modular-synthesis-philosophy
Skill17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub
Apply modular synthesis principles to system design, workflow architecture, and conceptual frameworks. Use when designing modular systems, creating architecture diagrams using synthesis metaphors, applying signal flow thinking to data pipelines, or translating between audio engineering and software concepts. Triggers on modular architecture design, signal flow diagrams, synthesis-inspired system thinking, or "oscillator/patch" metaphors.
1 other project uses a version of this.
Other versions1 project uses a version of this.
Word for word · 1
- organvm-iv-taxis/a-i--skills★ 17100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository170 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- algorithmic-artSkill
- audio-engineering-patternsSkill
- canvas-designSkill
- creative-writing-craftSkill
- generative-art-algorithmsSkill
- generative-art-deploymentSkill
- generative-music-composerSkill
- interactive-theatre-designerSkill
- movement-notation-systemsSkill
- narratological-algorithmsSkill
- natural-center-extractionSkill
- react-three-fiber-patternsSkill
- reality-tv-narrative-analyzerSkill
- script-analysis-dramaturgicalSkill
- theme-factorySkill
- three-js-interactive-builderSkill
- corpus-persona-extractionSkill
- data-ingestion-pipelineSkill
- data-pipeline-architectSkill
- data-storytelling-analystSkill
- market-gap-analysisSkill
- ml-experiment-trackerSkill
- prompt-atom-formalizationSkill
- sql-query-optimizerSkill
- systemic-product-analystSkill
- time-series-analystSkill
- accessibility-patternsSkill
- agent-testing-patternsSkill
- api-design-patternsSkill
- artifacts-builderSkill
- backend-implementation-patternsSkill
- browser-extension-patternsSkill
- cli-tool-designSkill
- code-refactoring-patternsSkill
- code-review-checklistSkill
- coding-standards-enforcerSkill
- community-platform-patternsSkill
- configuration-managementSkill
- continuous-learning-agentSkill
- data-backup-patternsSkill
- database-migration-patternsSkill
- deployment-cicdSkill
- docker-containerizationSkill
- dotfile-systems-architectSkill
- error-handling-logging-patternsSkill
- fastapi-patternsSkill
- feature-workflow-orchestratorSkill
- frontend-design-systemsSkill
- fullstack-starter-packSkill
- gcp-resource-optimizerSkill
- htmx-interaction-patternsSkill
- iterative-code-explorationSkill
- json-schema-designSkill
- mcp-builderSkill
- mcp-server-orchestratorSkill
- mobile-platform-architectSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 146
Document: If it works, it's a technique
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Modular Synthesis Philosophy
Translate the wisdom of modular synthesis into system design and conceptual frameworks.
Core Principles
Everything is a Module
In modular synthesis, every function is a discrete, replaceable unit with defined inputs and outputs. Apply this to:
- Software: Microservices, functions, components
- Workflows: Tasks, stages, handoffs
- Organizations: Teams, roles, interfaces
- Knowledge: Concepts, connections, domains
Patch Points are Everything
The power isn't in the modules—it's in how they connect. A simple oscillator becomes complex through routing.
System design equivalent: APIs, interfaces, data contracts, message passing.
CV is Control, Audio is Signal
Modular synthesis distinguishes between:
- Control Voltage (CV): Tells modules how to behave
- Audio: The actual signal being processed
System equivalent:
- CV = Configuration, parameters, metadata
- Audio = Data, content, payload
No Signal Path is Wrong
Synthesis philosophy: there are no mistakes, only unexpected results. Patching a clock into an audio input creates something.
Design equivalent: Embrace emergence. Systems can be recombined in ways designers didn't anticipate.
Module Types (Translated)
Oscillators → Signal Generators
| Synthesis | System Equivalent |
| VCO (voltage-controlled oscillator) | Data source, API endpoint, sensor |
| LFO (low-frequency oscillator) | Scheduler, cron job, heartbeat |
| Noise source | Random generator, entropy source |
| Sample & Hold | Cache, state capture, snapshot |
Filters → Signal Processors
| Synthesis | System Equivalent |
| VCF (voltage-controlled filter) | Data transformer, query filter |
| Lowpass filter | Noise reduction, smoothing, aggregation |
| Highpass filter | Change detection, delta extraction |
| Bandpass filter | Specific extraction, search query |
Modulation → Control Systems
| Synthesis | System Equivalent |
| Envelope (ADSR) | Lifecycle management (init, active, decay, cleanup) |
| Sequencer | Workflow orchestrator, state machine |
| Quantizer | Validator, normalizer, type coercer |
| Slew limiter | Rate limiter, gradual rollout |
Utilities → Infrastructure
| Synthesis | System Equivalent |
| Mixer | Aggregator, combiner, merge function |
| VCA (voltage-controlled amplifier) | Gain control, feature flag, throttle |
| Multiple/Splitter | Fan-out, broadcast, pub/sub |
| Switch | Router, conditional, A/B test |
| Attenuator | Scaler, normalizer, reducer |
Patching Patterns
Series (Linear Pipeline)
[Source] → [Process A] → [Process B] → [Output]Simple, predictable, easy to debug. Each stage transforms and passes on.
When to use: ETL pipelines, request processing, assembly lines.
Parallel (Split & Merge)
┌→ [Process A] →┐
[Source] [Mixer] → [Output]
└→ [Process B] →┘Process the same signal differently, combine results.
When to use: A/B testing, redundancy, multi-format output.
Feedback Loop
[Source] → [Process] → [Output]
↑____________|Output feeds back into input. Creates complexity, can create instability.
When to use: Iteration, learning systems, self-regulation. Warning: Needs attenuation or the system oscillates out of control.
Cross-Modulation
[Osc A] ←→ [Osc B]
↓ ↓
[Mix] → [Output]Two modules modulate each other. Creates complex, evolving behavior.
When to use: Emergent systems, creative AI, market dynamics.
Anti-Consensus Methodology
Standard approach: Follow established patterns, use popular frameworks, minimize surprise.
Synthesis approach: Experiment with unconventional signal paths. The "wrong" patch might create something novel.
Application
- Identify the consensus in your domain
- Ask: What if we routed this differently?
- Patch experimentally: Try connections that "shouldn't" work
- Evaluate: Does the unexpected result have value?
- Document: If it works, it's a technique
Examples
- AI Agents as Oscillators: Multiple AI instances generating continuous output, mixed and filtered before reaching user
- Feedback in Writing: Output feeds into prompt, iteratively refining
- Cross-domain Patching: Using music theory for visual composition, or rhetoric for code architecture
Designing with Synthesis Metaphors
Step 1: Identify Your Voices
What are the signal generators in your system?
- Data sources, user inputs, scheduled events, external APIs
Step 2: Map Your Processing
What transforms signals?
- Business logic, validation, enrichment, formatting
Step 3: Define Your Modulation
What controls behavior?
- Configuration, user preferences, system state, time
Step 4: Establish Your Routing
How do signals flow?
- Direct connections, message queues, event buses, shared state
Step 5: Set Your Mix
How do multiple signals combine?
- Priority, averaging, voting, concatenation
Diagram Conventions
┌─────────────┐
│ MODULE │
│ │
│ ○ CV In │ ○ = Input
│ ● Audio In │ ● = Output (filled)
│ ● Out │
└─────────────┘
Patch cables: ──────── (audio)
········ (CV/control)References
references/module-mappings.md- Extended module-to-system translationsreferences/patch-diagrams.md- Example system diagrams in synthesis style
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

