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

78%

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

86%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 lean, highly actionable instruction skill: an executable command block, explicit routing rules, and a clear handoff protocol, with zero token waste. Its main weakness is the implicit rather than explicit workflow sequence and the unexplained placeholder for workload customization.

Dimension	Reasoning	Score
Conciseness	The body (~49 lines) contains no concept explanations and no padding — every line in Contract, Built-In Recipe Uses, Commands, and Handoff is operative. Not 4: there are no over-explanation instances to trim; it assumes Claude's competence throughout.	5 / 5
Actionability	The Commands section is a fully executable, copy-paste-ready CLI block covering list, recommend, show, setup-plan, and doctor, plus concrete routing rules ("prefer explicit Bun/package commands over a generic npm recipe"). Not 5: "after replacing the placeholder with the real workload" refers to a placeholder that is never shown, leaving a minor gap in how to customize memory-usage and command-latency recipes.	4 / 5
Workflow Clarity	The skill is read-only with a clear implied progression (recommend → inspect → setup-plan → handoff) and checkpoints present ("run benchmark-lint before any packet", the doctor --check-benchmark --explain command). Not 5: the sequence is conveyed by section order rather than explicit numbered steps, and there is no guidance on how to choose between overlapping recipes (e.g. node-test-runtime vs vitest-runtime) beyond naming them.	4 / 5
Progressive Disclosure	The body is under 50 lines with well-organized sections and no need for external references — no references/, scripts/, or assets/ bundle exists, and no file references in the body are broken. The simple-skill exception applies: well-organized sections alone merit 5.	5 / 5
	Total	18 / 20 Passed

Description

71%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 strong, specific description that clearly states what the skill does and enumerates concrete capability areas, undermined by the complete absence of when-to-use trigger guidance in the description itself. Distinctiveness is good but shares vocabulary with generic perf skills.

Suggestions

Append an explicit trigger clause to the description, e.g. "Use when the user asks which Autoresearch loop to run, or a task is measured but not obviously performance-specific" — mirroring the body's "Use this when..." guidance.

Add natural-language synonyms (e.g. "slow tests", "build size", "startup time") alongside the technical metric names to broaden trigger coverage beyond internal jargon.

Clarify that this skill routes and plans rather than runs loops, to reduce trigger overlap with actual performance-execution skills.

Dimension	Reasoning	Score
Specificity	"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" lists multiple specific concrete actions with comprehensive coverage of the loop types. Not 4: there are no meaningful coverage gaps — the what is enumerated fully.	5 / 5
Completeness	The "what" is explicit (list/recommend recipes, produce setup plans, map loops), but the description has no "Use when..." clause or equivalent trigger guidance — that guidance appears only in the body, not the description. The judging guideline caps completeness at 3 for a missing when-clause; not 4 because the when is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	"test runtime", "typecheck", "bundle size", "memory", "command latency" are natural metric terms users would say, giving good keyword coverage. Not 5: synonyms and variations are missing and terms like "Autoresearch recipes" and "setup plans" are internal jargon rather than natural user phrasing.	4 / 5
Distinctiveness Conflict Risk	"Slate v2 Autoresearch recipe picker" carves a clear niche with distinct triggers around Codex Autoresearch recipes and non-perf loop mapping. Not 5: the enumerated metric terms (bundle size, memory, command latency) overlap with generic performance-tuning skills that could vie for the same trigger.	4 / 5
	Total	16 / 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-recipe/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.