CtrlK
BlogDocsLog inGet started
Tessl Logo

test-flet-apps-dev

Use when testing or debugging Flet apps in maintainer/contributor development mode with local Python package sources and the local Flutter client, including web, desktop, browser, and computer-use verification workflows.

71

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An excellent operational skill body: copy-paste-ready commands, an explicit core model explaining when one vs. two processes are needed, dual-sided evidence reading, and a troubleshooting section with concrete fallbacks. The only structural note is that it is entirely self-contained with no progressive disclosure into reference files, which is acceptable at this size but leaves a minor organization opportunity.

Suggestions

Consider moving the Troubleshooting and Browser/UI-interaction detail into a single one-level-deep reference file (e.g. references/troubleshooting.md) to keep SKILL.md as a tighter overview with well-signaled links.

DimensionReasoningScore

Conciseness

Lean and dense with operational specifics throughout — the port-8550 rationale is delivered in four lines with a code excerpt, and no section explains concepts Claude already knows (there is no 'what is Flet' or 'how Flutter works' padding). Matches anchor 5: every token earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: 'uv run flet run -w -p 8550 examples/...', 'fvm flutter run -d macos', '-d chrome', '-d web-server --web-hostname 127.0.0.1 --web-port 8660', plus concrete hot-reload keys (r, R, q). Only trivial gap: 'open -a' is macOS-specific. Matches anchor 5.

5 / 5

Workflow Clarity

Clear multi-step sequence (start the Python app on 8550, run the local Flutter client on the right target, interact, read evidence from both sides, hot reload/restart, finish checklist) with explicit validation checkpoints in 'Reading evidence' and 'Finish checklist' and an error-recovery feedback section in 'Troubleshooting' (escalation fallback, web-server fallback). This is not a destructive or batch operation, so the validation cap does not apply. Matches anchor 5.

5 / 5

Progressive Disclosure

Well-organized sections with clear headers and appropriate placement of nearly all content, but everything is inline — there are no bundle or reference files at all, and ~150 lines of troubleshooting/browser-interaction detail could partly live in one-level-deep reference files. Matches anchor 4 (good structure, minor organization gaps); not anchor 5, which requires well-signaled references.

4 / 5

Total

19

/

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 strong, well-targeted description: highly distinctive for the Flet maintainer/contributor niche with an explicit trigger clause and good natural keywords. The main weakness is that the 'what' is embedded in the 'when' clause rather than stated as a separate capability summary, and 'verification workflows' is slightly abstract.

Suggestions

Lead with a brief capability statement before the trigger clause, e.g. 'Run and verify Flet apps against local Python packages and the local Flutter client. Use when testing or debugging ...', so the what and when are separately explicit.

Add common natural trigger variations such as 'run the app locally', 'smoke test', or 'Flutter client' to widen keyword coverage.

Replace the abstract 'verification workflows' with the concrete verification surfaces it covers (e.g. 'packaged web, local Flutter web, and desktop targets').

DimensionReasoningScore

Specificity

Names several concrete elements — 'testing or debugging Flet apps', 'local Python package sources', 'local Flutter client', 'web, desktop, browser, and computer-use verification workflows' — though 'verification workflows' is somewhat abstract and no specific operations or commands are named. It exceeds anchor 3 (which expects only 1-2 concrete actions) but falls short of anchor 5's comprehensive action list.

4 / 5

Completeness

An explicit 'Use when ...' trigger clause with concrete conditions (maintainer/contributor dev mode, local packages, local Flutter client) is present, and the what (testing/debugging/verification of Flet apps) is stated, but the what is conflated into the single when-clause rather than given as a distinct capability statement. This sits between anchor 4 and anchor 5; it is not the exemplary two-part what+when structure of anchor 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage — 'testing', 'debugging', 'Flet', 'development mode', 'web', 'desktop', 'browser', 'computer-use' — matching phrases a maintainer would naturally say. A few common variations are missing ('run locally', 'smoke test', 'Flutter client'), keeping it below anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers — 'Flet', 'maintainer/contributor development mode', 'local Flutter client' — that would not naturally collide with generic testing or app-development skills. Matches anchor 5 (clear niche, minimal conflict risk).

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
flet-dev/flet
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.