Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Signal Integrity Review

ASecurity

RAG-backed. Review DipTrace PCB impedance, stackup, routed geometry, return paths, and configured external-solver evidence without inventing targets. Use when the user says “Review impedance and return-path evidence for these PCB nets.”

23 stars
0 votes
0 copies
1 views
Added 9/19/2026
researchgitapi

Works with

cliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add fireostendere/mcp_diptrace --skill signal-integrity-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Signal Integrity Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Signal Integrity Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fireostendere-signal-integrity-review/badge)](https://www.skillsdirectory.com/skills/fireostendere-signal-integrity-review)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: signal-integrity-review
description: RAG-backed. Review DipTrace PCB impedance, stackup, routed geometry, return paths, and configured external-solver evidence without inventing targets. Use when the user says “Review impedance and return-path evidence for these PCB nets.”
---

Read [runtime access](../shared/runtime.md) before choosing between explicit-path
MCP, a live bridge session, and native/headless CLI. Their availability is separate.

# Signal-integrity review

RAG: **engineering memory by default** — [shared workflow](../shared/rag.md).
Use the indexed transmission-line, grounding and EMC material to justify the model,
assumptions and return-path checklist; solver output does not replace that basis.

Keep analytical equations, geometry heuristics, and external solver output in separate evidence
classes. No result is fabrication sign-off.
Use public `tools/list` for exact callable names and `get_capabilities` for document/configured
feature and adapter availability.

## Scope selection

- `microstrip`: supported single-ended analytical model for an outer-layer trace.
- `differential_microstrip`: supported coupled analytical model with explicit gap.
- `symmetric_stripline`: supported single-ended analytical estimate within its published range.
- Differential stripline: unavailable; return `blocked_by_capability`.
- `run_openems_stripline_analysis`: a registered typed external adapter, not a bundled solver.
- `run_ngspice_simulation`: a registered batch adapter for a caller-supplied netlist, not a PCB
  geometry extractor.

## Workflow

1. Call `diptrace_status`, `get_capabilities`, and `get_document_info`; freeze the PCB SHA-256.
2. Read `get_stackup` and `get_route_details`. Require explicit net, layer, dielectric
   height/permittivity, copper width/thickness, reference conductor, and target/tolerance when a
   pass/fail judgment is requested.
3. Use `calculate_impedance` for standalone inputs,
   `analyze_stackup_for_impedance` for complete outer-layer microstrip stackups, and
   `validate_impedance_constraints` or `analyze_controlled_impedance` for named routed nets.
4. Use `analyze_return_path` only as a caller-radius geometry heuristic. Disclose boundary-only
   pour geometry, layer-transition ambiguity, and confidence limits. If native refill evidence
   is needed, use the PCB headless profile on a copy and retain its exported geometry and verdict;
   do not call all native work unavailable based on the MCP tool list. Even refilled geometry
   does not turn this heuristic into a field solution.
5. Invoke ngspice/openEMS only when runtime discovery says the configured adapter is available.
   For openEMS retain request SHA-256, solver version, convergence, result SHA-256, and resources.
   For ngspice retain the netlist SHA-256, job status, return code/log summary, and resources; its
   current API exposes no executable version, convergence field, or result SHA-256, so record those
   fields as unavailable instead of inventing them.
6. Emit [`../shared/result.schema.json`](../shared/result.schema.json). Put impedance, effective
   permittivity, length/skew, frequency, and return-path coverage values in `measurements`, each
   with a unit, evidence class, and evidence IDs; do not hide numeric evidence in prose.

## Published and implementation boundaries

- Coupled microstrip validity requires `0.1 <= width/height <= 10` and
  `gap/height >= 0.01`; outside it, report unavailable/low-confidence metadata rather than forcing
  the permittivity-order invariant.
- Single-ended microstrip effective-permittivity validity uses
  `0.01 <= width/height <= 100`.
- Symmetric stripline uses `width/free_height < 0.35` and
  `thickness/free_height < 0.25`.
- Finite copper thickness is not corrected in the coupled branch. Do not use its wide-gap
  decoupling asymptote as a thickness validation.
- Every distance is millimetres; impedance is ohms.

These bounds and citations are returned by
[`impedance.py`](https://github.com/fireostendere/mcp_diptrace/blob/20e4bc107e3810945f729d3c81d0a379d9af8012/src/diptrace_mcp/impedance.py).
Adapter behavior is implemented in
[`external_adapters.py`](https://github.com/fireostendere/mcp_diptrace/blob/20e4bc107e3810945f729d3c81d0a379d9af8012/src/diptrace_mcp/external_adapters.py)
and mapped truthfully in
[`../capability-map.json`](../capability-map.json).

Use `analytical`, `heuristic`, and `external_solver` exactly as appropriate; never collapse them
into one confidence label.

Attribution

fireostenderefireostendere
View sourceMore from fireostendere →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

486982 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

805541 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

486981 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →