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

80%

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

85%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 content is highly actionable and the multi-pass workflow is exceptionally clear with explicit validation gates and feedback loops. The main weakness is progressive disclosure: a large monolithic body that could offload taxonomy, report templates, and scoring tables into reference files.

Suggestions

Extract the Portable Test Taxonomy and the report markdown template into references/ (e.g. TAXONOMY.md, REPORT_TEMPLATE.md) and link them one level deep from SKILL.md.

Consolidate the repeated license/copy-policy rules into a single authoritative section to reduce restatement across Core Rules, License Gate, and Output Shape.

Move the Confidence Score dimension table and caps into a reference file, keeping only the threshold summary inline.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific, assuming Claude's competence with editor concepts and providing executable commands without padding; however the license/copy-policy rules are restated across Core Rules, License Gate, and Output Shape, which could be consolidated.	4 / 5
Actionability	It supplies copy-paste-ready bash (exact rg filters, license classification pipeline, report_dir resolution), a complete report markdown template, and concrete verification commands covering the common harvest cases.	5 / 5
Workflow Clarity	The nine-pass schedule is explicitly sequenced with a pass-state ledger, scored completion gates (>=0.92, no dimension <0.85), caps, and feedback loops (rerun idempotency, re-validate on failure), giving clear validation checkpoints throughout.	5 / 5
Progressive Disclosure	There are no bundle files in references/scripts/assets and the entire skill is a single ~700-line SKILL.md; the Portable Test Taxonomy, Output Shape template, and Confidence Score tables are candidates for one-level-deep reference files but are inlined, so structure is present but references are not used.	3 / 5
	Total	17 / 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 highly specific and distinctive with a strong, concrete action list, but it omits an explicit "Use when..." trigger clause, which caps its completeness. Adding a natural-language trigger phrase would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. "Use when mining Lexical, ProseMirror, CodeMirror, Tiptap, Monaco, or Quill repos for portable editor-behavior tests to port into Slate v2 or Plate."

Surface the framework names (Lexical, ProseMirror, etc.) in the description so the natural trigger terms users say appear there, not only in the body.

Keep the concrete action list but pair it with the trigger phrase to satisfy both "what" and "when" at the description level.

Dimension	Reasoning	Score
Specificity	The description enumerates 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"—giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	The "what" is clearly stated, but the description lacks an explicit "Use when..." trigger clause; per the judging guidelines a missing trigger clause caps completeness at 3 even though the capability list is strong.	3 / 5
Trigger Term Quality	Natural terms like "editor repositories", "editor-behavior tests", "inventory", "skip reasons", and "coverage mapping" are present, but a few common phrasings a user would actually say (e.g. "harvesting tests", named editor frameworks) are not in the description itself.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined—mining editor repos for portable behavior tests routed to Slate v2 vs Plate with license-aware invariants—making collision with unrelated skills minimal.	5 / 5
	Total	17 / 20 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: cce36d3

Reviewed: 1 day 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.