Evaluation report
Warningsscholarly-writing-refiner · skill9d252b3· last month
Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.
Structural
7 passedRepository is reachable
https://github.com/zebbern/claude-code-guide @ 9d252b3 — ★ 4,568 · Python · MIT · last push today
Manifest detected
kind=skill slug=scholarly-writing-refiner · path=skills/scholarly-writing-refiner · source=SKILL.md
Slug is URL-safe
"scholarly-writing-refiner" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for skill/scholarly-writing-refiner
Version is semver
0.1.0
Manifest present and parseable
Manifest found at SKILL.md.
Name declared and well-formed
Name "scholarly-writing-refiner" is well-formed.
Documentation
8 passed1 warningHomepage or repository declaredwarn
No homepage or repository declared.
Add a "homepage" or "repository" field to SKILL.md.
Description quality
46 words · 364 chars — "Polishes academic English paragraph by paragraph, reviewing grammar, word choice…"
README is present and substantial
168,182 chars · 12 sections · 127 code blocks
Tags / topics declared
20 total — ai, ai-agent, ai-agent-tools, anthropic-claude, claude, claude-ai (+14)
README has usage / example sections
found: Quick Start · Example · Example
Homepage / docs URL declared
no homepage declared (registry will use the repo URL) — info-only, not blocking
Safety
8 passed1 queuedLICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found
License declared
License file present.
No credentials in file contents
No credentials found in 1 files.
No invisible characters in model-read text
No invisible characters in 1 files.
Kind-specific
6 passed4 warningsSkill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Tool scope declaredwarn
No tool scope declared.
Declare `allowed-tools` with the minimum set the skill actually needs. If it needs none, declare an empty list explicitly.
Skill is not needlessly expensive to loadwarn
Skill loads heavier than it needs to (~91 + ~5149 tokens). body is ~5149 tokens and inlines everything — no scripts/ or references/ to lazy-load.
Trim the description to the routing cue. Move long procedures, examples, and reference material into files under references/ and point to them, so they load only when actually needed.
Description says when to use the skillwarn
Description says what the skill is, but not when to use it.
Maintenance
2 passed1 warning1 queuedTests detectedwarn
no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files
Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.
Recent activity
last push today
CI configuration detected
GitHub Actions (1 workflows)