slate-plan

Review Slate v2 architecture/API plans against React 19.2 runtime performance, Slate-close unopinionated DX, legacy-regression proof, research evidence, and shadcn-style composability; write a scored plan and keep completion pending until every required pass and closure gate is complete.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/slate-plan/SKILL.md

Quality

Content

56%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 highly actionable and validation-heavy process skill with concrete commands, checklists, and feedback loops, but it is a 61KB monolith with substantial rule duplication across sections. It would score far better split into reference files with the redundancy collapsed.

Suggestions

Deduplicate the ClawSweeper/ledger and `.tmp/slate-v2` verification rules, each currently stated in 3-5 sections (Required Artifacts, Read First, Issue Ledger Pass, PR Reference And Issue Accounting, Hard Policy, Verification Workspace Gate, Pressure Passes), into one authoritative section.

Move the stable reference material — the Slate Maintainer Objection Ledger field list, the issue-classification rules, and the 25-item Plan Shape — into separate reference files (e.g., references/objection-ledger.md, references/issue-accounting.md), since no references/ bundle exists at all.

Name the exact `.tmp/slate-v2` verification commands for each touched surface instead of placeholders like "the relevant command" and "the broadest feasible gate", which currently force the model to guess the closure gate.

Dimension	Reasoning	Score
Conciseness	The 1,250-line body restates the same policies repeatedly — ClawSweeper/ledger discipline appears in Required Artifacts, Read First, Issue Ledger Pass, PR Reference And Issue Accounting, and Pass Schedule, and the `.tmp/slate-v2` verification rule is repeated across three sections. It avoids generic-concept padding, but the duplicated sections are clearly unnecessary tokens.	2 / 5
Actionability	Concrete executable material throughout: `node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template slate-plan --title "<short Slate Plan title>"`, `rg -n "RenderVoidProps\|renderVoid\|renderElement" .tmp/slate-v2/packages/slate-react .tmp/slate-v2/site`, exact goal strings, exact table formats, and exact status vocabularies. Minor gaps: several gates only say "run the relevant `.tmp/slate-v2` command" or "the broadest feasible `.tmp/slate-v2` gate" without naming commands.	4 / 5
Workflow Clarity	A 12-step pass schedule, an explicit pass-status vocabulary, a closure checklist ("Before Slate Plan closure, prove in the plan"), and feedback loops ("A failing relevant `.tmp/slate-v2` command keeps the plan or execution review `pending`") are all present. Not a 5 because the workflow is smeared across Hard Policy, Goal And Plan State, Pass Schedule, and User Review And Execution Mode with heavy duplication, so following the flow requires cross-referencing redundant sections.	4 / 5
Progressive Disclosure	No bundle files exist, and everything is inlined in the monolithic SKILL.md. Sections are well-organized with headers and clearly signaled repo-file references (e.g., links to vercel-react-best-practices, performance-oracle, and tdd SKILL.md files, and `docs/plans/templates/slate-plan.md`), but large policy blocks (the objection ledger format, issue accounting, and the 25-item Plan Shape) that belong in separate reference files are inlined — bordering on a 2 given the sheer volume.	3 / 5
	Total	13 / 20 Passed

Description

70%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 specific, distinctive description that clearly states what the skill does with concrete named review criteria. Its main weakness is the absence of an explicit use-when trigger clause and of natural synonyms a user might phrase differently.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks for a harsh or absolute-best Slate v2 architecture/API/DX review, or when repeated review keeps producing more suggestions."

Include natural synonyms such as "rich text editor", "Slate 2", or "migration" so users phrasing the request differently still surface the skill.

Mention the execution mode (running an accepted plan against the live `.tmp/slate-v2` workspace) so the description covers both halves of the two-phase skill.

Dimension	Reasoning	Score
Specificity	"Review Slate v2 architecture/API plans against React 19.2 runtime performance, Slate-close unopinionated DX, legacy-regression proof, research evidence, and shadcn-style composability; write a scored plan and keep completion pending..." lists several specific actions with named criteria. Not a 5 because it omits the execution-mode half of the skill and leans on domain jargon rather than a comprehensive action list.	4 / 5
Completeness	The "what" is clear and concrete (review plans against named criteria, write a scored plan, hold completion pending), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only implied by the task named in the "what". Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	"Slate v2", "architecture/API plans", "React 19.2", "DX", and "composability" are exactly what a user of this niche would say, and "Review" matches the natural request verb. A few natural variations are missing (e.g., "rich text editor", "Slate 2", "migration"), keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	"Slate v2", "React 19.2 runtime performance", and "shadcn-style composability" carve out a clear niche with distinct triggers and minimal overlap risk against generic review or code-review skills.	5 / 5
	Total	16 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1261 lines); consider splitting into references/ and linking	Warning
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
relative_links	Relative link issues: 4 missing, 4 deeper-than-1-level, 1 suspicious	Warning

	Total	11 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/slate-plan/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.