Borrowing it
Nothing to install: this file belongs to drandyhaas/KiCadRoutingTools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/drandyhaas/KiCadRoutingTools/main/.claude/skills/recommend-stackup/SKILL.mdgit clone --depth 1 https://github.com/drandyhaas/KiCadRoutingToolsWrote 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.
[](https://agentmods.dev/skills/drandyhaas/kicadroutingtools/recommend-stackup)<a href="https://agentmods.dev/skills/drandyhaas/kicadroutingtools/recommend-stackup"><img src="https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/recommend-stackup/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.
<a href="https://agentmods.dev/skills/drandyhaas/kicadroutingtools/recommend-stackup"><img src="https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/recommend-stackup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01178 |
| Opus 5.5 | $0.00028 | $0.00471 |
| Sonnet 5.5 | $0.00014 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
recommend-stackup 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommend Stackup
When this skill is invoked with a KiCad PCB file, review the stackup and recommend one suited to the board's impedance and plane requirements. The router's --impedance widths and --time-matching delays are computed from the stackup — a default stackup silently skews both.
Step 1: Read the Current Stackup
import sys
sys.path.insert(0, "py_router")
from kicad_parser import parse_kicad_pcb
pcb = parse_kicad_pcb('path/to/file.kicad_pcb')
for layer in pcb.board_info.stackup: # List[StackupLayer], ordered top to bottom
print(layer.name, layer.layer_type, layer.thickness, layer.epsilon_r)
Judge whether it looks deliberate or default:
- No stackup section at all, or all dielectric layers with identical thickness and ε_r ≈ 4.5, suggests KiCad's untouched default.
- Real fab stackups have distinct core/prepreg thicknesses (e.g. JLCPCB 4-layer: ~0.21mm prepreg, ~1.0mm core).
Report the verdict explicitly: "stackup appears to be KiCad's default — impedance calculations will not match your fab" vs. "stackup looks deliberate."
Step 2: Gather Requirements
- Layer count and roles: copper layers from the board; which should be planes (GND/power) vs signal.
- Impedance targets: from
/identify-diff-pairsand/find-high-speed-netsresults if available; otherwise infer from net names (USB 90Ω, LVDS/Ethernet/HDMI 100Ω, PCIe 85Ω, 50Ω single-ended for RF/clocks). - The fab: ask the user. If they name one (JLCPCB, PCBWay, OSH Park, Eurocircuits…), WebSearch its standard multilayer stackup and impedance-control offerings rather than inventing thicknesses.
Step 3: Recommend and Validate
Propose: layer assignment (e.g. 4-layer: F.Cu signal / In1.Cu GND plane / In2.Cu power-or-routable / B.Cu signal), dielectric thicknesses and ε_r per the fab's standard stackup, and copper weights. For impedance, what matters is the solid GND reference ADJACENT to each impedance-carrying layer — the other inner layer need not be a solid plane (on dense/BGA boards /recommend-plane-mappings will usually keep it split or routable; making BOTH inners solid planes is a minority human practice and starves dense boards of routing layers).
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.
- 5d ago Changed · +11 lines 7fb360116afd
- 18d ago Changed · +4 lines 18a10d2ea4db
- 2mo ago First seen · 58 lines · 71 tokens per session scan A e55ffbebfc32
recommend-stackup is a skill published in the GitHub repository drandyhaas/KiCadRoutingTools (706 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,178 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
tao-train-visual-changenet
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NOPASS classification, or producing change-segmentation masks. Trigger phrases include…
cad-skills
Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 21 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, Blender, KiCad, SolveSpace, QCAD, xBIM, Clipper2, TongWen and more.
altium-library
Create and verify Altium schematic symbols (.SchLib) and PCB footprints (.PcbLib) from datasheets and 2D drawings, as code. Use whenever a part library must be made, fixed, measured from a drawing, or checked. Triggers: "make a footprint", "create a symbol", "add this part to the library", "SchLib", "PcbLib"…
universal-netlist
Query EDA netlists from the shell with the universal-netlist command line: Cadence OrCAD .DSN, Altium .PrjPcb, KiCad .kicadpro and Universal Netlist .netlist.json. Finds designs, searches nets and components, traces connectivity across passives (XNETs), and runs electrical rule checks. Use when reviewing a schematic…
pcb-design
Design, modify, review, validate, or export a KiCad schematic or PCB from natural-language hardware requirements. Use for circuit design, component selection, schematic capture, footprint assignment, board layout, routing, ERC/DRC, BOM, Gerbers, and manufacturing handoff through the KiCad MCP tools.
kicad-copilot-mcp
Use when KiCad Copilot MCP tools are available. Entry point for KiCad schematic and PCB workflows.