ReddRadar
Agent skill
lyric-writing
Write complete song lyrics with structural annotations and production notes optimized for AI music generation platforms like Suno and Udio
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/social-sciences-humanities/arts-culture/music-album-creation/skills/lyric-writing
SKILL.md
Lyric Writing
Write complete, emotionally resonant song lyrics with detailed structural annotations and embedded production notes for AI music generation.
Overview
This skill provides comprehensive lyric writing capabilities optimized for text-to-music AI platforms. It encompasses structural design, emotional mapping, hook development, and the embedding of production directions within the lyrics themselves.
Capabilities
Structural Composition
- Write complete verse-chorus-bridge structures
- Design pre-choruses and post-choruses
- Create intros, outros, and instrumental breaks
- Develop song sections with appropriate line counts
- Balance repetition and variation
Production Annotations
- Embed delivery directions:
[whispered],[spoken word],[belt] - Include dynamics:
[building],[soft],[crescendo],[fade] - Add vocal techniques:
[falsetto],[raspy],[breathy] - Note harmonies and layers:
[harmony],[double-tracked] - Mark ad-lib sections:
[ad-lib],[improvise]
Emotional Mapping
- Design emotional arcs within songs
- Create tension and release patterns
- Build to climactic moments
- Craft vulnerable, intimate sections
- Balance intensity throughout
Hook Development
- Create memorable chorus hooks
- Design catchy phrase patterns
- Develop callback lines and motifs
- Craft earworm melodies through syllabics
Voice Consistency
- Maintain artist persona throughout
- Match lyrical style to genre
- Keep thematic coherence
- Preserve character voice
Usage Guidelines
Annotation Standards
[Verse 1]
Opening lines that set the scene
[building] Lines that increase in intensity
[whispered] Intimate, soft delivery here
[Pre-Chorus]
[spoken word] Transition moment
Building tension toward chorus
[Chorus]
[belt] Main hook with power
Memorable, repeatable lines
[harmony] Layered vocal moment
[Bridge]
[falsetto] Vulnerable high notes
[raw] Emotionally exposed delivery
[Outro]
[fade] Final fading lines...
Quality Checklist
- Clear structural markers for all sections
- Production notes embedded where needed
- Emotional arc mapped and intentional
- Hooks are memorable and repeatable
- Voice matches artist persona
- Syllable counts support melodic flow
- Rhyme scheme is intentional (tight or loose)
Integration Points
Related Skills
- SK-MAC-002 (style-specification) - Musical context for lyrics
- SK-MAC-004 (persona-development) - Voice and character
- SK-MAC-005 (album-conceptualization) - Thematic alignment
Related Agents
- AG-MAC-001 (lyricist-agent) - Primary executor
- AG-MAC-005 (album-curator-agent) - Thematic guidance
Output Format
# [Song Title]
**Artist**: [Artist Name]
**Album**: [Album Name]
**Track**: [Number]
## Lyrics
[Intro]
...
[Verse 1]
...
[Chorus]
...
---
## Production Notes
- Key emotional moments: ...
- Dynamic range: ...
- Special directions: ...
References
- Song structure theory and common forms
- AI music platform annotation best practices
- Emotional songwriting techniques
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?