Evaluation report

• Repository is reachable

  https://github.com/YIKUAIBANZI/forge-skill @ 6bb2448 — ★ 100 · Python · MIT · last push 3 months ago

• Manifest detected

  kind=skill slug=eval-consistency · path=evals/eval-consistency · source=SKILL.md

• Slug is URL-safe

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

• Slug is unique within kind

  No collision found for skill/eval-consistency

• Version is semver

  0.1.0

• Description quality

  44 words · 69 chars — "测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景，生成回复并按 5 个维度评分，输出一致性报告。"

• README is present and substantial

  8,076 chars · 17 sections · 11 code blocks

• Tags / topics declared

  7 total — ai-agent, claude-code, claude-skill, digital-twin, memory, persona (+1)

• README has usage / example sections

  no labeled section but 11 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 evals/eval-consistency/SKILL.md · frontmatter source: SKILL.md

• Skill: body content present

  891 words · 1,917 chars · 11 sections · 4 code blocks

• Skill: allowed-tools scope

  no allowed-tools restriction (Claude may use anything)

• Recent activitywarn

  last push 3 months ago — looks slowing down

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

• 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.

• Tests detected

  1 test directory · 8 test files

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