agentmods.dev

iccap-extraction

iccap-extraction is a skill for Claude Code, Codex from Solitario119/iccap-mcp-server. It costs 0 tokens per session (352 once invoked), scanned A, original, MIT.

A collection of instructions for extracting compact-model parameters in IC-CAP, an engineering tool used to fit semiconductor device models to measurements.

In plain words
What is it for?
Use it to fit diode, Gummel-Poon BJT, or ASM-HEMT GaN models to measured device data and check whether the resulting fit is physically reasonable.
Why use it?
It organizes the extraction process around prerequisites, starting estimates, physical limits, simulation, optimization, and validation. It does not provide ready-made parameter values.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo 1mo ago A scan 0 tokens original MIT

Good fit Use it to fit diode, Gummel-Poon BJT, or ASM-HEMT GaN models to measured device data and check whether the resulting fit is physically reasonable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/solitario119/iccap-mcp-server/iccap-extraction
View source ↗ Solitario119/iccap-mcp-server
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 Solitario119/iccap-mcp-server --skill iccap-extraction
Clone the repo
git clone --depth 1 https://github.com/Solitario119/iccap-mcp-server

Made for: Claude Code, Codex.

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 iccap-extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/solitario119/iccap-mcp-server/iccap-extraction/github.svg)](https://agentmods.dev/skills/solitario119/iccap-mcp-server/iccap-extraction)
Your own site
<a href="https://agentmods.dev/skills/solitario119/iccap-mcp-server/iccap-extraction"><img src="https://agentmods.dev/badge/skills/solitario119/iccap-mcp-server/iccap-extraction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for iccap-extraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/solitario119/iccap-mcp-server/iccap-extraction"><img src="https://agentmods.dev/badge/skills/solitario119/iccap-mcp-server/iccap-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 352 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 $0.00000 $0.00352
Opus 5.5 $0.00000 $0.00141
Sonnet 5.5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 2mo ago against content hash d2259e8a8426, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iccap-extraction 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 2mo 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.

src/mcp_iccap_server/skills/iccap-extraction/SKILL.md · 45 lines

What it actually says

IC-CAP Parameter Extraction Skills

Use this resource group to plan, execute, evaluate, and refine compact-model parameter extraction in IC-CAP.

Skill index

Reusable extraction operations

Extraction-strategy skills

The strategy files encode triggers, prerequisites, parameter dependencies, phase order, physical constraints, validation criteria, and corrective actions for a model family. They do not store expert-extracted final parameter values. Initial values must be estimated from the target device measurements or chosen from justified physical ranges.

Adapt parameter names and available mechanisms to the installed compact-model version and the measurement set.

Extraction loop

  1. Identify the model family, characterization domain, and available data.
  2. Check project and data prerequisites.
  3. Select the smallest parameter group identified by the current domain.
  4. Estimate starting values from the target measurements.
  5. Apply physically meaningful bounds.
  6. Simulate and inspect the initial state.
  7. Optimize the active group through IC-CAP.
  8. Evaluate numerical error, curve shape, and physical plausibility.
  9. Apply a targeted corrective action when the phase is not acceptable.
  10. Recheck earlier domains before moving to the next phase.

Parameter extraction is not a single optimizer call. Project construction, data preparation, phase order, parameter coupling, physical constraints, and cross-domain evaluation all affect the accepted result.

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 45 lines · 0 tokens per session scan A d2259e8a8426

Subscribe to this mod's changes

iccap-extraction is a skill published in the GitHub repository Solitario119/iccap-mcp-server (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 352 tokens. 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 2026-08-31.

Hardware and IoTScientific
Related

iccap-extraction compared with skills from other repositories

iccap-extraction next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
iccap-extractionSolitario119/iccap-mcp-serverSkill51mo agoMITA0Claude Code, Codex
neuroskill-bciNousResearch/hermes-agentSkill261kyesterdayMITA18Claude Code, Codex
ruview-applicationsruvnet/RuViewSkill103kyesterdayMITA79Claude Code
lab-hardware-cadK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA108Claude Code
pylabrobotK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA49Claude Code
pybammK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA70Claude Code, Codex
calibrate-roomruvnet/RuViewSkill103kyesterdayMITA41Claude Code