CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

api-test-generator

Генерация полных Python pytest тестов для REST API эндпоинтов с валидацией схемы. Использовать при создании тестов для новых эндпоинтов, добавлении покрытия для CRUD операций или валидации соответствия API с OpenAPI схемами.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills_all/api-test-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

45%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.

The body has a genuinely clear step sequence and useful MikoPBX-specific details (auth fixture, verify=False, container/debug commands), but it is undermined by heavy redundancy, placeholder pseudocode instead of runnable examples, and links to bundle files that do not exist. It reads as a padded rewrite of what should be a lean overview pointing to real template files.

Suggestions

Collapse 'What This Skill Does', 'When to Use', 'Output Format', 'Quick Reference', and 'Example Invocation' into the 'Quick Start' workflow stated once — that alone removes roughly a third of the body.

Make the code examples executable: replace 'payload = { # Based on DataStructure.php }' and 'requests.post(...)' with real payloads/calls for a worked example (e.g., Extensions), and make the DataStructure.php find command machine-agnostic instead of hard-coding '/Users/nb/PhpstormProjects/mikopbx'.

Ship the referenced bundle files (templates/test-template.py, templates/crud-tests.py, templates/edge-cases.py, reference/pytest-patterns.md) or remove the links — the 'generate test file' step currently depends on a template that is not in the bundle.

DimensionReasoningScore

Conciseness

The body is noticeably padded: the same 5-step workflow is stated three times ('Quick Start', 'Quick Reference', 'Example Invocation'), and 'What This Skill Does', 'Output Format', and 'Best Practices' are checklists that largely restate the description and each other. This matches the 2 anchor ('several unnecessary explanations or padded sections'); it is above 1 because it never explains concepts Claude already knows and much of the content is concrete.

2 / 5

Actionability

Guidance is a mix of executable code and placeholders: 'payload = { # Based on DataStructure.php }', 'response = requests.post(...)' with a literal ellipsis, and a find command hard-coded to a personal path '/Users/nb/PhpstormProjects/mikopbx/...'. Anchor 3 ('pseudocode instead of executable code; missing key details') fits; not 4 because the flagship 'generate test file' step relies on a template file that does not exist in the bundle.

3 / 5

Workflow Clarity

The 'Quick Start' section gives a clear numbered sequence (identify endpoint → locate DataStructure.php → analyze parameters → generate test file → customize), and the Troubleshooting/Debug Commands sections provide error-recovery feedback. It stays at 4 rather than 5 because the workflow ends at generation without an explicit verify step (e.g., run the generated tests and fix failures), and the locate command is machine-specific.

4 / 5

Progressive Disclosure

The body links to 'templates/test-template.py', 'templates/crud-tests.py', 'templates/edge-cases.py', and 'reference/pytest-patterns.md', but none of these files (or templates/reference directories) exist in the bundle, so navigation dead-ends. Combined with substantial template-style content inlined in the body, this matches the 2 anchor ('content that clearly belongs in separate files is inlined; or references are buried') rather than 3, where references would at least be real.

2 / 5

Total

11

/

20

Passed

Description

83%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: it states concrete capabilities in third person, includes an explicit and multi-trigger 'Use when' clause, and defines a distinct niche (Python pytest tests for REST API endpoints with schema/OpenAPI validation). The only weaknesses are minor: a few natural synonyms are absent and coverage of edge/negative testing is not mentioned.

DimensionReasoningScore

Specificity

The description names several specific capabilities: 'Генерация полных Python pytest тестов для REST API эндпоинтов' (generate complete Python pytest tests for REST API endpoints), 'с валидацией схемы' (with schema validation), plus CRUD coverage and OpenAPI compliance in the when-clause. Minor gaps in coverage (e.g., negative/edge-case testing is not mentioned), so it falls between the 'several specific actions' anchor (4) and fully comprehensive (5), closer to 4.

4 / 5

Completeness

It explicitly answers both parts: the 'what' ('Генерация полных Python pytest тестов для REST API эндпоинтов с валидацией схемы') and a concrete 'when' clause ('Использовать при создании тестов для новых эндпоинтов, добавлении покрытия для CRUD операций или валидации соответствия API с OpenAPI схемами') with three concrete trigger phrases. This matches the 5 anchor exactly.

5 / 5

Trigger Term Quality

Natural trigger terms users would say are present: 'pytest тестов', 'REST API эндпоинтов', 'создании тестов для новых эндпоинтов', 'CRUD операций', 'OpenAPI схемами'. Not at 5 because common synonyms such as 'API testing', 'test coverage', or 'unit tests' are missing; not at 3 because keyword coverage is genuinely good across the domain.

4 / 5

Distinctiveness Conflict Risk

The combination of pytest + REST API + schema validation + OpenAPI gives a clear, fairly distinct niche ('CRUD операций', 'OpenAPI схемами' are distinctive triggers). Minor overlap risk remains with generic test-generation or Python-testing skills, which keeps it at 4 rather than 5; well above 3 since it would not plausibly trigger for unrelated skills.

4 / 5

Total

17

/

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

allowed_tools_field

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

Warning

relative_links

Relative link issues: 10 missing

Warning

Total

14

/

16

Passed

Repository

Microck/ordinary-claude-skills

Path

skills_all/api-test-generator/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.