plate-plan

Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan. Use for behavior law, authority maps, protocol rows, parity gates, research-backed winner shifts, editor chrome contracts, and implementation-roadmap changes.

Quality

88%

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

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 body is highly actionable and workflow-clear with strong validation gates, but it is a long, repetitive monolith that violates progressive disclosure by inlining nearly all detailed process in SKILL.md rather than splitting it into referenced files. Tightening the duplicated lens/gate material would materially improve it.

Suggestions

Deduplicate the shadcn/Vercel-React/useEffect/performance-oracle/tdd lens guidance: state the applies-when matrix once in 'Applicable Implementation Reviews' and have other sections (Hard Policy, Required Artifacts, Read First, Pressure Passes, Confidence Score) reference it rather than restating it.

Collapse the repeated completion-gate and pass-state rules (Confidence Score, Goal And Plan State, Pass Schedule, Final Response) into one canonical gate section and link to it, to cut length without losing the validation logic.

Move the dense detail (Objection Ledger fields, Ecosystem Maintainer Pass, High-Risk Deliberate Mode, Done Handoff bullet taxonomy) into one-level-deep reference files under a bundle directory, keeping SKILL.md as an overview with the pass schedule and gate summary.

Dimension	Reasoning	Score
Conciseness	The ~1000-line body is competent and never lectures on concepts Claude already knows, but it is padded with heavy repetition — the shadcn/Vercel-React/useEffect/performance-oracle/tdd lens material recurs verbatim in Hard Policy, Required Artifacts, Read First, the Applicable Implementation Reviews matrix, Pressure Passes, and Confidence Score rules, and the completion gates are restated across multiple sections. It could be tightened substantially via dedup.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact file paths (docs/plans/YYYY-MM-DD-...md), exact enum values (current_pass_status: pending\|in_progress\|complete\|revise\|blocked\|skipped), a 23-item plan shape, a 9-pass schedule, decision-brief and objection-ledger field lists, and good/bad goal examples.	3 / 3
Workflow Clarity	The process is a clearly sequenced 9-pass schedule with explicit conjunctive completion gates, a pass-state ledger, and strong feedback loops ("If any gate fails, status stays pending", "Do not mark multiple major passes complete in one activation"), matching the validate-fix-retry anchor.	3 / 3
Progressive Disclosure	No skill bundle files exist and the doc links are one-level-deep and clearly signaled, but the SKILL.md itself is a monolithic ~1000-line wall of detailed process rather than an overview pointing to separate reference material — content that should be split into referenced files is almost entirely inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 third-person, concise, and cleanly answers both what the skill does and when to use it, with concrete scope enumeration and an explicit "Use for" trigger clause. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete scopes — "behavior law, authority maps, protocol rows, parity gates, research-backed winner shifts, editor chrome contracts, and implementation-roadmap changes" — naming the specific surfaces the plan touches rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what ("Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan") and when ("Use for behavior law, authority maps, protocol rows ..."), satisfying the explicit-trigger requirement for the top anchor.	3 / 3
Trigger Term Quality	The "Use for ..." clause gives broad coverage of domain trigger terms a Plate maintainer would naturally say (behavior law, authority maps, protocol rows, parity gates, roadmap changes), matching the rubric's good-coverage anchor; the process jargon ("pass-gated, evidence-scored plan") is mechanism, not trigger, but does not undermine the trigger list.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to Plate editor-behavior spec planning with distinct triggers, making it unlikely to fire for unrelated skills like a generic code review or bug-fix skill.	3 / 3
	Total	12 / 12 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 (1002 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: 29 missing, 29 deeper-than-1-level, 1 suspicious	Warning

	Total	11 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/plate-plan/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.