frb-fix-ci

Use when CI fails in flutter_rust_bridge - before deep investigation

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

88%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 is a high-quality, actionable CI triage skill with concrete commands, explicit validation checkpoints, and clear escalation logic; its only weakness is mild repetition of the precommit-generate escalation guidance and large inline sections that could be externalized.

Suggestions

Consolidate the repeated 'two similar generated Dart drifts -> escalate to clean remote precommit-generate' rule into one canonical statement and cross-reference it from the other sections.

Consider moving the full mermaid dependency graph and/or the Escalation Protocol into a references/ file, keeping a one-line pointer and the decision rule inline in SKILL.md.

The body is otherwise strong; no further actionability or workflow changes needed.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific with no padding about concepts Claude already knows, but the 'two similar drifts -> escalate to clean remote precommit-generate' guidance is restated across Whack-a-Mole, Escalation Protocol, and Generate-caused Failures, leaving minor trim opportunities.	4 / 5
Actionability	Concrete copy-paste commands cover the common cases — 'gh run rerun --failed', 'pbpaste \| git apply', './frb_internal precommit-generate', 'git reset --hard HEAD && git clean -fdx', './frb_internal lint --fix' — with the sub-commands the lint fix runs broken out explicitly.	5 / 5
Workflow Clarity	Triage Order is a numbered sequence, the Escalation Protocol is a 7-step ordered list, and validation/feedback checkpoints are explicit throughout (verify generated output present, 'Only when valid', clean-before-reproduce, accept only after no new regressions) — appropriate for a batch/destructive-adjacent CI context.	5 / 5
Progressive Disclosure	Sections are clearly headed and cross-link related skills (frb-dev-env, frb-ci-filter, frb-code-generation, frb-debugging), but the dependency graph plus escalation protocol are large inline blocks that could be split into reference files for the main body.	4 / 5
	Total	18 / 20 Passed

Description

57%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 is well-scoped and triggerable, with a clear 'when' clause and low conflict risk, but it does not state concrete capabilities — only an ordering cue — so completeness and specificity land at mid-level.

Suggestions

Add 1-2 concrete actions after the trigger (e.g. 'Triage, rerun flaky jobs, apply or regenerate CI diffs') so the 'what' is explicit.

Include natural synonyms like 'red CI', 'CI broken', or 'pipeline failing' alongside 'CI fails' for broader trigger coverage.

Keep the existing 'before deep investigation' cue — it usefully positions this skill against frb-debugging.

Dimension	Reasoning	Score
Specificity	The description names the domain ('CI fails in flutter_rust_bridge') and gives one behavioral cue ('before deep investigation'), but states no concrete fix actions — matching the anchor that names the domain with minimal actions.	3 / 5
Completeness	It has a clear, explicit 'when' ('Use when CI fails in flutter_rust_bridge') but the 'what' is only weakly implied via the ordering hint 'before deep investigation' rather than concrete actions, so it sits at the clear-'when'/weak-'what' level.	3 / 5
Trigger Term Quality	'CI fails' and 'flutter_rust_bridge' are natural phrases a user would say, but no synonyms or variations (e.g. 'CI broken', 'red CI', 'pipeline') are included, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The trigger is tightly scoped to 'CI fails in flutter_rust_bridge', a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	14 / 20 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: 0876e2e

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.