agentsclimarketplace

Run2 verification checklist

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/chinese-poem-generator/run2_verification-checklist

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_verification-checklist

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Comprehensive checklist to verify a completed seven-character regulated verse meets all requirements

SKILL.md

1.9 KB, 452 tokens by cl100k_base, as published. Nobody here has run it

Verification Checklist for 七言律诗

Format Requirements

  • Title present: One line with poem title
  • Total lines: Exactly 8 lines
  • Characters per line: Exactly 7 characters in each line
  • No extra spaces or formatting: Clean, readable text

Rhyme Scheme (韵脚)

  • Lines 2, 4, 6, 8 rhyme: Check ending sounds using modern Mandarin pronunciation
  • Rhyme consistency: All 4 rhyming lines use same rhyme category (-ang, -ing, -an, etc.)
  • Clear rhyme words: Rhyming characters are identifiable and natural-sounding

Parallel Couplets (对仗)

  • Lines 3-4 form couplet:
    • Grammatical structure mirrors each other
    • Word positions correspond (Adj-Adj, Verb-Verb, Noun-Noun)
    • Semantic relationship: contrast, parallel, or complementary
  • Lines 5-6 form couplet: Same checks as 3-4

Content Requirements

  • Theme: Focuses on peace, tranquility, or anti-war sentiment
  • War suffering: Clearly describes difficulties, hardship, or devastation
  • Peace longing: Expresses hope, prayer, or yearning for peace
  • Ordinary perspective: Voice represents common people, not rulers or warriors
  • Emotional coherence: Narrative flows from suffering → longing → hope

Language Quality

  • Natural diction: Words and phrases sound poetic, not forced
  • Meaningful imagery: Vivid descriptions that evoke emotion
  • Character appropriateness: Each character fits context and meaning
  • No anachronisms: Language feels classical Chinese, not modern

Modern Mandarin Compliance

  • Rhyming based on modern pronunciation: Not historical Middle Chinese
  • Readable in modern context: But maintains classical style

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.