CtrlK
BlogDocsLog inGet started
Tessl Logo

flutter-add-integration-test

Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests. Use when adding integration testing to a project, exploring UI components via MCP, or automating user flows with the integration_test package.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

Strong skill body: fully executable commands and complete code examples, a sequenced checklist with an explicit error-recovery feedback loop, and clean section structure. The only meaningful improvement is moving the three inlined example files into a references/ directory to slim the main file.

DimensionReasoningScore

Conciseness

The body is lean and imperative — exact commands, bullet guidance, and code with no padding about what Flutter or integration testing is. It falls short of 5 because of minor trimmable material: the 6-line Contents TOC for a ~155-line document and framing sentences like 'Use the Dart/Flutter MCP server tools to interactively explore and manipulate the application state before writing static tests.'

4 / 5

Actionability

Guidance is fully executable: exact 'flutter pub add' dependency syntax, complete 'flutter drive --driver=... --target=... -d ...' invocations per platform, and three copy-paste-ready Dart files (app test, host driver, perf driver). The only non-executable step is the manual 'Upload both APKs to the Firebase Test Lab console', but the common cases are covered completely, matching the 5 anchor.

5 / 5

Workflow Clarity

The 'Workflow: End-to-End Integration Testing' section gives a clearly sequenced four-phase checklist (Setup, Exploration, Authoring, Execution) plus an explicit feedback loop: 'Review test output -> If PumpAndSettleTimedOutException occurs, check for infinite animations -> If widget not found, add scrollUntilVisible -> Re-run test until passing.' This matches the top anchor's sequencing, validation, and error-recovery criteria.

5 / 5

Progressive Disclosure

Sections are well organized with a working internal-anchor TOC and no nested or buried references (no bundle files exist, so none are dangling). It does not reach 5 because roughly 70 lines of example code (three full Dart files) are inlined in SKILL.md when they could be split into an examples reference file, which is a minor organization gap rather than the misplacement of the 3 anchor.

4 / 5

Total

18

/

20

Passed

Description

78%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 well-constructed description with a clear what/when structure, concrete technology names, and natural trigger phrases. Its main weakness is limited action coverage — only two capability verbs — and a few missing synonyms that would strengthen both specificity and trigger matching.

Suggestions

Enumerate one or two more concrete capabilities in the first sentence (e.g., 'runs tests on Android, Chrome, and headless web via flutter drive, and captures performance timelines') to raise specificity from two actions to several.

Add natural synonyms such as 'end-to-end tests', 'e2e', or 'widget tests' to the 'Use when' clause to broaden trigger-term coverage.

Narrow the 'exploring UI components via MCP' trigger to tie it explicitly to integration testing so it cannot fire for a generic MCP-exploration skill.

DimensionReasoningScore

Specificity

The description names the domain and exactly two concrete actions — 'Configures Flutter Driver for app interaction' and 'converts MCP actions into permanent integration tests' — which matches the anchor for 1-2 concrete actions without comprehensive coverage. It does not reach 4 because 'several specific actions' (e.g., also mentioning execution, profiling, or setup) is not met.

3 / 5

Completeness

It explicitly answers both questions: the 'what' ('Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests') and a concrete 'when' clause listing three trigger scenarios. This matches the top anchor exactly and is clearly above the 4 anchor, where the 'when' would be less specific.

5 / 5

Trigger Term Quality

Includes natural phrases users would say such as 'adding integration testing to a project', 'exploring UI components', and 'automating user flows', plus the package name 'integration_test'. It stops short of 5 because common variations like 'end-to-end tests', 'e2e', 'widget tests', or 'flutter drive' are absent.

4 / 5

Distinctiveness Conflict Risk

The Flutter + MCP + integration_test niche is mostly distinct with clear triggers, but 'exploring UI components via MCP' and 'adding integration testing' could overlap with a generic Flutter testing or MCP exploration skill. Minor overlap risk matches the 4 anchor rather than the minimal-conflict 5 anchor.

4 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
flutter/agent-plugins
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.