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

68%

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

62%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 highly actionable and exceptionally well-gated with a clear pass sequence and validation checkpoints, but it is markedly verbose due to heavy rule repetition and is a monolith with no progressive disclosure into reference files.

Suggestions

Consolidate the issue-ledger/ClawSweeper discipline and the .tmp/slate-v2 verification rules into single canonical sections, replacing the repeated restatements with cross-references, to reduce token load.

Move the long Plan Shape schema, the maintainer objection-ledger field list, and the evidence-ladder/verdict vocabularies into reference files under references/ and link to them, enabling progressive disclosure.

Tighten abstract instruction phrasing ('run the relevant command') into the specific named command where the surface is known.

Dimension	Reasoning	Score
Conciseness	At ~1260 lines the body restates the same rules several times—issue-ledger/ClawSweeper discipline appears in Required Artifacts, Read First, Issue Ledger Pass, PR Reference And Issue Accounting, and Pressure Passes, and the .tmp/slate-v2 verification gate recurs across Hard Policy, Verification Workspace Gate, and Pressure Passes—so it is noticeably verbose with padded restatements.	2 / 5
Actionability	Provides concrete commands and templates (create-goal-scratchpad.mjs invocation, rg -n grep examples, bun --filter gates), concrete file paths, a goal-handle format, named state fields, and exact wording like 'Fixes #....: <description>'; minor gaps remain where commands stay abstract ('run the relevant command').	4 / 5
Workflow Clarity	The 12-pass schedule is explicitly sequenced, closure is gated by a conjunctive completion-threshold checklist with a pending/done state machine, and feedback loops are present (validate-fix-rerun, autoreview until clean), giving clear checkpoints and error recovery for a risky batch workflow.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is a monolithic 1260-line document; section headers give some structure, but content that clearly belongs in separate reference files (the Plan Shape schema, objection-ledger fields, repeated issue-ledger rules) is inlined rather than split out.	3 / 5
	Total	14 / 20 Passed

Description

75%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 is specific and highly distinct, naming the domain and several concrete review dimensions and actions. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the activation condition only implied.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases (e.g., repeated Slate v2 architecture/DX review requests, plan-confidence gating) to lift completeness above 3.

Include a couple of common synonyms a user might say ('Slate v2 API review', 'editor architecture plan') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Slate v2 architecture/API) and lists multiple concrete actions—review plans against five named dimensions, write a scored plan, and gate completion until every pass and closure gate is complete—giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only weakly implied; per the rubric guideline this caps completeness at 3.	3 / 5
Trigger Term Quality	Includes domain-natural terms like 'Slate v2', 'architecture/API plans', 'React 19.2 runtime performance', 'unopinionated DX', 'legacy-regression proof', and 'shadcn-style composability', but is missing some common synonyms or phrasings a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to Slate v2 architecture/API review against named dimensions, giving it a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	17 / 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: 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.