Evaluation report

• Repository is reachable

  https://github.com/zscole/adversarial-spec @ f90cf0c — ★ 553 · Python · MIT · last push 6 months ago

• Manifest detected

  kind=plugin slug=adversarial-spec · source=.claude-plugin/plugin.json

• Slug is URL-safe

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

• Slug is unique within kind

  No collision found for plugin/adversarial-spec

• Version is semver

  1.0.0

• Description quality

  29 words · 242 chars — "Iteratively refine product specs through multi-model debate until consensus. Cla…"

• README is present and substantial

  20,106 chars · 18 sections · 27 code blocks

• Tags / topics declared

  7 total — anthropic, claude-ai, claude-code, claude-code-plugin, claude-skills, llm (+1)

• README has usage / example sections

  found: Quick Start · 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

• Plugin: manifest fields complete

• Plugin: bundled artifacts present

  1 skill

• Plugin: bundle shape

  1 skill

• Plugin: manifest location

  manifest at .claude-plugin/plugin.json (modern convention)

• Recent activitywarn

  last push 6 months ago — looks slowing down

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

• Tests detected

  1 test directory · 7 test files

• CI configuration detected

  GitHub Actions (1 workflows)

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