frb-prepare-pr

Use when about to create a PR or push changes in flutter_rust_bridge to ensure code generation is up to date

Quality

74%

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-prepare-pr/SKILL.md

Quality

Content

75%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 lean, well-structured orchestration workflow with concrete commands, conditional REQUIRED markers, and clearly signaled peer-skill references. Its main gap is that validation feedback loops (lint-fails → fix → re-run) are implicit rather than spelled out, which caps workflow clarity just below the top anchor.

Suggestions

Make the validation feedback loop explicit, e.g. after 'Run ./frb_internal lint --fix' add 'If lint reports issues, fix them and re-run until clean' to reach anchor 5 on workflow clarity.

Collapse the ASCII workflow diagram and the Quick Checklist into a single representation (or explicitly label one as summary and one as detail) to remove the minor redundancy.

Inline the one or two most-used generation commands from frb-code-generation so the most common path is executable without a follow-up read.

Dimension	Reasoning	Score
Conciseness	The body is efficient, assumes Claude's competence (no explaining what a PR or codegen is), and provides concrete commands; only minor trimming is possible (the 'Core principle: Generate → Lint → Commit → PR' line partially restates the workflow), so it sits at anchor 4 rather than the fully-lean anchor 5.	4 / 5
Actionability	It gives concrete executable commands ('./frb_internal lint --fix', 'precommit-integrate', 'sync-cargokit-copies', 'gh pr create') and specific paths, but several steps delegate execution via 'Read frb-X skill' rather than inlining the command, leaving minor gaps.	4 / 5
Workflow Clarity	A clear numbered sequence with REQUIRED/Optional and conditional markers plus checkpoints (lint, the frb-pr-review gate, the CI codegen check) is present, but explicit fix-and-retry feedback loops are only implicit, so it does not reach anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist; the body is organized into clear sections and delegates detail to one-level-deep peer-skill references ('Read frb-code-generation skill', the Related Skills list), with only minor organization overlap between the ASCII workflow and the Quick Checklist.	4 / 5
	Total	16 / 20 Passed

Description

73%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-targeted with an explicit, distinctive trigger and clear domain, but it undersells the skill's scope by naming only code generation rather than the full generate-lint-review-PR workflow. Expanding the 'what' to mention the broader steps would lift completeness and specificity.

Suggestions

Broaden the 'what' clause to reflect the full scope, e.g. 'to ensure code generation is up to date, lint passes, and the PR is review-ready' — this would raise specificity and completeness.

Add a common synonym such as 'pull request' alongside 'create a PR' to improve trigger-term coverage.

Keep the explicit 'Use when...' phrasing as-is; it already satisfies the trigger-guidance requirement.

Dimension	Reasoning	Score
Specificity	Names the domain ('create a PR or push changes in flutter_rust_bridge') and one concrete action ('ensure code generation is up to date'), but is not comprehensive — it omits the lint, review-gate, and CI-filter steps the body actually covers, so it does not reach anchor 4.	3 / 5
Completeness	It has both an explicit 'Use when' trigger ('about to create a PR or push changes in flutter_rust_bridge') and a stated purpose ('to ensure code generation is up to date'), but the 'what' is narrow — it describes only codegen, understating the full PR-prep scope — which keeps it below anchor 5.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ('create a PR', 'push changes', 'code generation'), giving good keyword coverage, but misses common synonyms such as 'pull request' or 'open a PR', so it falls short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The trigger is tightly scoped to a specific project ('flutter_rust_bridge') and a specific act (creating a PR / pushing), creating a clear niche with minimal risk of firing for unrelated skills.	5 / 5
	Total	16 / 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-prepare-pr/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.