CtrlK
BlogDocsLog inGet started
Tessl Logo

api-testing-observability-api-mock

You are an API mocking expert specializing in realistic mock services for development, testing, and demos. Design mocks that simulate real API behavior and enable parallel development.

28

Quality

21%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/api-testing-observability-api-mock/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

20%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is largely a high-level outline with no concrete, actionable content. It repeats its own description multiple times, explains obvious applicability criteria, and defers all real implementation detail to referenced files that don't exist in the bundle. The skill would benefit enormously from inline executable examples and specific tool/framework guidance.

Suggestions

Add at least one concrete, executable code example showing how to set up a mock server (e.g., using msw, WireMock, or Express) with a sample route and fixture response.

Remove the redundant 'Context' section and trim 'Use this skill when' / 'Do not use this skill when' to reduce token waste—Claude can infer applicability from the instructions themselves.

Add explicit validation steps to the workflow, such as verifying mock responses match the API contract schema before serving, to improve workflow clarity.

Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the most critical content (checklists, templates) directly in the skill body so it is self-contained enough to be useful.

DimensionReasoningScore

Conciseness

The content is padded with unnecessary context Claude already knows—'You are an API mocking expert' restates the description, 'Use this skill when' / 'Do not use this skill when' sections explain obvious applicability, and the 'Context' section repeats the description again. Very little unique, actionable information is conveyed for the token cost.

1 / 3

Actionability

There are no concrete code examples, executable commands, or specific mock server implementations. The instructions are abstract directives like 'Clarify the API contract' and 'Define mock routes' without showing how to do any of these things. No copy-paste ready content exists.

1 / 3

Workflow Clarity

The instructions section provides a rough sequence (clarify contract → define routes → provide fixtures → document usage), but there are no validation checkpoints, no feedback loops for verifying mock correctness, and no explicit verification steps before serving mocks.

2 / 3

Progressive Disclosure

The skill references `resources/implementation-playbook.md` and a sub-skill, which is good structure in principle. However, no bundle files are provided, so the references are unverifiable. The main file itself contains very little substantive content, making it feel like an empty shell pointing to resources that may not exist.

2 / 3

Total

6

/

12

Passed

Description

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads more like a persona prompt ('You are an API mocking expert') than a skill description, using second-person framing and vague aspirational language rather than concrete capability listings. It lacks specific actions, explicit trigger guidance, and natural user keywords, making it difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Replace the persona-style framing with third-person action verbs listing specific capabilities, e.g., 'Generates mock API endpoints, creates response fixtures with realistic data, simulates error codes and latency, and configures stateful mock servers.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about API mocking, mock servers, stub APIs, fake endpoints, test doubles, or needs to simulate API responses for development or testing.'

Remove the second-person 'You are' framing and buzzwords like 'enable parallel development' in favor of concrete, distinguishable actions that differentiate this from general API development or testing skills.

DimensionReasoningScore

Specificity

The description uses vague language like 'design mocks that simulate real API behavior' and 'enable parallel development' without listing concrete actions. No specific operations (e.g., generate mock endpoints, create response fixtures, configure latency simulation) are mentioned.

1 / 3

Completeness

The description partially addresses 'what' (design mocks) but in very vague terms, and completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the weak 'what' brings it to 1.

1 / 3

Trigger Term Quality

Contains some relevant keywords like 'API mocking', 'mock services', 'development', 'testing', and 'demos', but misses common user terms like 'stub', 'fake API', 'mock server', 'test doubles', 'API simulation', or specific tool names.

2 / 3

Distinctiveness Conflict Risk

The 'API mocking' domain is somewhat specific and distinguishable from general coding skills, but the vague framing ('development, testing, and demos') could overlap with general testing skills, API development skills, or integration testing skills.

2 / 3

Total

6

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
Dokhacgiakhoa/antigravity-ide
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.