frb-debugging

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with a sensible diagnostic order and an explicit gate to the sibling frb-fix-ci skill. Its weakness is actionability: the headline codegen command is incomplete and the deep section defers to external docs without concrete steps.

Suggestions

Complete the debug-logs command instead of leaving '...', e.g. 'RUST_LOG=debug flutter_rust_bridge_codegen generate' with the actual subcommand.

Add one or two concrete first steps under Full Troubleshooting (e.g. how to read frb_dump IR) rather than only linking to docs.

Add a short validate/retry checkpoint after running diagnostics, e.g. 'regenerate and compare the dump before/after your fix'.

Dimension	Reasoning	Score
Conciseness	The ~50-line body is lean and assumes Claude's competence; non-obvious facts like the dump_all default and the rust/target/frb_dump/ path each earn their tokens without restating known concepts. It is not the padded, explanatory style of the score-1 anchor.	3 / 3
Actionability	It gives some concrete guidance (the frb_dump directory and the RUST_LOG=debug command) but the command is left as '...' and Full Troubleshooting only points at doc files, leaving key details incomplete.	2 / 3
Workflow Clarity	There is a clear Quick-Diagnostics-then-Full-Troubleshooting sequence plus an explicit MUST gate to frb-fix-ci first, but the diagnostics themselves lack a validate/fix/retry feedback loop.	2 / 3
Progressive Disclosure	Under 50 lines with well-organized sections and one-level external doc references, and no bundle files exist to structure further; the simple-skill scoring note applies, so well-organized sections suffice for a 3.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 has a clear, explicit trigger ('Use when...') and a recognizable FRB niche, but it omits any statement of what the skill actually does and risks overlapping with sibling codegen/CI skills. Tightening it to name concrete diagnostic actions would lift both completeness and specificity.

Suggestions

Add a 'what' clause naming concrete actions, e.g. 'Dump intermediate representations, read RUST_LOG=debug output, and diagnose FRB codegen failures'.

Sharpen triggers to reduce overlap with frb-fix-ci, e.g. 'Use when generated code is wrong or codegen fails AFTER simpler CI-failure causes have been ruled out'.

Include natural keyword variations like 'codegen', 'frb_dump', or 'flutter_rust_bridge' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the FRB domain and concrete situations ('generated code looks wrong', 'code generation fails') but states no concrete debugging actions. It is not abstract like 'helps with code', yet it stops short of listing multiple specific actions.	2 / 3
Completeness	An explicit 'Use when' clause answers when, but what the skill does (dump IR, read debug logs, diagnose) is never stated, leaving one of the two required halves missing.	2 / 3
Trigger Term Quality	Phrases like 'generated code looks wrong' and 'code generation fails' are natural things a user would say, but coverage is thin and misses common variations (e.g. 'codegen', 'build failed').	2 / 3
Distinctiveness Conflict Risk	It targets a clear FRB niche, but 'code generation fails' overlaps with sibling skills frb-code-generation and frb-fix-ci — a conflict the body itself acknowledges.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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-debugging/SKILL.md
Commit: 1d5348b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.