CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flutter-runtime-debugging

Reproduce, inspect, diagnose, and fix Flutter failures in a running app using logs, debugger attachment, DevTools, framework diagnostics, and minimal experiments. Use for runtime exceptions, incorrect live state, hangs, lifecycle failures, or failures that require execution evidence; route benchmarked jank to flutter-performance and planned device-flow verification to flutter-device-testing.

Quality

94%

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

The canonical home for this skill is thiennc-tesoglobal/flutter-skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 instruction-only skill body: lean decision-rule prose, a clearly sequenced diagnose-then-verify workflow with explicit validation and unverified-gap reporting, and a clean overview-to-references split that matches the actual bundle. The single gap is that the body names tools and decisions but defers all literal commands to the reference files.

Suggestions

Include one or two literal commands in the body (e.g. `flutter attach --flavor <flavor>` or `flutter run --profile`) so the primary flow is executable without loading a reference.

Consider a compact numbered restatement of the four-phase flow (reproduce → localize first incorrect transition → minimal fix → re-run as evidence) to make the sequence scannable at a glance.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows (no "what is Flutter" or "how hot reload works" padding) and every sentence encodes a constraint or decision rule, e.g. "Do not infer a root cause from the last stack frame, a screenshot, or a downstream assertion alone". It assumes competence throughout, matching the lean anchor rather than the minor-over-explanation anchor 4.

5 / 5

Actionability

Guidance is specific and executable at the decision level — "perform a full rebuild and clean-process launch on every affected supported target", "Change one relevant variable at a time", "Use Dart and Flutter MCP capabilities... otherwise rely on DevTools and CLI output" — but the body contains no copy-paste commands (e.g. `flutter attach`, `flutter run --profile`); concrete commands live only in the reference files. This sits between anchor 3 (missing key details) and anchor 5 (copy-paste ready), so 4.

4 / 5

Workflow Clarity

The opening line states the sequence ("Turn a reported symptom into a repeatable failure, identify the first incorrect state... apply the smallest supported fix, and repeat the same flow as evidence") and the sections follow it, with explicit checkpoints: record trigger/expected/actual, "require the first incorrect transition at every implicated boundary", one-variable-at-a-time experiments, and a Verification section that repeats the original flow and states "anything not reproduced or verified". Error-recovery loops and gap reporting are explicit, matching anchor 5.

5 / 5

Progressive Disclosure

The body is a concise overview with two well-signaled, conditionally-loaded references — "Read [reproduction and attachment](references/reproduction-and-attachment.md) when..." and "Read [DevTools diagnosis](references/devtools-diagnosis.md) when..." — both of which exist in the bundle, are one level deep, and contain the appropriately-split detail (the body's boundaries/verification summary vs. the references' procedures). No nesting beyond one level, so anchor 5 rather than the minor-gaps anchor 4.

5 / 5

Total

19

/

20

Passed

Description

92%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 that answers what and when explicitly, uses concrete third-person action verbs, and disambiguates against sibling skills with routing clauses. The only weakness is modest synonym coverage in its trigger terms.

Suggestions

Add common user-facing synonyms to the Use-for clause, e.g. "crashes, freezes/ANRs, or runtime exceptions", so the description triggers on the words users most naturally say.

DimensionReasoningScore

Specificity

"Reproduce, inspect, diagnose, and fix Flutter failures in a running app using logs, debugger attachment, DevTools, framework diagnostics, and minimal experiments" lists four concrete lifecycle actions plus the evidence modalities, matching the comprehensive-coverage anchor. It is not a 4 because coverage of the debugging lifecycle (reproduce → diagnose → fix) is complete rather than having minor gaps.

5 / 5

Completeness

The "what" is concrete ("Reproduce, inspect, diagnose, and fix Flutter failures in a running app...") and the "when" is an explicit "Use for..." clause with concrete trigger conditions, matching the anchor-5 example structure. Not a 4 because the when-clause is fully explicit, not merely present-but-imprecise.

5 / 5

Trigger Term Quality

Explicit triggers "runtime exceptions, incorrect live state, hangs, lifecycle failures, or failures that require execution evidence" are natural user phrases with good coverage. It falls short of 5 because common synonyms users say — "crash", "freeze", "error", "bug" — are absent, and "hangs" only partially covers the freeze family.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (runtime failures requiring execution evidence in a running app) and actively routes adjacent work away: "route benchmarked jank to flutter-performance and planned device-flow verification to flutter-device-testing". This explicit disambiguation gives minimal conflict risk, exceeding the mostly-distinct anchor 4.

5 / 5

Total

19

/

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

thienqo/flutter-skills

Path

skills/flutter-runtime-debugging/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.