CtrlK
BlogDocsLog inGet started
Tessl Logo

frb-debugging

Use when generated code looks wrong, code generation fails, or you need to understand FRB internals

55

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/frb-debugging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is a concise, well-structured debugging overview that points to deeper materials rather than inlining them, with a clear quick-to-deep sequence and a useful frb-fix-ci gating checkpoint. It would be fully executable if the placeholder codegen command were completed.

DimensionReasoningScore

Conciseness

The body is lean and efficient with no padded explanations of concepts Claude already knows; every section earns its place, assuming competence.

5 / 5

Actionability

It gives concrete guidance such as checking 'rust/target/frb_dump/' and a real 'RUST_LOG=debug flutter_rust_bridge_codegen ...' command, but the literal '...' makes the command a minor gap rather than copy-paste ready.

4 / 5

Workflow Clarity

There is a clear quick-diagnostics to full-troubleshooting sequence with an explicit gating checkpoint ('MUST use frb-fix-ci first'), though the deep-debugging steps themselves are loosely defined.

4 / 5

Progressive Disclosure

Sections are well organized with clearly signaled one-level-deep 'see:' references to docs files and sibling skills; minor gaps remain from the '...' placeholder and unverified repo paths.

4 / 5

Total

17

/

20

Passed

Description

40%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.

The description gives clear trigger guidance for when to invoke the skill but never states what the skill actually does, leaving the 'what' half of completeness unanswered. Trigger terms are natural but sparse on synonyms, and capabilities are implied rather than concretely listed.

Suggestions

Add a 'what' clause stating the concrete debugging actions the skill performs, e.g. 'Dumps intermediate representations and surfaces debug logs for flutter_rust_bridge codegen.'

Broaden trigger-term coverage with natural synonyms such as 'flutter_rust_bridge', 'codegen fails', or 'generated output is wrong'.

Lead with the 'what' before the 'Use when ...' clause so both halves of completeness are explicit.

DimensionReasoningScore

Specificity

Names the FRB/generated-code domain via 'generated code looks wrong, code generation fails, or you need to understand FRB internals', but these are trigger scenarios rather than concrete actions the skill performs (e.g. dump IR, enable debug logs), so actions are minimal/generic.

2 / 5

Completeness

It has an explicit 'Use when ...' clause but omits any 'what does this skill do' statement, matching the anchor where only 'when' is present without 'what'.

2 / 5

Trigger Term Quality

Phrases like 'generated code looks wrong', 'code generation fails', and 'FRB internals' are reasonably natural things a user would say, but coverage lacks common variations or synonyms and leans on the FRB jargon term.

3 / 5

Distinctiveness Conflict Risk

The FRB/generated-code niche is clear and the triggers are domain-specific, with only minor overlap risk against closely related sibling skills such as frb-fix-ci.

4 / 5

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fzyzcjy/flutter_rust_bridge
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.