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

63%

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

77%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.

A well-structured, token-efficient workflow skill with an explicit routing order, a completion checklist, and a bug-to-fix-to-resume feedback loop. Its main weakness is actionability: the routing is concrete but the autogoal invocation, goal format, and gate/benchmark mechanics are referenced by name only, with no examples or commands.

Suggestions

Add one compact example of an `autogoal` goal (surface, completion threshold, gates, boundaries) so the Contract section is executable rather than descriptive.

Show how to invoke the lane owners (a one-line command or call signature each), since six sibling skills are referenced by name with no invocation detail.

Trim the three overlapping opening paragraphs into a single 'Use when' paragraph to recover wasted tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence ('Faster broken editor behavior is not progress'), but the three-paragraph opening restates the same intent three ways ('Use this when... This is the high-level loop for... This is the main... workflow'), which could be trimmed to one.	4 / 5
Actionability	The routing section gives a concrete ordered owner list (slate-ar-status → slate-ar-quality → slate-patch → slate-ar-gate...), but the core mechanism stays abstract: 'Use `autogoal` for durable work' gives no invocation shape, no example goal, and no commands or examples of what a behavior gate or perf benchmark looks like.	3 / 5
Workflow Clarity	The sequence is explicit and ordered, the Completion section is a concrete stopping checklist (P0/P1 regressions, gates green or N/A, goal plan check), and an error-recovery feedback loop is spelled out: 'If perf work exposes a correctness bug, route to `slate-patch`, fix it, then resume the perf target.'	5 / 5
Progressive Disclosure	Single-file skill with no bundle files and no content that belongs in a separate file; the Contract / Routing / Completion / Handoff sections are clean and well-organized, so there is nothing to disclose progressively.	5 / 5
	Total	17 / 20 Passed

Description

50%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 communicates what the skill does at a high level and is appropriately short, but it leans on internal jargon, has no 'Use when...' trigger clause, and doesn't distinguish itself from sibling slate-ar skills. It consistently lands at the mid-anchor across all four dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to make a Slate v2 surface genuinely good — perfect pagination, perfect huge document perf, perfect editor behavior — rather than fixing one isolated issue.'

Replace or gloss internal jargon ('Autogoal', 'Slate AR routing', 'named surface') with the natural phrases users actually say, such as the 'perfect pagination' / 'huge document perf' / 'editor behavior' phrasing already used in the body.

State what distinguishes this from the sibling slate-ar-fast / slate-ar-stabilize lanes (e.g. 'This is the main entry point; the other lanes are internal or expert overrides') so it wins the trigger conflict.

Dimension	Reasoning	Score
Specificity	Names the domain (Slate v2 surface improvement) and a mechanism ('Uses Autogoal plus Slate AR routing') but the core action is the abstract 'improve a named surface across quality, bugs, behavior proof, and perf' — domain plus 1-2 actions without comprehensive concrete verbs.	3 / 5
Completeness	The 'what' is fairly clear (improve a named surface across four quality dimensions), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Some relevant natural keywords exist ('quality, bugs, behavior proof, and perf'), but they sit alongside internal jargon ('Autogoal', 'Slate AR routing') no user would naturally say, and the natural trigger phrases from the body ('perfect pagination', 'perfect huge document perf') are missing from the description.	3 / 5
Distinctiveness Conflict Risk	Scoped to Slate v2, but the skill's own body names sibling skills (slate-ar-fast, slate-ar-stabilize) that perform similar broad-improvement work, and the description does nothing to distinguish itself from them — real overlap risk with closely related skills.	3 / 5
	Total	12 / 20 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: babb3c2

Reviewed: 2 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.