slate-ar

Wrap Codex Autoresearch for Slate v2 measured loops. Delegates generic packet/dashboard/finalization mechanics to codex-autoresearch while enforcing `.tmp/slate-v2`, Slate correctness routing, target registry context, and short operator modes.

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/SKILL.md

Quality

Content

67%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 a well-structured, actionable operational spec with explicit validation gates and good progressive disclosure via delegation to codex-autoresearch. Its main weakness is redundancy: routing rules are restated across several sections, which hurts conciseness.

Suggestions

Consolidate the routing rules: state them once in 'Start Or Resume' or 'Relationship To Other Lanes' and have 'Natural Modes' reference that table instead of restating every route.

Trim the 'Relationship To Other Lanes' list to the lanes that affect routing decisions, or move the full registry to a reference file.

Add a short validate->fix->retry feedback loop inside 'Start Or Resume' for the packet keep/discard cycle so the workflow reads as an explicit error-recovery loop rather than a route-elsewhere rule.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of beginner-concept padding, but routing to slate-patch/slate-plan/slate-ar-perf/slate-ar-gate is restated across 'Use When', 'Relationship To Other Lanes', 'Natural Modes', and 'Start Or Resume', which could be tightened; not a 4 due to that repeated redundancy.	3 / 5
Actionability	Provides concrete executable commands ('pnpm bench:targets:dry-run -- <target-id>', 'node tooling/scripts/bench-targets.mjs autoresearch-init <target-id>', 'finalize-preview --cwd .tmp/slate-v2') and specific paths; not a 5 because much of the guidance is routing to other skills rather than directly copy-paste-ready execution.	4 / 5
Workflow Clarity	'Start Or Resume' is a clear 5-step sequence with explicit validation checkpoints (keep only when measured target improves and correctness checks pass; checks_failed/discard on behavior regression) and the finalization mode has explicit approval gates, satisfying the destructive/batch validation requirement; not a 5 because some checkpoints route elsewhere rather than providing an in-loop validate->fix->retry cycle.	4 / 5
Progressive Disclosure	Well-organized into clear sections and explicitly defers command details, packet lifecycle, dashboard operation, ASI syntax, and finalization rules to codex-autoresearch as one-level, well-signaled references; not a 5 because the body is long and the lane-relationship list plus repeated routing could arguably be trimmed or factored out.	4 / 5
	Total	15 / 20 Passed

Description

58%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 clearly communicates what the skill does and establishes a distinct Slate v2 wrapper niche, but it is jargon-heavy and lacks an explicit 'when to use' trigger clause. Adding natural trigger phrases and a 'Use when...' clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause listing concrete natural-language triggers (e.g., 'Use when the user invokes slate-ar or asks for Slate v2 research, status, quality-gap, or finalization').

Soften jargon with natural synonyms users actually say ('research a topic', 'check status', 'find quality gaps') alongside the technical terms.

Briefly contrast against the closest siblings (slate-ar-perf, slate-ar-next) in the description to reduce overlap risk within the slate-ar* family.

Dimension	Reasoning	Score
Specificity	Names the Slate v2 measured-loop domain and lists several concrete responsibilities ('Delegates generic packet/dashboard/finalization mechanics', 'enforcing .tmp/slate-v2, Slate correctness routing, target registry context, and short operator modes'), with only minor coverage gaps; not a 5 because the actions are structural/delegation rather than a comprehensive set of user-facing concrete actions.	4 / 5
Completeness	The 'what' is clear (wraps Codex Autoresearch for Slate v2 and enforces specific defaults), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relies on technical jargon ('Codex Autoresearch', 'measured loops', 'packet/dashboard/finalization mechanics', 'target registry context') with few natural phrases a user would actually say; it omits common trigger words like 'research', 'status', 'quality gap' that appear only in the argument-hint, so it is not a 4.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche as the Slate v2 wrapper that delegates generic mechanics to codex-autoresearch, distinguishing it from the generic engine; not a 5 because it does not disambiguate within the crowded slate-ar* sibling family.	4 / 5
	Total	14 / 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/SKILL.md
Commit: d76efae

Reviewed: 3 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.