api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/api-testing/skills/api-testing/SKILL.mdQuality
Discovery
82%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 is a strong description with excellent specificity, naming concrete tools, languages, and testing domains. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are naturally what users would say when needing API testing help.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to write or debug HTTP API tests, test endpoints, or set up integration tests with Supertest, httpx, or pytest.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Test REST APIs, GraphQL, request/response validation, authentication, and error handling' along with specific tools (Supertest, httpx, pytest). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities and tools, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'API testing', 'REST APIs', 'GraphQL', 'Supertest', 'httpx', 'pytest', 'authentication', 'request/response validation', 'HTTP'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to HTTP API testing with specific language/framework pairings (TypeScript/Supertest, Python/httpx+pytest). This is a distinct niche unlikely to conflict with general testing or general API skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill with excellent actionability—every section provides executable, copy-paste ready code examples covering both TypeScript and Python ecosystems. The main weaknesses are verbosity (redundant patterns, obvious best practices) and the monolithic structure that could benefit from splitting into language-specific reference files. The skill reads more like a cookbook than a workflow guide, which is appropriate for the topic but could be more concise.
Suggestions
Remove the 'Request Methods' section as those patterns are already demonstrated in 'Basic Setup', or consolidate into a compact cheat-sheet table
Trim the 'Best Practices' list to only non-obvious guidance—items like 'test both happy path and error cases' and 'validate status codes first' are things Claude already knows
Consider splitting TypeScript and Python content into separate reference files (e.g., SUPERTEST.md, HTTPX.md) and keeping SKILL.md as a concise overview with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable examples, but includes some redundancy—the 'Request Methods' section repeats patterns already shown in 'Basic Setup', and the best practices list states things Claude already knows (e.g., 'test both happy path and error cases'). Could be tightened significantly. | 2 / 3 |
Actionability | All examples are fully executable, copy-paste ready code with specific libraries, imports, and assertions. Covers GET/POST/PUT/DELETE, auth, file upload, GraphQL, and error handling with concrete, runnable code. | 3 / 3 |
Workflow Clarity | The skill is primarily a reference of patterns rather than a multi-step workflow, so sequencing is less critical. However, there's no guidance on test execution order, setup/teardown workflows, or validation checkpoints (e.g., verifying the test server is running, database state). The installation → setup → write tests flow is implicit but not explicitly sequenced. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and a 'See Also' section linking to related skills. However, at ~200 lines it's quite long and could benefit from splitting the TypeScript and Python sections into separate reference files, keeping SKILL.md as a concise overview with links. | 2 / 3 |
Total | 9 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- secondsky/claude-skills
- Commit
88da5ff
- 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.