AI Flow

The board loop as one command for KiCad boards on the Adom KiCad Bridge: start a measured run from the human's prompt, plan the stages and say which ones you take yourself (placement, routing) and which the binary runs (router, pours, gate, landing, measurement, current and thermal analysis), then finish only when the board is 100 percent routed, DRC-clean, poured, analysed and measured. One clock from the prompt to the finish line and one manifest per run, so Claude, Codex and any other engine compare on the same flow. Every command answers OK or ERROR with Hint lines that depend on this board and this run. Trigger words: aiflow, adom-aiflow, place and route the board, route the board to 100%, copper pours, current density, thermal analysis, finish the board, compare engines on a board, board loop, from placement to fab, kelvin keepouts, ablation copper, measured run, prompt-to-board time.

The board loop as one command for KiCad boards on the Adom KiCad Bridge: start a measured run from the human's prompt, plan the stages and say which ones you take yourself (placement, routing) and which the binary runs (router, pours, gate, landing, measurement, current and thermal analysis), then finish only when the board is 100 percent routed, DRC-clean, poured, analysed and measured. One clock from the prompt to the finish line and one manifest per run, so Claude, Codex and any other engine compare on the same flow. Every command answers OK or ERROR with Hint lines that depend on this board and this run. Trigger words: aiflow, adom-aiflow, place and route the board, route the board to 100%, copper pours, current density, thermal analysis, finish the board, compare engines on a board, board loop, from placement to fab, kelvin keepouts, ablation copper, measured run, prompt-to-board time.

The engineering step of an adom-aiflow run between sourcing and simulation: derive every component value from the datasheet's own equations in a script that sits beside the values (design/calcs.py writes design/calcs.json), search the stocked values instead of assuming ideal ones, check margins at both ends of every tolerance, derate what derates, write the reasoning next to each choice, and catch the classic part-reading mistakes (Isat typical vs minimum, Isat vs Irms, the wrong row of a series table, nominal vs maximum body size, a dimension written from memory). Trigger words: aiflow circuit design, design equations, calcs.py, calcs.json, component values, datasheet equations, feedback divider, inductor selection, Isat, output capacitance, DC bias derating, feed-forward capacitor, UVLO divider, losses, efficiency, margins.

How to make the comparison video and page for two AI Flow runs (two engines, one board) with adom-aiflow: pull the other run, cut the side-by-side with `compose --with`, write the narration script the words lead (the setup, what each step is, who won each step, the overall winner, how the clock was measured), never dead air, then `compare --push` for the sub-README that leads with the video and links both runs. Trigger words: comparison video, side by side, fable vs astra, two engines, compare runs, narration script, comparison page, who won.

How an adom-aiflow run gets into vendor sites (TI, Mouser, DigiKey, manufacturer CAD portals, PSpice downloads) without ever asking the human for a login: the ladder pup vault, then import the user's own browser logins, then vault sync from another desktop, then create or reset an account with the user's work email and read the verification code from Gmail with adom-google. Human-verification (bot) checks go to the human as ONE click, never solved or bypassed; another account's saved password is never submitted; secrets are never printed or passed through tools that crash on them. nb (the user's real Chrome) when pup is blocked. Trigger words: vendor login, sign in to TI, myTI account, Mouser login, DigiKey login, need a password, credentials, sign up on a vendor site, verification code, captcha, press and hold, bot check, pup vault, import browser logins, vault sync, nb login.

The first step of an adom-aiflow run, before any board exists: turn the human's brief (a video, a spec, a chat message, "reproduce this") into requirements.json (rails, interfaces, form factor, fab target and sourcing profile, deliverables), start the clock at the prompt rather than at the first board, and ask the human only what is truly their decision. Read this the moment someone asks for a new board or molecule. Trigger words: aiflow intake, new board from a brief, requirements.json, design from a video, design from a datasheet, make a molecule, reproduce this design, what are the requirements, start the clock, prompt time, before the board exists, what should I ask the user.

Keep a live clips page for an adom-aiflow run: after every step's clip stops, append it (the 10x cut, the nine-frame contact sheet, which step, what it shows, whether it is suspect) to docs/clips.md on the project's wiki page and push it at once, so the human can follow the build in a pup or webview tab, and an overnight run leaves a morning's worth of clips. Covers the wiki sub-readme mechanics (adom-wiki repo push --files, repo-root-relative media paths, verify by looking), the clip-notes file, and the pre-push scrub. Trigger words: live clips, clips page, clips.md, follow along, watch the build, overnight run, wake up to clips, step clips, append clip, contact sheet, 10x cut, sub-readme for clips, publish clips as they land.

How an adom-aiflow run is measured, in John's words (2026-09-14). The number is the wall clock from the human's first prompt to the AI saying "done, here is your video", and the per-step cost is the AI's thinking, not the binary's seconds. Every command is a turn in run.jsonl with the thinking gap before it in an append-only run.jsonl; every return to an earlier step (placement moved because a pour had bad heatsinking) is recorded with its reason. Read this before you start, run, report, or compare a aiflow run, and before you hand a run to another engine. Trigger words: aiflow stats, measure the run, how long did each step take, prompt to done, AI thinking time, iterative rework, go back to placement, fable vs codex comparison, deliver the video, run.json ledger.

Make an adom-aiflow board an Adom molecule that fits the scaffold: the 2 mm grid, the origin at the MP1 (front-left) machine pin, MachinePinMediumShort (1.6 mm pad, 1.2 mm drill) at the corners as MP1 to MP4, MachineContactMedium (1.3 mm pad, 0.78 mm drill) for the signal contacts, footprints from the Adom KiCad Library 1.2.3, the fab-rules profile (3rd party fab default, jlcpcb optional), then STEP export, `step2glb convert --molecule` with its stats gates, and molecule-publish. Medium-pin molecules mount on a LrgMed user scaffold (4 mm medium contact grid, large pins on a 32 mm base grid). Trigger words: aiflow molecule, make it a molecule, fits our scaffold, machine pins, MachinePinMediumShort, MachineContactMedium, MP1, molecule grid, molecule outline, fab rules profile, kicad_dru, molecule conformance, molecule export, step2glb molecule, publish molecule, LrgMed scaffold.

