slate-ar-recipe

Slate v2 Autoresearch recipe picker. Lists/recommends Codex Autoresearch recipes, produces read-only setup plans, and maps non-perf loops such as test runtime, typecheck, bundle size, memory, command latency, and quality-gap.

Quality

77%

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-recipe/SKILL.md

Quality

Content

87%

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

The body is concise, actionable, and well-organized with copy-paste-ready commands and a clear handoff, scoring strongly on conciseness, actionability, and progressive disclosure. Workflow clarity is the only middling dimension because validation steps exist as hints rather than an explicit checkpointed sequence.

Suggestions

Turn the validation hints into an explicit numbered workflow with checkpoints (e.g. run 'doctor --check-benchmark --explain', then 'benchmark-lint', and only proceed on success) to lift workflow clarity.

Add a brief feedback loop for the case where 'doctor' or 'benchmark-lint' fails so the skill guides error recovery rather than just naming the checks.

Sequence the decision flow explicitly (recommend -> show -> setup-plan -> handoff) so the intended path is unambiguous beyond the command listing.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes domain competence — it does not explain what recipes or benchmarks are and every section (Contract, Built-In Recipe Uses, Commands, Handoff) earns its place, matching the top anchor.	3 / 3
Actionability	Provides fully executable, copy-paste-ready CLI commands in the Commands block (e.g. 'node ../codex-autoresearch/.../autoresearch.mjs recipes list --cwd .tmp/slate-v2'), fitting the top anchor for concrete, specific examples.	3 / 3
Workflow Clarity	Commands and a handoff checklist are present, and there are validation hints ('benchmark-lint before any packet', 'doctor --check-benchmark'), but they are not framed as an explicit validate->fix->retry sequence with checkpoints, so it sits at the middle anchor.	2 / 3
Progressive Disclosure	At ~48 lines with no external bundle files needed, the content is well-organized into clearly labeled sections, which the rubric allows to score 3 for simple skills without external references.	3 / 3
	Total	11 / 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.

The description is specific and distinctive, naming concrete recipe actions and a clear niche, but it omits an explicit 'Use when...' trigger and leans on domain jargon that limits natural-term coverage. Completeness and trigger quality are the weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. when the user asks which Autoresearch loop to run or a task is measured but not obviously performance-specific.

Soften jargon in the lead ('Slate v2 Autoresearch recipe picker', 'non-perf loops') or pair it with plainer user-facing phrasing so natural trigger terms are more covered.

Surface common user phrasings (e.g. 'test runtime', 'bundle size', 'typecheck') as explicit triggers rather than only as examples of mapped loops.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Lists/recommends Codex Autoresearch recipes, produces read-only setup plans, and maps non-perf loops such as test runtime, typecheck, bundle size, memory, command latency, and quality-gap' — matching the top anchor for several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause; when-to-use is only implied, so completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes some natural measurement terms ('test runtime', 'typecheck', 'bundle size', 'memory') but the framing is jargon-heavy ('Slate v2 Autoresearch recipe picker', 'non-perf loops'), so it has relevant keywords but misses common user variations.	2 / 3
Distinctiveness Conflict Risk	The 'Slate v2 Autoresearch recipe picker' framing carves a clear, narrow niche tied to a specific toolchain, making it unlikely to trigger for unrelated skills.	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-recipe/SKILL.md
Commit: 45116fd

Reviewed: about 13 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.