CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An intentionally thin, well-organized router skill that correctly defers detail to an audited README while preserving the critical invariants (immutability of the promoted base, candidate-rebuild-smoke-promote workflow) inline. It is maximally token-efficient and unambiguous about what lives where. The only soft spot is that the smoke-test failure path and the actual commands live entirely outside the skill.

DimensionReasoningScore

Conciseness

The ~25-line body is lean and directive with zero padding: every line either points to the source of truth, states a constraint, or defines the rebuild/promote workflow. It assumes competence and explicitly states "Keep this skill thin so the guide remains the audited source of truth", so nothing could be trimmed without losing information.

5 / 5

Actionability

Guidance is concrete for an instruction-only skill: exact paths ("tools/tart_macos/README.md", "tools/tart_macos/packer/frb-tart-base.pkr.hcl"), named artifacts ("frb-tart-base-candidate", "frb-tart-base"), and specific dos/don'ts. Not a 5 because no actual commands (packer build, smoke-test invocation) appear inline — they are deferred to the external README; not a 3 because the specific paths, VM names, and rules make the guidance directly executable in outline.

4 / 5

Workflow Clarity

The durable-change workflow is clearly sequenced with a validation gate: "Use `frb-tart-base-candidate` for rebuilds, smoke test the candidate, then promote it to `frb-tart-base`", plus a guardrail against mutating the promoted base. Not a 5 because there is no error-recovery loop (what to do when the smoke test fails — presumably covered in the README); not a 3 because the sequence and the smoke-test checkpoint are explicit, not implicit.

4 / 5

Progressive Disclosure

This is a sub-50-line, single-purpose skill with well-organized sections and no bundle files (references/, scripts/, assets/ are absent), so the simple-skill exception applies. Its one clearly signaled reference (the checked-in README) is one level deep, and it cleanly routes the Tart daily-usage concern to the sibling skill.

5 / 5

Total

18

/

20

Passed

Description

78%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.

A well-scoped, third-person description with an explicit 'Use when' clause and a concrete enumerated domain. It clearly communicates both purpose and trigger context for this narrowly-defined skill. Minor room to grow by adding operation-level trigger terms (rebuild, promote, smoke test) and slightly sharper capability phrasing.

DimensionReasoningScore

Specificity

The description names a concrete domain ("FRB Tart base VM for iOS Simulator validation") and enumerates specific areas — "local OCI registry mirroring, Packer provisioning, and base VM hygiene" — which is several specific items, though the actions themselves ("preparing or explaining") are generic verbs. Not a 5 because it omits concrete operations from the body's workflow (rebuild, smoke test, promotion), and not a 3 because the enumerated coverage goes beyond 1-2 actions.

4 / 5

Completeness

It has an explicit "Use when preparing or explaining..." trigger clause plus a clear 'what' via the enumerated scope (registry mirroring, Packer provisioning, hygiene). Not a 5 because the 'what' is expressed as included topics rather than explicit capability statements, and the 'when' could name more concrete trigger scenarios; not a 3 because both what and when are present and specific.

4 / 5

Trigger Term Quality

Strong natural keyword coverage for this domain ("Tart base VM", "iOS Simulator", "OCI registry", "Packer", "provisioning") that a user in this repo would plausibly say. Not a 5 because synonyms and variations like "rebuild", "promote", "macOS VM image", or file/tool extensions are missing; not a 3 because coverage clearly goes beyond a couple of generic keywords.

4 / 5

Distinctiveness Conflict Risk

"FRB Tart base VM" is a highly niche, named target with distinct technical triggers (OCI registry, Packer) that would not collide with generic skills; it only brushes against the sibling frb-dev-env skill, which the body explicitly disambiguates. Clear niche with minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.