Evaluation report

• Repository is reachable

  https://github.com/smixs/creative-director-skill @ d2cd8f4 — ★ 98 · Python · MIT · last push 8 days ago

• Manifest detected

  kind=skill slug=creative-director · path=creative-director · source=SKILL.md

• Slug is URL-safe

  "creative-director" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for skill/creative-director

• Version is semver

  0.1.0

• Description qualitywarn

  28 words · 207 chars — manifest description is empty; graded the GitHub repo description instead

  A skill's manifest description doubles as its trigger — add one to SKILL.md (15+ words, e.g. “use this skill when …”).

• README is present and substantial

  16,452 chars · 18 sections · 5 code blocks

• Tags / topics declared

  15 total — advertising, agent-skill, ai-agent, ai-creative, brainstorming, cannes-lions (+9)

• README has usage / example sections

  found: Installation · Usage

• Homepage / docs URL declared

  no homepage declared (registry will use the repo URL) — info-only, not blocking

• 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 creative-director/SKILL.md · frontmatter source: SKILL.md

• Skill: body content present

  2,828 words · 18,852 chars · 25 sections

• Skill: allowed-tools scope

  no allowed-tools restriction (Claude may use anything)

• 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.

• Recent activity

  last push 8 days ago

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