Menu
Full creative synthesis — combine song, visual concept, and TED talk from a single technical insight
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/live-neon/skills --skill side-questsThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Same skill compression power in half the context — 975 tokens vs 2,500.
Skill compression reminder in 100 tokens — just trigger, action, result.
Complete skill compression documentation — all options, modes, and calibration details (~2,500 tokens).
Based on SOC occupation classification
Showing SKILL.md
| name | side-quests |
| version | 1.0.2 |
| description | Full creative synthesis — combine song, visual concept, and TED talk from a single technical insight |
| author | Live Neon <hello@liveneon.ai> |
| homepage | https://github.com/live-neon/skills/tree/main/creative/side-quests |
| repository | leegitw/side-quests |
| license | MIT |
| tags | ["creative","synthesis","songwriting","storytelling","ted-talk","visual-guide","reflection","knowledge-transfer","suno","learning"] |
| layer | creative |
| status | active |
| alias | sq |
| user-invocable | true |
| emoji | 🎭 |
Full creative synthesis that combines all three creative artifacts from a single technical insight: a Suno-ready song, a visual concept guide, and a full TED talk.
Trigger: 明示呼出 (explicit invocation) or when deep technical insight emerges
Core insight: "Context without action is paralysis. Action without context is chaos. Side quests are context made actionable through creative synthesis."
openclaw install leegitw/side-quests
Dependencies: None required, but works with component skills:
leegitw/insight-song — Song component (can be used standalone)leegitw/visual-concept — Visual guide component (can be used standalone)leegitw/ted-talk — TED talk component (can be used standalone)Data handling: This skill synthesizes content from user-supplied input or the current conversation context (default). It does NOT read files from the workspace or access project artifacts directly. Results are returned to the invoking agent, who decides how to use them.
Technical insights fade with context compression. Multi-format creative synthesis provides reinforcement through multiple channels:
The insight: Creation forces synthesis. Making creative artifacts about a concept reveals gaps that passive understanding cannot. Audio + visual + narrative = deeper learning.
/sq [topic]
Or use individual components:
/song [topic] # Just the song
/vc [topic] # Just the visual concept
/ted [topic] # Just the TED talk
| Argument | Required | Description |
|---|---|---|
| topic | No | Topic focus (default: synthesize current conversation) |
Before creating a side quest, ensure:
You must be able to answer:
| Question | What It Means |
|---|---|
| Core insight? | Not "we talked about X" but "we discovered X solves Y" |
| Problem solved? | The pain point, not just the topic |
| Why, not just what? | The reasoning, not just the outcome |
| Substantial depth? | Teaches something new, not standard practice |
Each side quest produces a single markdown file with three sections:
## Song
**Title**: [Song Name]
**Suno.ai Style Tags**:
[300-500 characters describing musical style]
[Verse 1]
[Lyrics]
[Chorus]
[Lyrics]
[...]
Song Rules:
## Visual Concept Guide
**Core Visual Concept**: [Primary metaphor]
### Visual Themes & Imagery
[3-7 major themes]
### Symbolic Visual Elements
[Technical concepts as visual symbols]
### Emotional Color Arc
[Color palette evolution]
### Motion & Rhythm
[Movement patterns]
### Key Visual Contrasts
[Before/after, chaos/order]
Visual Guide Rules:
## TED Talk: "[Talk Title]"
### Opening (0:00-2:00)
[Hook with relatable problem]
### Setup: Why This Matters (2:00-6:00)
[Why this matters, stakes]
### The Problem (6:00-12:00)
[Deep dive into the pain point]
### Core Concept (12:00-25:00)
[Explain thoroughly]
### Real-World Examples (25:00-38:00)
[Concrete, specific details from context provided]
### Broader Implications (38:00-45:00)
[Connect to broader context]
### Closing (45:00-48:00)
[Call to action]
### Q&A Preparation (48:00-50:00)
[Address objections]
TED Talk Rules:
| Element | Question |
|---|---|
| Problem | What was broken/painful? |
| Discovery | What did we learn? |
| Solution | What pattern emerged? |
| Impact | Why does this matter? |
The skill generates each component sequentially:
Return the complete artifact (song + visual concept + TED talk) to the invoking agent.
Context: Discovered reproduce-to-debug problem. Introduced Bootstrap → Learn → Enforce phases.
Narrative arc:
Song excerpt:
[Verse 1]
Three in the morning, the logs are all silent
System's on fire but the metrics don't know
Building in darkness, no baseline to measure
Can't debug what you've never seen before
Visual concept:
TED talk opening:
"It's 3 AM. Your pager goes off. The system is on fire — users are complaining, something is clearly wrong. You pull up your logs and... nothing."
Use individual components when you only need one format:
| Skill | Alias | Output |
|---|---|---|
| insight-song | /song | Suno-ready song |
| visual-concept | /vc | Visual concept guide |
| ted-talk | /ted | Full TED talk |
| Condition | Behavior |
|---|---|
| Insufficient context | Ask clarifying questions first |
| No clear narrative arc | Decline, explain what's missing |
| Surface-level topic | Suggest deeper exploration first |
| Main work not documented | Prompt to save progress first |
Orchestration Note:
This skill implements combined logic directly. It does NOT spawn or invoke other installed
skills (insight-song, visual-concept, ted-talk). The component skill instructions
are embedded inline within this skill.
Input sources:
What this skill does NOT do:
Output behavior: This skill returns the combined artifact (song + visual concept + TED talk) directly to the invoking agent. The agent can then display, save, or pass the result to another skill as needed.
Note on TED talks: TED talks use concrete details from the context you provide. Review before sharing externally to ensure no sensitive information is included.
Provenance note:
This skill is developed by Live Neon (https://github.com/live-neon/skills) and published
to ClawHub under the leegitw account. Both refer to the same maintainer.
/sq generates all three artifact types/song, /vc, /ted"The detours became destinations. The questions we didn't expect to ask. The patterns we found by paying attention to what emerged."
Part of the Live Neon Creative Suite.