Evaluation report

• Repository is reachable

  https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep @ 7182624 — ★ 13,277 · Python · MIT · last push today

• Manifest detected

  kind=skill slug=experiment-audit · path=skills/experiment-audit · source=SKILL.md

• Slug is URL-safe

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

• Slug is unique within kind

  No collision found for skill/experiment-audit

• Version is semver

  0.1.0

• Description quality

  53 words · 339 chars — "Audit experiment integrity before claiming results. Uses cross-model review (ext…"

• README is present and substantial

  183,954 chars · 17 sections · 36 code blocks

• Tags / topics declared

  20 total — ai-research, ai-tools, aris, autonomous-agent, claude, claude-code (+14)

• README has usage / example sections

  no labeled section but 36 code blocks document 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 skills/experiment-audit/SKILL.md · frontmatter source: SKILL.md

• Skill: body content present

  1,492 words · 11,353 chars · 27 sections · 8 code blocks

• Skill: allowed-tools scope

  10 declared: Bash(*), Read, Write, Edit, Grep (+5)

• Recent activity

  last push today

• Tests detected

  1 test directory · 37 test files

• CI configuration detected

  GitHub Actions (4 workflows)

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