frb-fix-ci

Use when CI fails in flutter_rust_bridge - before deep investigation

Quality

67%

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-fix-ci/SKILL.md

Quality

Content

77%

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

The content is highly actionable and well-sequenced with strong feedback loops, earning top marks for actionability and workflow clarity. Its main weaknesses are repetition of the escalation guidance across sections and a monolithic structure that could benefit from splitting detail into referenced files.

Suggestions

Consolidate the clean-remote `precommit-generate` escalation guidance into one section and cross-reference it from the others instead of restating it three times.

Move the detailed dependency-graph and escalation-protocol material into a referenced file (e.g. DEPENDENCIES.md) and keep SKILL.md as an overview to improve progressive disclosure.

Tighten repeated phrasing around "do not hand-edit generated files" which appears near-verbatim in multiple failure-type sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal, repo-specific guidance Claude would not already know, but the clean-remote `precommit-generate` escalation is restated across Whack-a-Mole Prevention, the Escalation Protocol, and Generate-caused Failures, so it could be tightened.	2 / 3
Actionability	Concrete executable commands appear throughout (`gh run rerun --failed`, `./frb_internal precommit-generate`, `git reset --hard HEAD && git clean -fdx`, `./frb_internal lint --fix`), with specific file paths and copy-paste-ready snippets.	3 / 3
Workflow Clarity	The numbered Triage Order and numbered Escalation Protocol give clear sequences, and the clean-workspace -> reproduce -> inspect-diff -> accept loops provide explicit feedback checkpoints for risky regen operations.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the ~319-line body is monolithic with no bundle files and no offloading of detail (e.g. the dependency graph or escalation protocol) into separate references.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 and a distinctive niche, but it is terse to a fault: it implies rather than states what the skill does and lacks concrete action terms and common keyword variations.

Suggestions

Add a concrete action clause, e.g. "Triages and applies quick fixes (rerun failed jobs, apply CI diffs, run --fix) for flutter_rust_bridge CI failures".

Include common trigger variations such as "FRB" and "CI broken/failing" alongside "CI fails in flutter_rust_bridge".

Make the "what" explicit so the description answers both what it does and when to use it, not just when.

Dimension	Reasoning	Score
Specificity	The phrase "CI fails in flutter_rust_bridge" names the domain clearly, and "before deep investigation" hints at quick triage, but no concrete actions (rerun, git apply, --fix) are listed, so it stops at naming domain and some implied actions.	2 / 3
Completeness	The "when" is explicit via the "Use when" clause, but the "what" is only implied (triage/fix CI) rather than stated as a concrete action, so it does not clearly answer both what and when.	2 / 3
Trigger Term Quality	"Use when CI fails in flutter_rust_bridge" supplies natural trigger terms a user might say, but coverage is limited to one phrasing and omits common variations such as "FRB" or "CI broken/failing", so it is not a 3.	2 / 3
Distinctiveness Conflict Risk	"flutter_rust_bridge" is a narrow niche and "- before deep investigation" disambiguates it from sibling skills like frb-debugging, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 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-fix-ci/SKILL.md
Commit: 1d5348b

Reviewed: 5 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.