editor-test-harvester

Mine external editor repositories for portable editor-behavior tests with ClawSweeper-style discipline: multi-pass exhaustive inventory, confidence scoring, framework-specific skip reasons, Slate/Plate coverage mapping, license-aware invariant extraction, and copy/refactor/create decisions.

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/editor-test-harvester/SKILL.md

Quality

Content

70%

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 and has a well-sequenced, validated workflow, but it is excessively long and repetitive and fails progressive disclosure by keeping everything inline with no companion reference files.

Suggestions

Split the heavy detail (Portable Test Taxonomy, full report template, license-detection script) into reference files under references/ and link to them one level deep to fix progressive disclosure.

Deduplicate the behavior-only / fresh-invariant rules, which are restated in at least five sections, to reduce token cost.

Keep a concise overview at the top of SKILL.md pointing to those references so the entry point stays lean.

Dimension	Reasoning	Score
Conciseness	The body is ~700 lines and restates the behavior-only / fresh-invariant rules many times across 'License Gate,' 'Core Rules,' 'Pass Schedule,' 'Output Shape,' and 'Verification'; it is mostly efficient and accurate but padded with repetition, so not the lean score-3 level.	2 / 3
Actionability	Provides fully executable bash (license detection, rg inventory commands, gitcrawl usage), explicit output paths, a complete report template, and concrete actions (covered/refactor-existing/create-new/copy-now/defer/plate-owned), matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	A clear 9-pass schedule with explicit sequence plus closure gates and validation checkpoints (bun check, bun check:full, check-complete.mjs, score thresholds) with error-recovery feedback, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist and the body is a monolithic wall of text with all detail inline; nothing is offloaded to one-level-deep reference files, matching the score-1 monolithic anchor rather than the structured score-2 or 3.	1 / 3
	Total	9 / 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 distinct, naming many concrete harvesting actions and a clear Slate/Plate niche. It loses points for lacking an explicit 'Use when...' trigger and for jargon-heavy language that users would not naturally say.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when mining tests from Lexical, ProseMirror, CodeMirror, Tiptap, Monaco, or Quill repos for Slate/Plate.'

Soften internal jargon ('ClawSweeper-style discipline,' 'license-aware invariant extraction') or pair it with plain-language terms a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'multi-pass exhaustive inventory, confidence scoring, framework-specific skip reasons, Slate/Plate coverage mapping, license-aware invariant extraction, and copy/refactor/create decisions' — matching the score-3 anchor for several specific actions.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit 'Use when...' trigger clause; per the judging guidelines a missing trigger clause caps completeness at 2, so it is not the level above.	2 / 3
Trigger Term Quality	Names the domain and some relevant terms ('editor repositories,' 'portable editor-behavior tests'), but leans on jargon like 'ClawSweeper-style discipline' and 'invariant extraction' that a user would not naturally say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The niche is clearly delimited — mining specific external editor repos into Slate/Plate — with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (714 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

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/editor-test-harvester/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.