Evaluation report

• Repository is reachable

  https://github.com/SDLLL/claude-for-safari @ dc2f449 — ★ 40 · MIT · last push 4 months ago

• Manifest detected

  kind=skill slug=claude-for-safari · source=SKILL.md

• Slug is URL-safe

  "claude-for-safari" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for skill/claude-for-safari

• Version is semver

  0.1.0

• Description quality

  76 words · 486 chars — "Control the user's real Safari browser on macOS using AppleScript and screencapt…"

• README is present and substantial

  5,397 chars · 6 sections · 4 code blocks

• Tags / topics declared

  12 total — ai-agent, applescript, browser-automation, browser-control, claude-code, claude-code-skill (+6)

• README has usage / example sections

  found: Quick Start

• Homepage / docs URL declared

  https://safari.skilljam.dev

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• Skill: 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`.

• Skill: SKILL.md present

  found at SKILL.md · frontmatter source: SKILL.md

• Skill: body content present

  1,728 words · 12,223 chars · 17 sections · 22 code blocks

• Skill: allowed-tools scope

  no allowed-tools restriction (Claude may use anything)

• Recent activitywarn

  last push 4 months ago — looks slowing down

  Consumers prefer artifacts that are actively maintained (threshold: 90 days, configurable via EVAL_RECENCY_PASS_DAYS).

• Tests 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.

• CI configuration detectedwarn

  no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)

  Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.

Behavioral results aren't published for this artifact. The publisher sees the full report on their own dashboard.