by adom
Agent skill for auditing any KiCad board before fab: real ERC/DRC, pad-level netlist extraction from the .kicad_pcb, and a checklist for the bugs ERC can't see — floating mandatory pins, supply pins on GND, wrong straps, wrong-variant feedback dividers, missing pull-ups, impedance class misassignment — verified against datasheets and reported by severity.
← Commit history
README.md+4−4@@ -1,16 +1,16 @@ # KiCad Board Audit An agent skill that turns "review this board for errors" into a repeatable,-verified audit of any KiCad project — schematic and layout — before you spend+verified audit of any KiCad project, schematic and layout, before you spend money on fabrication. ## What it does -1. **Runs the real checkers** — `kicad-cli` ERC + DRC (locally or through the+1. **Runs the real checkers**: `kicad-cli` ERC + DRC (locally or through the Adom desktop KiCad bridge), and reads the project's silenced-rule config so a "clean" pass can't hide muted checks. 2. **Extracts the pad-level netlist** from the `.kicad_pcb` (the synced ground- truth) with the bundled `assets/kicad_netlist.py` — components, per-net pin+ truth) with the bundled `assets/kicad_netlist.py`: components, per-net pin lists, unconnected pads, routed lengths, via counts. Handles KiCad 7–10 format differences. 3. **Walks an electrical checklist** for the bugs ERC is structurally blind to:@@ -22,7 +22,7 @@ money on fabrication. conflicts, keepout allow-flags, stale zones, unrouted items. 5. **Verifies every suspicion against a primary source** (datasheet, vendor hardware-design checklist, EVB schematic) before reporting it, then delivers- a severity-ranked report — Critical / High / Medium / Low — each finding+ a severity-ranked report (Critical / High / Medium / Low), each finding with refs, pins, evidence, and a concrete fix, plus a verified-correct section so good design doesn't get re-flagged next review.
SKILL.md+21−21@@ -4,7 +4,7 @@ description: >- Audit a KiCad board (.kicad_sch + .kicad_pcb) for design errors before fab: run real ERC/DRC via kicad-cli or the Adom desktop KiCad bridge, extract the pad-level netlist from the PCB file, then walk a checklist that catches what- ERC cannot — floating mandatory pins (VCAP-type), supply pins tied to GND,+ ERC cannot: floating mandatory pins (VCAP-type), supply pins tied to GND, wrong strap/boot-pin encodings, regulator feedback dividers computed with the wrong variant's VFB, missing pull-ups on open-drain buses, crystal load-cap math, impedance net-class misassignment, unrouted nets, keepout misconfig.@@ -24,17 +24,17 @@ checklist below is ordered by how often each step finds real bugs. ## 1. Run the real checkers first -- Local KiCad: `kicad-cli sch erc <root.kicad_sch>` (KiCad ≥8) and- `kicad-cli pcb drc <board.kicad_pcb>` (≥7). The installed KiCad must be ≥ the+- Local KiCad: `kicad-cli sch erc <root.kicad_sch>` (KiCad 8+) and+ `kicad-cli pcb drc <board.kicad_pcb>` (7+). The installed KiCad must be ≥ the file format version (check the `(version …)` header). - Adom cloud container without KiCad: send the project to the user's desktop and- use the KiCad bridge — `send_files` → `kicad_run_erc` / `kicad_run_drc`.+ use the KiCad bridge: `send_files` → `kicad_run_erc` / `kicad_run_drc`. - Before trusting either result, read the project's silenced rules: `.kicad_pro` → `erc.rule_severities` and- `board.design_settings.rule_severities` — anything on `"ignore"` makes a+ `board.design_settings.rule_severities`. Anything on `"ignore"` makes a clean pass hollow.-- DRC `unconnected_items` = unrouted copper = fab blocker. Report those first.-- Group the rest of the DRC list by root cause before reporting — hundreds of+- DRC `unconnected_items` = unrouted copper, a fab blocker. Report those first.+- Group the rest of the DRC list by root cause before reporting; hundreds of violations usually collapse to a handful of causes (one bad footprint, one keepout flag, one via style). @@ -43,7 +43,7 @@ checklist below is ordered by how often each step finds real bugs. Three blind spots hide critical bugs behind a 0/0 ERC: - **Symbol pin types.** `power_out` and `bidirectional` pins float silently.- Classic: MCU VCAP pins with no capacitors — board dead, ERC green. List every+ Classic: MCU VCAP pins with no capacitors. Board dead, ERC green. List every unconnected pin from the PCB side and judge each yourself. - **Mistyped power pins.** A custom symbol will happily let a supply pin sit on GND without complaint. Trust the datasheet pin table, not the symbol.@@ -58,29 +58,29 @@ pin lists with pin functions, pads with no net, and per-net routed length + via count. Format gotchas it already handles: pad nets are `(net N "name")` before v10 but `(net "name")` from v10, and the tokenizer must be quote-aware because pin names contain parentheses. (Multi-instance hierarchical sheets store their-references in `(instances …)` blocks — don't diagnose "missing from schematic"+references in `(instances …)` blocks, so don't diagnose "missing from schematic" from the default Reference property.) -## 4. Electrical audit — walk the netlist per IC+## 4. Electrical audit: walk the netlist per IC - **Power pins.** Every supply pin on the right rail. Traps: pins named `*COM` / `E_*` that read like grounds but are supplies ("common **block** supply", not "common"); supply pins left floating; one 100 nF per VDD pin plus bulk. - **Mandatory passives.