An engineer uses a netlist script with Claude Code to settle facts about KiCad boards (nets, pin maps, DNP parts), but on every board the method around it had to be rediscovered: unzip into scratch, run --check-pcb before trusting a net, read DNP flags, tag each claim with its source. Getting that wrong has cost real corrections: one review presented PDF-text readings as netlist facts, and a pin-transform bug went unnoticed until a later pass checked the netlist against the PCB. His fix is to write the procedure into an agent skill so the next review starts from it rather than from memory, tagging every fact netlist, PCB, datasheet or PDF text.
Missing capability reported against firstcontact (wongvin)
What engineers report
A missing capability reported against firstcontact (wongvin): cannot do a step the workflow needs, so people fill the gap by hand.
Recorded mode: agent / failure
Analyst note
From the Grok pain-radar digests, Nov 13-14 2026 (Nov 13 10:41 AM ET through Nov 14 7:41 AM ET digests plus the Haitch editions). Verified live 2026-11-14: issue/PR read; title and state confirmed.
What it costs a team
Modeled annual cost
$30,000
For a team of 5
Prototype delay
3 days
Modeled schedule slip per occurrence
Time lost
240 min
Per engineer per month, about 1 incidents
How the cost is modeled
240 min/month × 5 engineers × 12 months = 240 hours × $125/hour = $30,000
A modeled estimate with medium confidence. Swap in your own team size and loaded rate to size it for your team.
Engineering tools that address it
No engineering tool profile lists this error yet. Browse tools that connect to firstcontact (wongvin).
Evidence
More recurring errors in firstcontact (wongvin)
- Follow-on to #386 from last hour. His KiCad netlist skills settle circuit facts from design source, but boards designed in Altium have no equivalent: the only fallback is the schematic PDF, which produced plausible, wrong answers on the XIAO boards more than once. He tested KiCad 10's Altium importer on a 4-sheet nRF52840 keyboard: 620 pads across 151 nets, 0 split, 0 merged, then five problems. A missing library leaves the imported sheets unsaved, only the schematic gets saved with no .kicad_pcb, Value holds the library part name while the real resistance lands in ALTIUM_VALUE, variants come through per instance so his script reports 0 not-fitted parts, and the importer marked CON303 not fitted when Altium's variation actually points at CON302 by unique ID, a false DNP. kicad-cli cannot import a .SchDoc at all, so the skill has to walk a person through the GUI.Electronics & PCB · impact 74
- Before a firmware port can rely on a board's hardware facts, its netlist script has to learn hierarchical sheets, power symbol names (it reports #PWRnn instead of VSYS_3V3) and multi-unit symbols, which an earlier run attached to the wrong pins. Until then the XIAO header pin map comes from PDF text plus pinctrl.Embedded & firmware · impact 66
Sourced from public community reports. Costs and delays are modeled estimates, not measurements. Know a better source or a fix? Tell us at hello@productflo.io.