run2_composition-technique
Advanced techniques for composing seven-character regulated verse with thematic coherence
- License 许可
- MIT
- 最近更新
- 2026-10-02
- Stars
- ★ 92
- Forks
- 7
01 前言 Front Matter
- name
- run2_composition-technique
- description
- Advanced techniques for composing seven-character regulated verse with thematic coherence
03 SKILL.md 正文
Composition Techniques for Regulated Verse
Narrative Structure
- Opening (lines 1-2): Establish the scene and mood; introduce the problem
- Development (lines 3-6): Elaborate through parallel couplets
- Couplet 1 (lines 3-4): Describe hardship, suffering, or physical reality
- Couplet 2 (lines 5-6): Express emotion, longing, or consequence
- Conclusion (lines 7-8): Resolution, hope, or prayer
Parallel Couplet Excellence (对仗)
For lines 3-4 and 5-6 to work as parallel couplets:
Grammatical Parallelism
Each position should have the same word type:
- Adjective-adjective
- Verb-verb
- Noun-noun
Semantic Contrast
- Opposite meanings create impact
- "Then and now" contrast
- Physical vs. emotional description
Examples of Strong Couplets
- 断垣残壁见冬霜 / 焦土荒芜寄希望
- Parallel: [Adj+Noun] [Verb+Noun] / [Adj+Noun] [Verb+Noun]
- Contrast: Winter desolation / Spring hope
Voice and Perspective
- Use first person (我、我们) to represent ordinary person
- Include family (妻、儿、父、母) to show personal impact
- Show concrete suffering, not abstract philosophy
Rhyming Practice
- For regulated verse, lines 2, 4, 6, 8 must rhyme
- Use different rhyme words (rhyme 4 words, not repeat same sound)
- Ensure rhyme words fit naturally into meaning
04 同仓库更多 Skills
object_counter
Count occurrences of an object in the image using computer vision algorithm.
travel-planning-workflow
Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
bundled-dataset-search-tool
invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.
glm-output
Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final /root/metrics.json.
glm-calibration
Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.
glm-basics
A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.