slate-patch

Fix Slate v2 bugs in one pass with reproduction, behavior tests, architecture/DX/perf pressure, proactive rearchitecture when the patch is not the cleanest long-term shape, and final autoreview.

Quality

72%

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-patch/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, well-validated multi-step workflow, but it is long and monolithic for a complex skill and would benefit from offloading the selection-navigation matrix and benchmark-handoff detail into reference files.

Suggestions

Move the full Editor Selection Navigation Coverage matrix and the benchmark-target handoff workflow into dedicated reference files under references/, linking to them from the body to reduce inline length and improve progressive disclosure.

Tighten repeated refrains (e.g., the 'do not hand off works but dirty' sentiment appears across Hard Rules, Architecture Pressure, and Final Response) to a single canonical statement cross-referenced where needed.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without explaining basic concepts, but at ~370 lines it carries repeated refrains and inline detail (e.g., the full selection-navigation matrix and benchmark handoff workflow) that could be tightened or externalized, so it sits at 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands (e.g., 'pnpm bench:targets:dry-run -- <target-id>', the autoreview bash command with cwd, 'rg' proof commands), an explicit ownership ladder, and enumerated verdict types, meeting the fully-executable-guidance anchor at 3.	3 / 3
Workflow Clarity	A clearly sequenced Workflow 1-8 with explicit validation checkpoints (Verify step, autoreview 'rerun until no findings' loop) and an Architecture Pressure checklist with verdict outcomes, matching the clear-sequence-with-validation anchor at 3.	3 / 3
Progressive Disclosure	No bundle files exist in references/scripts/assets, and the body is a monolithic ~370 lines with large inline sections (selection-navigation coverage, benchmark handoff) that should be split out; workspace doc paths are mentioned inside instructions rather than as clearly signaled one-level-deep references, so it does not reach the well-organized-external-split anchor at 3.	2 / 3
	Total	10 / 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 has a clear, distinctive niche, but it leans on internal process jargon and omits an explicit "Use when" trigger clause, capping trigger-term quality and completeness at 2.

Suggestions

Add a 'Use when ...' trigger clause naming natural user phrases (e.g., 'Use when the user reports a Slate v2 bug, regression, or selection/focus/history issue and wants it fixed now, not planned').

Replace internal jargon ('architecture/DX/perf pressure', 'proactive rearchitecture', 'autoreview') with user-facing phrasing in the description so trigger terms match what users actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "reproduction, behavior tests, architecture/DX/perf pressure, proactive rearchitecture... and final autoreview", matching the multiple-specific-actions anchor rather than the domain-only anchor at 2.	3 / 3
Completeness	Clearly states what the skill does but contains no "Use when..." or equivalent explicit trigger guidance; per the judging guideline a missing trigger clause caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes some natural terms ("Slate v2 bugs", "fix") but is dominated by internal process jargon ("architecture/DX/perf pressure", "proactive rearchitecture", "autoreview") users would not naturally say; it does not reach the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The Slate v2 niche is sharply defined with distinct triggers ("Fix Slate v2 bugs", "one pass", "autoreview"), making it unlikely to fire for the wrong skill, matching the clear-niche anchor at 3.	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-patch/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.