Evaluation report

• Repository is reachable

  https://github.com/massimodeluisa/recursive-decomposition-skill @ 1780d46 — ★ 40 · MIT · last push 6 months ago

• Manifest detected

  kind=plugin slug=recursive-decomposition · path=plugins/recursive-decomposition/.claude-plugin · source=plugin.json

• Slug is URL-safe

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

• Slug is unique within kind

  No collision found for plugin/recursive-decomposition

• Version is semver

  1.0.1

• Description quality

  18 words · 138 chars — "Agent skill for handling long-context tasks through recursive decomposition stra…"

• README is present and substantial

  10,861 chars · 15 sections · 9 code blocks

• Tags / topics declared

  9 total — ai-agents, claude-code-plugin, claude-code-skill, claude-code-skills, claude-skills, llm (+3)

• README has usage / example sections

  found: Installation · Usage · Example

• Homepage / docs URL declared

  https://arxiv.org/abs/2512.24601

• 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: bundled artifacts presentwarn

  Couldn't find a skills/ subdir or an MCP server config inside the plugin

  A plugin is most useful when it bundles ≥ 1 skill or an MCP server.

• Plugin: manifest fields complete

• Plugin: bundle shape

  empty bundle

• Plugin: manifest location

  manifest at plugin.json

• 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 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.

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