frb-fix-ci

Use when CI fails in flutter_rust_bridge - before deep investigation

Quality

60%

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

81%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 high-quality, actionable CI triage skill with concrete commands, explicit validation/feedback loops, and a clear escalation protocol. Its main weakness is repetition of the same directives across several sections, which could be consolidated to improve token efficiency.

Suggestions

Consolidate the repeated directives ("do not hand-edit generated files", "check remote-testing rules", "do not answer from stale CI state") into a single stated-once rules block referenced where needed, to remove 3-5 restatements.

Consider moving the detailed mermaid dependency graph and Key Chains into a separate reference file linked from the Dependency Order section, since they are reference material rather than triage steps.

Tighten the Whack-a-Mole Prevention and Escalation Protocol sections, which overlap heavily on the two-similar-sync cutoff rule.

Dimension	Reasoning	Score
Conciseness	The body is substantive and project-specific (no generic concept explanations), but several directives are restated 3-5 times — "do not hand-edit generated files", "check remote-testing rules", "do not answer from stale CI state", and the two-similar-sync escalation cutoff appear across multiple sections — so it is mostly efficient but could be tightened.	3 / 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 Quick Reference table mapping symptoms to exact fixes.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (Triage Order 1-5, the 7-step Escalation Protocol) with explicit validation checkpoints and feedback loops — rerun-then-check-flaky, clean-then-reproduce, accept generated outputs only after confirming no new regressions — plus a Common Mistakes checklist.	5 / 5
Progressive Disclosure	The single file is well-organized with clear section headers and well-signaled one-level-deep pointers to sibling skills (frb-fix-merge-conflict, frb-ci-filter, frb-code-generation, frb-debugging), but at ~320 lines everything is inlined with no bundle files to split into, leaving minor organization gaps versus an ideal split.	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 is a strong, specific trigger ("Use when CI fails in flutter_rust_bridge - before deep investigation") but functions only as a trigger clause — it states when to use the skill without saying what it does. Adding a concrete capability statement would materially raise specificity and completeness.

Suggestions

Add a concrete "what" clause naming the actual fixes, e.g. "Triage flutter_rust_bridge CI failures with quick fixes — rerun flaky jobs, apply CI diffs, run --fix for lint/format, reproduce exact frb_internal commands. Use when CI fails in flutter_rust_bridge, before deep investigation."

Include natural trigger synonyms users may say, such as "CI failure", "build broken", or "tests failing", alongside "CI fails".

Name 1-2 concrete actions (rerun failed jobs, apply git diff, run lint --fix) so the capability is explicit rather than implied.

Dimension	Reasoning	Score
Specificity	The description names the domain concretely ("CI fails in flutter_rust_bridge") but lists no concrete fix actions — the capability is only implied by "before deep investigation", matching the anchor that names the domain with minimal/generic actions.	2 / 5
Completeness	Only the "when" is present and explicit ("Use when CI fails in flutter_rust_bridge - before deep investigation"); the "what" — what the skill actually does — is entirely absent and only weakly implied, matching the anchor where only the "when" is present without a "what".	2 / 5
Trigger Term Quality	"CI fails in flutter_rust_bridge" is a natural phrase a user would say, but the description offers only this single trigger phrase with no synonyms or variations (e.g. "build broken", "tests failing", "codegen failing"), matching the anchor with relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The phrase carves a clear niche (quick CI fixes "before deep investigation") that explicitly separates it from the sibling frb-debugging skill, leaving only minor overlap risk with closely related FRB skills like frb-code-generation.	4 / 5
	Total	11 / 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: 8f2ab1b

Reviewed: ~2 hours 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.