Evaluation report

• Repository is reachable

  https://github.com/eigent-ai/eigent @ 886e819 — ★ 14,536 · TypeScript · Apache-2.0 · last push today

• Manifest detected

  kind=skill slug=skill-security-auditor · path=resources/example-skills/skill-security-auditor · source=SKILL.md

• Slug is URL-safe

  "skill-security-auditor" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for skill/skill-security-auditor

• Version is semver

  0.1.0

• README has usage / example sectionswarn

  README has no Usage / Example / Quick start / Installation heading at any level

  Add a `# Usage`, `## Quick start`, or similar section so end users can copy/paste a working invocation. Code blocks alone work too if there are several.

• Description quality

  73 words · 546 chars — "Security auditing for code, configs, and infrastructure. Use when the user wants…"

• README is present and substantial

  22,070 chars · 11 sections · 2 code blocks

• Tags / topics declared

  9 total — agent-framework, agent-skills, agentic-ai, agentic-workflow, claude-cowork, claude-cowork-alternative (+3)

• Homepage / docs URL declared

  https://www.eigent.ai

• 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 resources/example-skills/skill-security-auditor/SKILL.md · frontmatter source: SKILL.md

• Skill: body content present

  886 words · 6,561 chars · 18 sections · 10 code blocks

• Skill: allowed-tools scope

  no allowed-tools restriction (Claude may use anything)

• Recent activity

  last push today

• Tests detected

  4 test directories · 120 test files

• CI configuration detected

  GitHub Actions (10 workflows)

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