matlab-model-ams-systems
Model a Phase-Locked Loop (PLL) IC from its datasheet or system specs using Mixed-Signal Blockset. Without this skill, agents universally select the wrong solver and produce non-functional PLL models — 100% of unguided attempts fail. Covers Integer-N, Fractional-N, Dual Modulus architectures, loop filter design, lock time optimization, VCO phase noise configuration, and msbPllArchitectures/msbPllFoundation block assembly. Use when: PLL modeling, frequency synthesizer design, phase noise simulation, lock time analysis, charge pump design, loop filter tuning, datasheet-to-model, Mixed-Signal Blo
npx skills add matlab/matlab-agentic-toolkit --skill matlab-model-ams-systems --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill instructs an agent to model a Phase-Locked Loop (PLL) IC in Simulink using the Mixed-Signal Blockset foundation library (msbPllFoundation). It targets datasheet-driven or spec-driven designs, supporting architecture selection (Integer-N, Fractional-N, or Dual Modulus), loop filter design, lock-time optimization, and VCO phase-noise configuration. It emphasizes using the correct architecture templates, gathering parameters one at a time, and building a complete model with validation workflow (Phases 1-4 described; companion file covers later phases).
How it works
The workflow mandates gathering specifications one question at a time in a defined sequence, then selecting an assembly strategy. It prioritizes Strategy A (Architecture block) for standard templates and Strategy B for non-standard topologies. It provides steps to extract datasheet parameters (Phase 1), choose an assembly strategy (Phase 2), and tune an existing model if needed (Phase C). It includes prerequisites, parameter derivation rules, and a Phases 1-4 path with prompts to generate a design plan, then build and simulate using msbPllFoundation blocks, with explicit blocks like msbPllArchitectures templates and parameters such as N, Kvco, Fc, Phi, and loop filter components. It also specifies validation steps, export of plots, and mandatory existence checks for required functions and libraries (e.g., thirdOrderPassiveFilterDesign, estimatePLLPhaseNoise, phaseNoiseMeasure, phaseNoiseToJitter, and libraries). The agent is guided to use exact commands and MATLAB code snippets when performing tasks, and to present progress with ASCII diagrams and a design plan before building a model.
When to use it
- When modeling a PLL IC from its datasheet (extracting parameters, selecting architecture)
- When designing a frequency synthesizer from system specs (fVco, fRef, lock time, phase noise targets)
- When building a behavioral PLL model in Simulink using Mixed-Signal Blockset
- When validating phase noise performance against datasheet measurements
- When deciding among Integer-N, Fractional-N, or Dual Modulus architectures
What it can touch
- The skill references and requires access to blocks and functions from:
msbPllFoundation,msbPllMeasurements,msbPllArchitectures. - It expects to interact with MATLAB/Simulink workspace, and uses functions such as
extractFileText,open_system,set_param,sim,pllOpenLoopPlot,pllCloseLoopPlot, and MATLAB file operations as part of the workflow. It also requires checks forexist(func,'file')andexist(lib,'file')==4for library validation.
Caveats
- The workflow relies on existence of specified MATLAB functions and MSB libraries; absence leads to skipping dependent steps.
- It explicitly prohibits circuit-level (transistor) design; focuses on behavioral/MSB-level modeling.
- It prescribes progressive, single-question data gathering per response, and iterative design only if targets are not met; otherwise, it stops after a successful first attempt with sufficient margin.
# Skill: PLL Datasheet Modeling -- Core (Phases 1-4) Model a PLL IC from its datasheet or system specifications using Simulink building blocks from the Mixed-Signal Blockset (MSB) foundation library `msbPllFoundation`. **Companion file**: `modeling-pll-datasheet-validate.md` covers Phases 5-9 (loop filter design, validation, measurement, iteration, pitfalls). ## When to Use - Modeling a PLL IC from its datasheet (extracting parameters, selecting architecture) - Designing a frequency synthesizer from system specs (fVco, fRef, lock time, phase noise targets) - Building a behavioral PLL model in Simulink using Mixed-Signal Blockset - Validating phase noise performance against datasheet measurements - Selecting between Integer-N, Fractional-N, or Dual Modulus PLL architectures ## When NOT to Use - Circuit-level PLL design (transistor-level VCO, charge pump schematic) - PLL analysis without building a Simulink model (use `estimatePLLPhaseNoise` directly) - Clock distribution or jitter cleaning (not frequency synthesis) - Non-MSB PLL modeling (e.g., custom Simulink blocks without the Mixed-Signal Blockset) --- ## Workflow Directives (MANDATORY) 1. **Gather specs ONE AT A TIME (MANDATORY
- When to Use
- When NOT to Use
- Workflow Directives (MANDATORY)
- Prerequisites
- Entry Points
- A. Datasheet-Driven (Full workflow, Phases 1-4)
- B. Spec-Driven (No datasheet)
- C. Tune Existing Model (Meet a new spec)
- Availability Check (MANDATORY)
- Phase 1: Extract Datasheet Parameters
- 1.0 Reading the Datasheet PDF
- 1.1 Architecture Identification
- 1.2-1.4 Detailed Parameter Extraction
- Phase 2: Select Assembly Strategy
What does the matlab-model-ams-systems skill do?
Model a Phase-Locked Loop (PLL) IC from its datasheet or system specs using Mixed-Signal Blockset. Without this skill, agents universally select the wrong solver and produce non-functional PLL models — 100% of unguided attempts fail. Covers Integer-N, Fractional-N, Dual Modulus architectures, loop filter design, lock time optimization, VCO phase noise configuration, and msbPllArchitectures/msbPllFoundation block assembly. Use when: PLL modeling, frequency synthesizer design, phase noise simulation, lock time analysis, charge pump design, loop filter tuning, datasheet-to-model, Mixed-Signal Blo
How do I install it?
Run `npx skills add matlab/matlab-agentic-toolkit --skill matlab-model-ams-systems --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From matlab/matlab-agentic-toolkit, a repository with 868 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.