slate-ar-perf

Slate v2 performance lane for Codex Autoresearch. Delegates generic loop mechanics to slate-ar/codex-autoresearch and adds target registry, fastest-safe stop rules, exactness gates, and pagination/virtualization defaults.

Quality

72%

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-perf/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced policy/router skill with explicit validation checkpoints and feedback loops, held back only by length and the absence of progressive-disclosure file structure for its two inline default contracts.

Suggestions

Move the Pagination Default Contract and Huge Document Select-All Default Contract into reference files (e.g. references/pagination-contract.md, references/huge-doc-select-all-contract.md) and link to them from the body to improve progressive disclosure and reduce inline length.

Tighten the two default-contract catalogs by collapsing repetitive metric/cohort/checklist prose into compact tables or terse bullet sets.

Dimension	Reasoning	Score
Conciseness	No concept re-explanation and it assumes Claude's competence, but two full inline default-contract catalogs (Pagination, Huge-Document Select-All) run long and could be tightened or partially deferred.	2 / 3
Actionability	Provides concrete executable commands (pnpm bench:targets:list, node tooling/scripts/bench-targets.mjs autoresearch-init <target-id>), exact METRIC examples, route URLs, and numeric promotion targets, all copy-paste ready.	3 / 3
Workflow Clarity	Clear numbered default path, a target-creation checklist with an explicit 'dry-run... before AR init' checkpoint, and an Exactness Gate feedback loop ('log checks_failed or discard, never keep') with plateau/promotion rules.	3 / 3
Progressive Disclosure	Single-file skill with well-organized sections, but no bundle reference files and two large inline default contracts that could be split; the only references point to sibling skills and external repo paths rather than one-level-deep bundle materials.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific, well-scoped description that names concrete capabilities and a clear niche, but it lacks an explicit 'Use when...' trigger clause and only partially covers the natural trigger terms the body enumerates.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g. 'Use when the user says fast, fastest, max perf, pagination, virtualization, benchmark, or wants a Slate v2 surface faster').

Surface the missing natural trigger terms ('fast', 'max perf', 'benchmark') directly in the description so trigger coverage matches the body's 'Use When' list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete features ('Delegates generic loop mechanics', 'adds target registry', 'fastest-safe stop rules', 'exactness gates', 'pagination/virtualization defaults') rather than vague language.	3 / 3
Completeness	Clearly states what the skill does, but provides no explicit 'Use when...' trigger clause in the description; the 'when' is only implied via trigger terms, capping completeness at 2.	2 / 3
Trigger Term Quality	Includes 'fastest', 'pagination', 'virtualization', and 'performance', but omits common variations the body itself surfaces ('fast', 'max perf', 'benchmark'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The 'Slate v2 performance lane' niche and explicit delegation to slate-ar/codex-autoresearch clearly separate it from sibling skills (slate-patch, slate-plan), making wrong-skill triggering unlikely.	3 / 3
	Total	10 / 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-perf/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.