agentleFS
elithrarelithrar/dotfiles/.agents/skills/motronic/SKILL.md

motronic

Skill222 starsChanged 57 days agoMITView on GitHub

Diagnose Porsche Carrera 3.2 Bosch Motronic faults and interpret DME ROMs or calibration changes. Use for 1984-1989 3.2 DME systems, including swaps into earlier cars; not generic 911, CIS, or other ECU advice.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only references needed for the current question.

    line 20
  2. Distinctive:

    Do not invent pinouts, component specifications, map addresses, checksums, or safe timing/AFR targets.

    line 24
  3. Distinctive:

    Use measurements to isolate the fault instead of prescribing parts replacement or restarting a completed diagnostic checklist.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Porsche 3.2 Motronic

Identify the actual engine, harness, DME, and chip family from available evidence; chassis year alone is insufficient on a conversion. Preserve measured facts and distinguish them from hypotheses. Ask only for the smallest missing detail that changes the next diagnostic branch or makes a specific instruction safe.

Read the relevant reference

TaskRead when needed
Fault isolation, no-start, hot-start, sensors, injector/spark, wiringDiagnostics
ROM identity, offsets, conversions, XDF alignmentROM decoding
AFR, timing, engine-build or calibration changesTuning
Pelican forum research or field-repair contextPelican research
Conflicting evidence, source selection, or a detailed decode reportSources and reporting

Read only references needed for the current question. Fetch current primary evidence when exact technical claims need verification; these notes do not replace the correct wiring diagram or a ROM-specific decode. Use forum accounts as hypotheses and cite them when they materially support the answer.

Diagnostic constraints

Do not invent pinouts, component specifications, map addresses, checksums, or safe timing/AFR targets. Before pin-level probing, establish the DME/harness version and verify the pin against its wiring source. State connector location, key or engine state, instrument mode, and what each result would establish.

Use measurements to isolate the fault instead of prescribing parts replacement or restarting a completed diagnostic checklist. Provide the next useful test and its possible branches; request the result before drawing a conclusion that depends on it. Investigate hardware faults before tuning around them.

For ROM work, preserve the original binary and record its hash. Treat bundled offsets and formulas as specific to their documented image until alignment is proven. Do not claim a tune is safe from map math or engine specifications alone; relate risk to actual AFR, timing, fuel, temperature, and controlled-load evidence.

For physical EPROM reads/writes, use an available programmer-specific workflow or verified programmer documentation. Do not assume a minipro skill is installed. Decoding a binary does not authorize programming a chip.

Response

Lead with the supported conclusion or next check, then the decisive evidence and material uncertainty. Use a fuller report only when the user asks for one or the data requires it. Keep electrical and engine-risk cautions specific to the proposed action; do not attach a generic risk section to every answer.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.