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

73%

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

85%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 dense, highly actionable skill body with executable commands, explicit validation gates, and well-defined stop/plateau rules — it assumes competence and wastes almost no tokens. Its main structural weakness is that everything lives in SKILL.md: the two long default contracts belong in reference files so the top-level body stays an overview.

Suggestions

Move the Pagination Default Contract and Huge Document Select-All Default Contract into references/ files (e.g. references/pagination-contract.md, references/select-all-contract.md), keeping a two-line summary and pointer in SKILL.md.

Add a short table of contents or pointer block near the top so the reference files are clearly signaled at one level of depth.

Trim the migration-ownership paragraph in Missing Target Policy to the two-sentence decision rule, cutting duplicated rationale.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude knows Slate and Codex Autoresearch — no concept explanations, no padding, every section carries operational content. A few spots could be trimmed (the migration ownership paragraph, some cohort/metric repetition across the two contracts), keeping it just below anchor 5.	4 / 5
Actionability	Fully executable guidance throughout: exact commands ('pnpm bench:targets:list', 'node tooling/scripts/bench-targets.mjs autoresearch-init <target-id>'), a copy-pasteable target route URL with concrete query params, an exact METRIC output format, and named cohort/metric contracts. Anchor 5 fits: copy-paste ready commands covering the common cases.	5 / 5
Workflow Clarity	The Default Path is a numbered 6-step sequence with explicit validation checkpoints ('dry-run the target and run pnpm bench:targets:check before AR init'), the Exactness Gate defines a feedback loop (log checks_failed or discard, never keep), and the Handoff section is a report checklist. Matches anchor 5: clear sequence, explicit validation, error-recovery loops, checklists.	5 / 5
Progressive Disclosure	Section structure is good, but there are no reference files at all (no references/, scripts/, or assets/ directories) and roughly 100 lines of detailed default contracts (Pagination, Huge Document Select-All) are inlined in SKILL.md where they clearly belong in separate one-level-deep reference files. Fits anchor 3 (structure present, content that should be separate is inline); not 2 because the structure is well-organized, not minimal.	3 / 5
	Total	17 / 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.

A distinctive, well-scoped description with concrete named components, but it omits any 'when to use this' trigger guidance and the natural trigger vocabulary that would let a user (or the model) select it. The jargon-heavy phrasing works for insiders but weakens discoverability.

Suggestions

Append a 'Use when...' sentence with concrete trigger phrases, e.g. 'Use when the user says fast, fastest, max perf, pagination, virtualization, or benchmark, or asks to make a Slate v2 surface faster.'

Include natural synonyms and surface words users actually say (typing, scroll, mount, huge document) alongside the technical terms.

State the delegation boundary in plain terms ('generic loop mechanics live in slate-ar') so the description doubles as conflict avoidance.

Dimension	Reasoning	Score
Specificity	Names the domain ('Slate v2 performance lane for Codex Autoresearch') and several concrete additions ('target registry, fastest-safe stop rules, exactness gates, and pagination/virtualization defaults') plus an explicit delegation boundary. Not a 5 because it reads as a scope declaration rather than a comprehensive list of executable actions; not a 3 because it goes beyond 1-2 generic actions.	4 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3, which matches the anchor 'clear what, when missing'.	3 / 5
Trigger Term Quality	Relevant keywords exist ('performance', 'pagination', 'virtualization') but the natural phrases users actually say ('fast', 'fastest', 'max perf', 'make it faster', 'benchmark') are absent from the description. Fits anchor 3 (some relevant keywords, missing common variations and synonyms); not 4 because the whole natural-language trigger layer is missing.	3 / 5
Distinctiveness Conflict Risk	'Slate v2 performance lane for Codex Autoresearch' carves a very narrow niche, and the explicit delegation statement ('Delegates generic loop mechanics to slate-ar/codex-autoresearch') distinguishes it from sibling skills. Minimal conflict risk with generic performance or Slate 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-perf/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.