slate-ar-next

Slate v2 Autoresearch daily driver. Reads current state, chooses the best next owner, and runs one safe next step without making the user pick quality/gate/perf/patch/finalize details.

Quality

61%

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-next/SKILL.md

Quality

Content

76%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 concise, well-structured routing skill with concrete condition-to-owner mapping and a clear default sequence. Its main weakness is the absence of an explicit validation checkpoint before the single mutating step it performs.

Suggestions

Add an explicit validation checkpoint before 'run one safe next step' (e.g., confirm read-only status and that the chosen step is non-destructive, or verify the metric/check passes before proceeding).

Spell out what 'report metric/check result' means concretely — which metric or check to read and how to pass/fail it — so the report-back step is unambiguous.

Clarify the stopping condition for multi-step paths with an explicit checklist of what constitutes a 'first meaningful packet or fix'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence throughout — routing rules, the default 5-step sequence, and handoff report fields are stated without padding or restating concepts Claude already knows.	5 / 5
Actionability	Routing rules map concrete conditions to named sibling skills (e.g., 'Known correctness failure: slate-patch') and list an explicit 5-step default sequence, but it is instruction-only with no executable commands or code, leaving minor gaps in concrete execution detail.	4 / 5
Workflow Clarity	A clear numbered 5-step default sequence is present with a report-back checkpoint, but this is a mutating skill ('runs one safe next step') and validation before the mutating step is only implicit, which caps workflow clarity at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Content is well organized into Contract, Routing, and Handoff sections with everything appropriately inline for a compact routing skill; no bundle files exist, so structure is good with only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

47%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 conveys a clear purpose and concrete workflow but leans on internal jargon and lacks an explicit 'Use when...' trigger. It is distinguishable within its niche yet overlaps with several sibling skills.

Suggestions

Add an explicit 'Use when...' trigger clause with natural user phrases (e.g., 'Use when the user asks to do the next Slate v2 autoresearch step or move a surface forward one safe step').

Replace or gloss internal terms like 'next owner' and 'quality/gate/perf/patch/finalize' with language a user would naturally say so the skill triggers correctly.

Sharpen distinctiveness by stating what this skill does NOT do (e.g., 'not for broad multi-step overhauls — use slate-ar-perfect') to reduce overlap with sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Slate v2 Autoresearch daily driver') and several concrete actions ('Reads current state, chooses the best next owner, and runs one safe next step'), but coverage of capabilities is not exhaustive — it describes one workflow rather than a full action list.	4 / 5
Completeness	It clearly states what the skill does, but the 'when' is only weakly implied by 'daily driver' with no explicit 'Use when...' trigger clause, which caps completeness at 3.	3 / 5
Trigger Term Quality	Relies on internal project jargon ('next owner', 'quality/gate/perf/patch/finalize', 'daily driver') rather than natural phrases a user would actually say; only minimal generic keywords are present.	2 / 5
Distinctiveness Conflict Risk	It targets a specific niche (Slate v2 AR), but heavily references sibling skills (slate-ar-perfect, status, gate, etc.) and jargon-heavy triggers leave real overlap risk with those 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-next/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.