frb-tart-prepare

Use when preparing or explaining the FRB Tart base VM for iOS Simulator validation, including local OCI registry mirroring, Packer provisioning, and base VM hygiene.

Quality

78%

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-tart-prepare/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.

A well-disclosed, concise skill body that correctly delegates detail to a checked-in README. The main gap is actionability/workflow clarity: it gives rules and file pointers but no executable build/promote commands or explicit validation steps.

Suggestions

Add a minimal ordered workflow with the actual commands for building, smoke-testing, and promoting frb-tart-base-candidate to frb-tart-base.

Include an explicit validation checkpoint (e.g., 'run the smoke test and confirm it passes before promoting') to back the destructive 'do not modify the promoted base' rule.

Add one short example command for the local OCI registry mirror so Claude can act without first reading the README.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and adds only project-specific reminders instead of explaining VM or Packer concepts.	3 / 3
Actionability	It names concrete files and image aliases, but provides no runnable commands for the build/promote/smoke-test workflow, delegating everything to the README.	2 / 3
Workflow Clarity	The candidate->smoke test->promote sequence is stated as reminders but lacks explicit ordered steps and a validation checkpoint for the destructive 'do not boot the immutable base' constraint.	2 / 3
Progressive Disclosure	It cleanly defers detail to a single one-level-deep README and points to the related daily-usage skill, keeping SKILL.md a thin overview.	3 / 3
	Total	10 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description that covers concrete actions and explicit 'what'/'when' guidance. It could improve by including more user-natural trigger phrasings rather than relying on project-internal jargon.

Suggestions

Add user-facing trigger phrasings (e.g., 'Use when the user asks to set up, rebuild, or troubleshoot the Tart macOS base VM for iOS Simulator runs').

Spell out what 'FRB Tart' stands for or surface a more generic keyword so the skill is discoverable by users who don't know the internal name.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'local OCI registry mirroring, Packer provisioning, and base VM hygiene' tied to a specific base VM and iOS Simulator validation workflow.	3 / 3
Completeness	Explicitly states what the skill does (prepare/explain the base VM) and when to use it ('Use when preparing or explaining...'), satisfying both 'what' and 'when.'	3 / 3
Trigger Term Quality	Includes natural terms like 'preparing,' 'base VM,' and 'validation,' but leans on internal jargon ('FRB Tart,' 'frb-dev-env') rather than phrases a user would commonly say.	2 / 3
Distinctiveness Conflict Risk	Narrowly scoped to the FRB Tart base VM with distinct internal triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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-tart-prepare/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.