seven-char-regulated-verse
Guidance on composing seven-character regulated verse (七言律诗). Use this skill whenever a task requires writing traditional Chinese poetry in the seven-character regulated style, ensuring adherence to structural, parallelism, and rhyming rules (using modern Mandarin pronunciation).
- License 许可
- MIT
- 最近更新
- 2026-10-02
- Stars
- ★ 93
- Forks
- 8
01 前言 Front Matter
- name
- seven-char-regulated-verse
- description
- Guidance on composing seven-character regulated verse (七言律诗). Use this skill whenever a task requires writing traditional Chinese poetry in the seven-character regulated style, ensuring adherence to structural, parallelism, and rhyming rules (using modern Mandarin pronunciation).
03 SKILL.md 正文
Seven-Character Regulated Verse (七言律诗)
A guide for composing traditional Chinese poetry in the seven-character regulated verse format.
Core Structure
- Length: Exactly 8 lines.
- Line Length: Exactly 7 characters per line.
- Couplets: The poem consists of 4 couplets:
- Shoulian (首联): Lines 1-2 (Head couplet) - Introduces the theme.
- Hanlian (颔联): Lines 3-4 (Jaw couplet) - Develops the theme; MUST be parallel (antithesis).
- Jinglian (颈联): Lines 5-6 (Neck couplet) - Transitions or deepens the theme; MUST be parallel (antithesis).
- Wei-lian (尾联): Lines 7-8 (Tail couplet) - Concludes the poem.
Rhyming (Modern Mandarin)
- Rhyme typically occurs at the end of even-numbered lines (2, 4, 6, 8).
- Line 1 may also rhyme (optional but common).
- Use modern Mandarin pronunciation for rhyming.
- All rhyming lines should share the same vowel sound (and often the same tone, usually level tone/平声).
Parallelism (Dui-zhang 对仗)
- Required for the middle two couplets (lines 3-4 and 5-6).
- Nouns should match nouns, verbs match verbs, adjectives match adjectives.
- Imagery should be balanced (e.g., "mountain" vs "river", "old" vs "new").
Tone Patterns (Ping-ze 平仄)
- Traditionally, regulated verse follows strict tonal patterns (Level/Ping and Oblique/Ze).
- While modern Mandarin tones (1, 2 = Level; 3, 4 = Oblique) can be used, prioritize the semantic flow and structural parallelism first unless strict classical adherence is requested.
Common Themes
- Nature, parting, history, war, and personal reflection.
- Use of classical imagery (e.g., autumn wind, lonely moon, frontier fortress).
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.