slate-ar-perfect

Slate v2 broad improvement mini-skill. Uses Autogoal plus Slate AR routing to improve a named surface across quality, bugs, behavior proof, and perf without requiring the user to pick sub-skills.

Quality

75%

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 ./.agents/skills/slate-ar-perfect/SKILL.md

Quality

Content

100%

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 tool routing, an explicit error-recovery feedback loop, and a validation checklist, scoring at the top of every dimension.

Dimension	Reasoning	Score
Conciseness	The body is terse imperative routing ("Keep the goal short. Put the real checklist in the goal plan.") with no explanation of concepts Claude already knows, matching the lean score-3 anchor rather than the padded score-1 or the could-be-tightened score-2.	3 / 3
Actionability	It gives concrete named tools in an ordered routing list ("Start with slate-ar-status, then choose owners... 1. slate-ar-quality...") with explicit conditions; as an instruction-only skill this is actionable, copy-paste-ready guidance, not the vague score-1 or pseudocode score-2.	3 / 3
Workflow Clarity	The numbered Routing sequence, the explicit feedback loop ("If perf work exposes a correctness bug, route to slate-patch, fix it, then resume the perf target"), and the Completion validation checklist match the score-3 anchor of clear sequence plus checkpoints and error recovery.	3 / 3
Progressive Disclosure	With no bundle files present, the skill is a self-contained, well-organized single file split into clear sections (Contract, Routing, Completion, Handoff) with no nested references, which per the simple-skills note earns a 3 for well-organized sections.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 conveys what the skill does and its niche within the Slate v2 ecosystem, but it is jargon-heavy and lacks an explicit "Use when..." trigger, leaving every dimension at the midpoint.

Suggestions

Add an explicit "Use when..." clause naming natural user phrases (e.g., "Use when the user asks to perfect pagination, huge-document perf, or editor behavior") to raise completeness and trigger_term_quality.

Replace internal jargon ("Autogoal", "Slate AR routing", "behavior proof", "sub-skills") with user-facing terms so trigger terms match what users actually say.

List concrete example surfaces or actions to better distinguish this orchestrator from the sibling slate-ar-* sub-skills and reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Quotes "improve a named surface across quality, bugs, behavior proof, and perf" name a domain and several improvement dimensions, but these are categories under one verb rather than multiple concrete actions like the score-3 anchor, and it is not the vaguer score-1 "Helps with documents".	2 / 3
Completeness	It states what the skill does ("improve a named surface across...") but has no "Use when..." clause or equivalent explicit trigger, which the guidelines explicitly cap at 2; it is not the both-answered score 3 nor the missing-what score 1.	2 / 3
Trigger Term Quality	Natural words like "quality", "bugs", and "perf" appear, but they sit alongside jargon users would not say ("Autogoal", "Slate AR routing", "behavior proof", "sub-skills"), so coverage is partial like the score-2 anchor rather than the rich natural-term list of score 3.	2 / 3
Distinctiveness Conflict Risk	The phrase "without requiring the user to pick sub-skills" carves a niche versus sibling slate-ar-* skills, but "improve a surface" still overlaps those skills and lacks distinct triggers, matching the score-2 "could still overlap" anchor.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/slate-ar-perfect/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.