CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frb-manual-test

Use when adding, executing, reviewing, or updating flutter_rust_bridge manual test reports under tools/manual_tests for scenarios that require human or agent-driven manual verification.

Quality

81%

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

73%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.

The body delivers a well-sequenced, evidence-driven manual-test workflow with explicit validation and blocked-state handling. Its weaknesses are redundancy between the gist-upload paragraph and the Reviewable Workflow Gate, and reliance on template files that are not present in the bundle.

Suggestions

Consolidate the gist-upload/artifact rules: the paragraph starting 'If the execution result belongs to a PR...' largely duplicates the 'Reviewable Workflow Gate' section — state the rules once in the gate and keep the earlier section to a one-line pointer.

Ship the referenced templates (test-template.md, execution-template.md) in the skill bundle, or restructure the body so the inline guidance stands alone without unverifiable external file references.

Trim the execution-evidence detail in SKILL.md (e.g. the long enumeration of evidence items and pass indicators) by moving it into execution-template.md, which is already declared the source of truth for run records.

DimensionReasoningScore

Conciseness

The body is mostly lean imperative guidance with no basic-concept padding, but the gist-upload and artifact rules are stated twice (the paragraph ending 'link that gist in the PR description...' and again as the 'Reviewable Workflow Gate' section), which is more than a minor trim.

3 / 5

Actionability

Guidance is largely executable: copy-paste-ready template commands, concrete artifact paths ('/private/tmp', '~/main/artifacts/flutter_rust_bridge/'), and concrete pass indicators ('All tests passed!', 'test result: ok'). Minor gaps remain, e.g. gist upload via 'git clone and push' is named without a command.

4 / 5

Workflow Clarity

Both the add and execute flows are clearly sequenced, and the Reviewable Workflow Gate is an explicit 7-step checklist with a validation rule ('Do not say that a PR-linked manual test execution is complete while any review-relevant artifact exists only as a local path') and an error-recovery path for gist-upload failure ('report... the PR/update step as blocked').

5 / 5

Progressive Disclosure

Detail is delegated one level deep to clearly signaled templates ('The detailed content requirements live in test-template.md; keep that template as the source of truth'), but neither test-template.md nor execution-template.md exists in the bundle (only SKILL.md is present), so the split cannot be verified and substantial execution-evidence detail still sits inline in the body.

4 / 5

Total

16

/

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, niche-specific description with an explicit trigger clause and concrete actions. Its main weakness is that the capability statement is only implicit in the 'Use when' verbs, and a few natural trigger synonyms are missing.

DimensionReasoningScore

Specificity

The description names the domain ('flutter_rust_bridge manual test reports under tools/manual_tests') and four concrete actions ('adding, executing, reviewing, or updating'), but never states what the skill itself provides (bundled templates, evidence rules), leaving minor gaps in coverage.

4 / 5

Completeness

The 'when' is explicit ('Use when adding, executing, reviewing, or updating...'), but the 'what' is only embedded in the trigger verbs with no distinct capability statement, so it sits between anchor 3 (what clear, when weak) and anchor 5 (both explicit and concrete).

4 / 5

Trigger Term Quality

Natural terms like 'manual test reports', 'manual verification', and 'tools/manual_tests' would be said by a user needing this skill, but common variations such as 'manual testing', 'test plan', or file extensions are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined by the project name, artifact type, and directory ('flutter_rust_bridge manual test reports under tools/manual_tests'), making it clearly distinguishable from generic testing or documentation skills with 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

fzyzcjy/flutter_rust_bridge

Path

.claude/skills/frb-manual-test/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.