CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

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

82%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 appropriately thin delegation skill that points to a single audited source-of-truth README and preserves the load-bearing immutability and promotion rules. It would reach top marks by adding a couple of concrete commands or formatting the references as explicit per-topic links.

Suggestions

Add 1-2 concrete smoke-test/promotion commands (e.g. the exact tart/packer invocation) so the body is copy-paste actionable without always opening the README.

Format the source-of-truth references as explicit per-topic links (e.g. 'Packer build: see tools/tart_macos/README.md#packer') to match top-tier progressive-disclosure navigation.

Add a one-line error-recovery note for the smoke-test gate (e.g. 'if the smoke test fails, keep iterating on the candidate; do not promote') to complete the feedback loop.

DimensionReasoningScore

Conciseness

Lean ~26-line delegation skill that never explains what Tart/Packer/OCI are and keeps every line load-bearing ('Keep this skill thin so the guide remains the audited source of truth').

5 / 5

Actionability

Gives concrete file paths and a named candidate→smoke→promote workflow, but delegates the executable commands to the README rather than providing copy-paste commands inline.

4 / 5

Workflow Clarity

The 'rebuild candidate, smoke test the candidate, then promote' sequence has an explicit pre-promotion validation gate, though error-recovery feedback-loop detail is left to the referenced guide.

4 / 5

Progressive Disclosure

Well-structured into 'Source Of Truth' and 'Required Reminders' with clear one-level-deep references to checked-in files; references are plain inline code-spans rather than the per-topic formatted nav links of a 5.

4 / 5

Total

17

/

20

Passed

Description

87%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 strong, niche-scoped description that explicitly couples a concrete action list with a clear 'Use when' trigger. Minor room for synonyms and a slightly more exhaustive action enumeration, but it cleanly answers both what and when.

DimensionReasoningScore

Specificity

Names a concrete domain (FRB Tart base VM) and several specific actions — 'local OCI registry mirroring, Packer provisioning, and base VM hygiene' — but stops short of the comprehensive action list needed for a 5.

4 / 5

Completeness

Explicitly answers both 'what' (the listed VM-preparation actions) and 'when' via the 'Use when preparing or explaining…' trigger clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Solid natural phrases a maintainer would say ('preparing or explaining', 'iOS Simulator validation', 'OCI registry mirroring'), but lacks synonyms and file extensions, keeping it below comprehensive 5-level coverage.

4 / 5

Distinctiveness Conflict Risk

The 'FRB Tart base VM' niche with iOS-Simulator/Packer/OCI-registry triggers is highly specific with minimal overlap risk against other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fzyzcjy/flutter_rust_bridge
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.