Layout judgement for small 2-layer power boards in an adom-aiflow run (bucks, LDOs, load switches on molecules): write the spec as the electrical judgement, keep B.Cu an unbroken ground under the hot loop (spec planeUnder, which the router keeps and the gate checks), give series chains one rotation (spec chains), route Kelvin taps on their own layer, make SW a small solid patch, put thermal vias beside small pins not in the pad, iterate the current-density necks with Fields (215 to 50 A/mm2 here), reason about a still-air thermal budget on a small board, use the silkscreen text verb correctly, and resume `land route` by revision after a dropped reply. Trigger words: power layout, buck layout, hot loop, ground plane under the hot loop, layer policy, FB routing, Kelvin sense, SW node, switch node copper, thermal vias SOT-23, current density neck, Fields, still air, thermal budget, silkscreen text batch, kicad_silk_text_batch, land route resume, dropped reply, route_live.

Make the "how this board was built" video for an adom-aiflow project: what to capture during the run so the video can be made at all (the prompt being typed, the token cost, smooth 3D), how to compose it (motion in every scene, narration that matches the frame, per-clip review in video-post before assembly), and where it lives (the project page README, explained in a sub-readme). Written from John's review of the first one (buck molecule, 2026-10-01). Trigger words: process video, build video, video of the whole process, make a video of the board, narrated video, prompt clip, token cost clip, clip review, storyboard, video-post, voice-over, re-cut the video, choppy 3D, video feedback.

After an adom-aiflow molecule is finished: place it on a scaffold wired to the Adom Control Panel (adom/control-panel-scaffold V2.1.0 contacts: +PS1 MC1-MC4, -PS1 MC20-MC22, GND MC15/MC16/MC55-MC63, USER_IO MC29-MC54 with MC29-MC32 ADC-capable), write the Hydrogen 3D Editor v2 layout JSON (molecules with sku, name, FL-pin position, rotation, pinType, pins; 24 AWG wires from molecule contacts to control-panel contacts), and write a probe plan with test points in the molecule frame and the expected values from simulation. Trigger words: aiflow scaffold, place on scaffold, control panel wiring, workcell layout, probing workcell, Hydrogen 3D editor layout, editorVersion v2, layout json, wire to control panel, controlPanelContactName, probe plan, test points, bench check, live probing.

The bridge from a finished design to an adom-aiflow board: one netlist.json as the single source, generate the KiCad schematic (.kicad_sch with embedded, flattened library symbols, pin stubs, net labels, PWR_FLAG) and the board (.kicad_pcb built with KiCad's own pcbnew Python, molecule interface fixed, parts staged beside the outline), prove them equal with ERC and a pin-by-pin netlist comparison, then `adom-aiflow start`. Covers the KiCad 10 traps (GetFieldByName removed, 3D model paths that do not persist, the single IPC socket owned by the first KiCad process, footprint field edits refused over IPC), project library tables, and running KiCad 10's kicad-cli from a container. Trigger words: aiflow schematic, schematic to board, netlist to pcb, generate kicad_sch, generate kicad_pcb, update pcb from schematic, pcbnew python, KiCad 10 python, ERC, netlist equivalence, sym-lib-table, fp-lib-table, kicad-cli remote, ADOM_AIFLOW_KICAD_CLI, board_mismatch.

Build and review useful two-sided board silkscreen with AI Flow, native geometry checks, grouped labels and full-board process videos.

The simulation step of an adom-aiflow run, after the calcs and before the schematic is frozen: ngspice in the container with two models (an averaged loop-gain model and a cycle-by-cycle XSPICE switching transient), honest labelling of any fitted model, the ngspice syntax traps, then the vendor model (TI PSpice packages are often Cadence-encrypted even when called "unencrypted", so they run only in PSpice for TI on a Windows desktop through Adom Bridge), a vendor-vs-own comparison table and a written design conclusion. Publish results freely; never publish LTspice or PSpice speed benchmarks. Trigger words: aiflow simulate, simulate the buck, ngspice, loop gain, phase margin, crossover, Middlebrook, switching transient, load step, ripple, startup, XSPICE, d_srlatch, PSpice, PSpice for TI, vendor model, encrypted model, CDNENCSTART, validate my model.

Parts and CAD sourcing for an adom-aiflow board, before the schematic is frozen: the fab profile picks where parts come from (default `fab` = the 3rd party fab, Mouser plus Adom stocked basic parts, no JLCPCB parts; user-selectable "jlcpcb" = JLCPCB/LCSC basic parts), search by spec and in stock before naming an MPN, constrain passives to the stocked set, record stock and lead time with a date, then get each part's symbol, footprint and STEP in a fixed order (manufacturer site, distributor CAD links, Adom wiki component page, draw your own labelled AI-generated) and check every model on the step2glb service. Never adom-chipsmith. Trigger words: aiflow sourcing, source the BOM, pick parts, in stock, lead time, sourcing profile, fab profile, Mouser or JLCPCB, Adom basic parts, stocked values, find the STEP, 3D model for this part, manufacturer CAD, SamacSys, Ultra Librarian, footprint source, symbol source.

No description in this skill's frontmatter.

Prepare AI Flow and Fields source changes and bridge PRs against the current wiki head; preserve concurrent modules, verbs and functions; inspect focused diffs and test the combined production build before submission.