor gap versus fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

The numbered checklist (1-4) plus the protocol section ('Follow AGENTS.md review throttling... before starting', 'After a completed PR review, post one Review record comment') gives a clear sequence with pre- and post-steps. It stops short of score 5 because there are no explicit checkpoints for what to do when a checklist item fails mid-review, though the non-destructive context (review-only, no mutation) makes feedback loops less critical.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references; the four well-organized sections and clearly signaled one-level links to repo docs (AGENTS.md, codex-review-protocol.md, pull-request-workflow.md) satisfy the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

80%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 strong description with comprehensive, concrete capability enumeration and an explicit trigger clause. Its only weaknesses are a slightly broad 'when' clause and missing common synonyms like 'endpoints' or 'REST'.

DimensionReasoningScore

Specificity

The description enumerates eight concrete capabilities ('routing contracts, input schema validation (Zod), JSON error taxonomies, request/response models, pagination, authentication, recoverability, and HTTP status codes'), matching the comprehensive multi-action anchor rather than the score-4 anchor with coverage gaps.

5 / 5

Completeness

Both parts are present: a clear 'what' ('Reviews API routes for...') and an explicit 'when' ('Use during API code changes or integrations'). The trigger clause is slightly broad — 'or integrations' is generic compared to the concrete trigger phrases in the score-5 anchor.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('API routes', 'API code changes', 'validation', 'authentication', 'pagination', 'HTTP status codes'), but common variations like 'endpoints', 'REST', or 'APIs' are absent, so it falls just short of the comprehensive synonym coverage of the score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

'Reviews API routes' plus specific markers like 'Zod' and 'JSON error taxonomies' establish a clear niche, but 'Use during API code changes' could co-trigger a general code-review skill, leaving minor overlap risk rather than the minimal conflict of the score-5 anchor.

4 / 5

Total

17

/

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/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.