** Core/VCAP caps, bias and reference resistors- (EXTRES / ISET / RBIAS): exact value *and* tolerance from the datasheet —- sibling parts differ (6.04 k vs 12.1 k is a real trap).+ (EXTRES / ISET / RBIAS): exact value *and* tolerance from the datasheet,+ because sibling parts differ (6.04 k vs 12.1 k is a real trap). - **Resets.** Every reset pin needs a defined source (RC, supervisor, or GPIO) meeting the documented supplies-stable-to-release time. Straps latch on the reset rising edge, so a floating reset also breaks strap latching. - **Straps / boot pins.** Build the full table (pin, pull, latched value) and- check each row against the datasheet encoding table — not intuition. Wrong+ check each row against the datasheet encoding table, never intuition. Wrong MODE encodings that half-work (e.g. advertise only one speed) are common. - **Regulators.** Recompute every feedback divider with the exact orderable- variant's VFB — siblings differ (0.6 / 0.763 / 0.8 V). Check LDO dissipation+ variant's VFB; siblings differ (0.6 / 0.763 / 0.8 V). Check LDO dissipation ((Vin−Vout)×I vs package θJA) and compare rail sizing to the vendor EVB. - **Chip-to-chip buses.** Verify pin-direction mapping end to end. PHY/MAC-mode- function swaps are the classic crossover — confirm against the vendor EVB+ function swaps are the classic crossover: confirm against the vendor EVB schematic, never the pin names. Open-drain buses (MDIO, I2C, IRQ) need pull-ups. Series terminations belong at the driver end. - **Crystals.** Caps from the crystal's CL: CL = C1·C2/(C1+C2) + 2–5 pF stray.@@ -88,15 +88,15 @@ from the default Reference property.) - **Connectors.** Shield/tab pins bonded to GND, unused pins terminated per datasheet, input protection on power entries. -## 5. Layout audit — scriptable from the file+## 5. Layout audit: scriptable from the file - **Net classes.** List the class patterns and confirm every- controlled-impedance net matches one — a net matching no pattern silently+ controlled-impedance net matches one. A net matching no pattern silently gets Default (classic: USB D+/D−). Then check each class's geometry gives the interface's required impedance on this stackup (USB 90 Ω, Ethernet pairs 100 Ω). - **Diff pairs.** Intra-pair skew from the script's per-net lengths.-- **Vias.** Every via style vs the board's min drill / annular constraints —+- **Vias.** Every via style vs the board's min drill / annular constraints; mixed styles are the usual violation source. - **Keepouts.** Check the allow-flags: a keepout drawn around a part but set to disallow *pads* flags the part's own pads.@@ -107,7 +107,7 @@ from the default Reference property.) Every suspicious finding gets a primary source: datasheet, vendor hardware design checklist, or EVB schematic. Check Adom wiki component pages and-`*-usage` skills first — they encode the exact variant (a "wrong" divider is+`*-usage` skills first; they encode the exact variant (a "wrong" divider is how the 0.763 V-VFB variant looks when you assume 0.6 V). For multi-IC boards, fan out one research agent per major IC with numbered questions; require quoted evidence and a confidence level. Anything unconfirmed stays flagged "verify@@ -118,5 +118,5 @@ against datasheet", never asserted. Severity-ranked: **Critical** (won't work / won't fab) → **High** (works wrong or marginal) → **Medium** (fix next spin) → **Low** (advisory). Each finding: refs + pin numbers, why (with source), and one concrete fix. Include a-**verified-correct** section for cleared suspicions — it stops the next-reviewer re-flagging good design.+**verified-correct** section for cleared suspicions so the next reviewer+does not re-flag good design.
package.json+4−4@@ -2,8 +2,8 @@ "slug": "kicad-board-audit", "title": "KiCad Board Audit", "type": "skill",- "version": "1.0.0",- "description": "Agent skill for auditing any KiCad board before fab: real ERC/DRC, pad-level netlist extraction from the .kicad_pcb, and a checklist for the bugs ERC can't see — floating mandatory pins, supply pins on GND, wrong straps, wrong-variant feedback dividers, missing pull-ups, impedance class misassignment — verified against datasheets and reported by severity.",+ "version": "1.0.1",+ "description": "Agent skill for auditing any KiCad board before fab: real ERC/DRC, pad-level netlist extraction from the .kicad_pcb, and a checklist for the bugs ERC can't see \u2014 floating mandatory pins, supply pins on GND, wrong straps, wrong-variant feedback dividers, missing pull-ups, impedance class misassignment \u2014 verified against datasheets and reported by severity.", "tags": [ "skill", "kicad",@@ -30,7 +30,7 @@ }, { "label": "Pre-order check",- "prompt": "I'm about to order this PCB from JLCPCB — audit it first"+ "prompt": "I'm about to order this PCB from JLCPCB \u2014 audit it first" }, { "label": "Netlist only",@@ -44,4 +44,4 @@ "hero": { "path": "docs/hero.png" }-}+}
page.json+1−1@@ -2,7 +2,7 @@ "slug": "kicad-board-audit", "title": "KiCad Board Audit", "type": "skill",- "version": "1.0.0",+ "version": "1.0.1", "description": "Agent skill for auditing any KiCad board before fab: real ERC/DRC, pad-level netlist extraction from the .kicad_pcb, and a checklist for the bugs ERC can't see — floating mandatory pins, supply pins on GND, wrong straps, wrong-variant feedback dividers, missing pull-ups, impedance class misassignment — verified against datasheets and reported by severity.", "tags": [ "skill",