slate-ar-fast

Slate v2 fastest-safe mini-skill. Picks or creates the hottest perf target, runs slate-ar-perf with no-regression checks, and stops at target, plateau, or correctness blocker.

Quality

74%

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-fast/SKILL.md

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.

The body is an exemplary lean instruction-only skill: a clear contract, explicit no-regression validation rules, quantified stop conditions, and a defined handoff, all with zero padding. The only weaknesses are delegated execution details and a couple of jargon terms ('packet', 'autogoal') that are used without definition.

Dimension	Reasoning	Score
Conciseness	Lean and imperative throughout — 'Load `slate-ar-status` first', 'Do not make the metric faster by weakening behavior, delaying input, or hiding work behind debounce' — with no explanation of concepts Claude already knows and every token earning its place. Nothing to trim without losing contract information.	5 / 5
Actionability	Gives concrete executable guidance: named sub-skills to invoke, a numbered target-priority list, a quantified stop condition ('three correctness-green packets improve the primary metric by less than 5%'), and an explicit handoff report field list. Not 5 because details like how to benchmark or what a 'packet' is are delegated without pointers, leaving minor gaps.	4 / 5
Workflow Clarity	Clear sequence — load status, resolve target, run the perf loop with no-regression checks, apply stop rules, then handoff — with real validation checkpoints (correctness evidence per kept packet, 'checks_failed' routing) so the destructive/batch cap does not apply. Not 5 because error-recovery detail (how checks are run, how to re-validate) is routed elsewhere rather than specified.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the single body is cleanly sectioned (Contract, No-Regression Rule, Stop Rules, Handoff) with every piece of content appropriately placed inline. All cross-mentions are sibling-skill invocations, not buried file references, so navigation is unambiguous.	5 / 5
	Total	18 / 20 Passed

Description

62%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 is specific, lean, and clearly niched to the Slate v2 performance workflow, but it omits any explicit 'Use when...' trigger guidance and lacks natural user-facing synonyms like 'make it faster' or 'speed up'. Its trigger terms are jargon-heavy, which limits discoverability even though the what is well described.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user says "make it fast", "fastest", "perf", or wants the agent to pick the highest-value Slate v2 performance target' — mirroring the guidance already present in the body.

Include natural user synonyms beyond 'perf', such as 'make it faster', 'speed up', 'optimize', and 'performance', so the description matches how users actually phrase the request.

Briefly define or drop opaque jargon like 'perf packet' and 'hottest target' so the what remains concrete to a reader outside the Slate tooling.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Picks or creates the hottest perf target, runs slate-ar-perf with no-regression checks, and stops at target, plateau, or correctness blocker' — with named tools and explicit stop conditions. Falls short of 5 because coverage is procedural and terms like 'perf packet' are left undefined.	4 / 5
Completeness	Has a clear 'what' (pick/create target, run slate-ar-perf with checks, stop at defined conditions) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('fastest-safe', 'perf', 'perf target') but misses the natural phrases users would actually say, such as 'make it faster', 'speed up', 'optimize', or 'performance'. Not 4 — a common variation is present ('perf') but the broader synonym set is absent; not 2 because more than one relevant keyword exists.	3 / 5
Distinctiveness Conflict Risk	Names a specific ecosystem ('Slate v2') and specific companion tools ('slate-ar-perf'), establishing a clear niche with distinct triggers and minimal conflict risk with generic performance or document skills.	5 / 5
	Total	15 / 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-fast/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.