characterization

characterization is a skill for Claude Code from hdl-tools/analog-chip-design-agents. It costs 79 tokens per session (2,556 once invoked), scanned A, original, MIT.

A workflow for measuring the timing, power use, and noise of a completed analog or mixed-signal circuit across process, voltage, and temperature conditions. It produces Liberty files and behavioral models for other chip-design tools.

In plain words
What is it for?
Use it to characterize a signed-off circuit block, generate integration models, and repeat the measurements after setup or design fixes.
Why use it?
It creates the summarized models that larger chip projects need, while checking that the circuit meets its requirements under different operating conditions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the analog-design-characterization plugin — 1 skill, 1 agent shipped together

Good fit Use it to characterize a signed-off circuit block, generate integration models, and repeat the measurements after setup or design fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hdl-tools/analog-chip-design-agents/characterization
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hdl-tools/analog-chip-design-agents --skill characterization
Clone the repo
git clone --depth 1 https://github.com/hdl-tools/analog-chip-design-agents

Made for: Claude Code.

Or install analog-design-characterization, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for characterization

README.md
[![agentmods](https://agentmods.dev/badge/skills/hdl-tools/analog-chip-design-agents/characterization.svg)](https://agentmods.dev/skills/hdl-tools/analog-chip-design-agents/characterization)
Your own site
<a href="https://agentmods.dev/skills/hdl-tools/analog-chip-design-agents/characterization"><img src="https://agentmods.dev/badge/skills/hdl-tools/analog-chip-design-agents/characterization.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.02556
Opus 5 $0.00039 $0.01278
Sonnet 5 $0.00016 $0.00511
Haiku 4.5 $0.00008 $0.00256

Measured 8d ago against content hash 19468048244f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

characterization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/characterization/skills/characterization/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Characterization

Invocation

  • If invoked by a user presenting a characterization task: immediately spawn the analog-chip-design-agents:characterization-orchestrator agent and pass the full user request and any available context. Do not execute stages directly.
  • If invoked by the characterization-orchestrator mid-flow (including re-validation): do not spawn a new agent. Treat this file as read-only — return the requested stage rules, sign-off criteria, or loop-back guidance.

Spawning the orchestrator from within an active orchestrator run causes recursive delegation and must never happen.

Pre-run Context

Before executing or advising on any stage, read the following if they exist:

  1. memory/characterization/knowledge.md — known .lib generation patterns, sweep/corner recipes, monotonicity fixes, and PDK/tool quirks. Incorporate its guidance into every stage.
  2. memory/characterization/run_state.md — current run identity for resume-after-interruption.

Purpose

Produce the validated abstract views of a signed-off, extracted analog/mixed macro: timing, power, and noise characterized across the required PVT corners, written as Liberty (.lib) plus behavioral models, and validated against SPICE. Seven stages with explicit QoR gates. Characterization is a terminal consumer — its loop-backs are stage-local retries (model_validation → char_setup); it does not open cross-domain fix_requests. A characterization that cannot converge on a valid model after the retry cap escalates to the user.


Supported EDA Tools

Open-Source

  • ngspice / Xyce (ngspice / xyce) — sweep harnesses driving the characterization grid
  • Python .lib writers — emit NLDM/CCS-style Liberty tables from the sweep results
  • scipy / numpy — monotonicity checks, interpolation, model fitting

Proprietary (detect-only — never installed)

  • Cadence Liberate (liberate) — characterization + .lib generation
  • Synopsys SiliconSmart (siliconsmart)
  • Siemens Solido ML Characterization (solido)
  • Altos (legacy)

Read the full file on GitHub · 270 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 270 lines · 79 tokens per session scan A 19468048244f

Subscribe to this mod's changes

characterization is a skill published in the GitHub repository hdl-tools/analog-chip-design-agents (22 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 2,556 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

neuroskill-bci

Use live BCI cognitive and mood state from NeuroSkill.

NousResearch/hermes-agent · 18 tokens

ruview-advanced-sensing

Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection…

ruvnet/RuView · 84 tokens

ruview-applications

Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…

ruvnet/RuView · 79 tokens

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

opentrons-integration

Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…

K-Dense-AI/scientific-agent-skills · 79 tokens

pylabrobot

Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.

K-Dense-AI/scientific-agent-skills · 49 tokens