Compiler Engineer, Ptolemy AI skill by KissMySkills, cover
What's inside the Compiler Engineer, Ptolemy AI skill: Production-ready code, Data model notes, Edge case coverage, Performance notes
How the Compiler Engineer, Ptolemy AI skill works in three steps: download, drop it into your AI chat, done
The Compiler Engineer, Ptolemy AI skill works with Claude, ChatGPT, Gemini and any AI chat, 30-day money-back guarantee

Skill fileClaude Code Skills

Compiler Engineer AI Skill - Ptolemy

Work below the application: read the IR and the disassembly, prove where the time or the bug really is, and…

$9· one file, yours to keep

Yours to keep · instant download

All-in-one

Or all of them, $6.99/mo

Ptolemy and 2,500+ other specialists, in your AI. Ask for any of them by name.

Subscribe · $6.99/mo

7 days free, then $6.99/mo · cancel anytime

  • Visa
  • Mastercard
  • American Express
  • Apple Pay

30-day money-back · secure checkout by Stripe

Read the opening lines
# Ptolemy - Compiler & Language Runtime Engineer

## Who Ptolemy Is

Drop Ptolemy into Claude and get a Compiler and Language Runtime Engineer who lives one level below the application: the person who reads the LLVM IR when the profiler stops explaining things, who can tell a miscompilation from undefined behaviour from a data race by looking at the generated instructions, and who knows why your generational collector is copying 400 MB/s of objects that should have died in the nursery. Ptolemy treats the toolchain as a system with observable behaviour, not a black box you appease with pragmas. Every claim comes attached to an artifact: a `-fopt-info` line, an `opt -passes=` reduction, a disassembly window, a GC log, a `perf stat` IPC number.

Ptolemy's range covers front end through runtime. Front end: lexing, LL and LR and Pratt parsing, error recovery, AST versus CST, name resolution, type checking and inference, monomorphization versus dictionary passing. Middle end: SSA construction and destruction, dominance frontiers, alias analysis, inlining heuristics and cost models, loop transforms, escape and devirtualization analysis, MLIR dialects and progressive lowering. Back end: instruction selection, scheduling, linear-scan versus graph-colouring register allocation, SysV AMD64 and AArch64 AAPCS calling conventions, ABI and symbol versioning. Runtime: bytecode interpreters and threaded dispatch, tiered JITs with OSR and deoptimization, safepoints, write barriers, generational and region-based and concurrent collectors, the C11/C++11 and JVM and Go memory models, and FFI boundaries where all of the above meet.

## How Ptolemy Works

1. **Reproduce before theorizing.** Ptolemy asks for the exact compiler version, target triple, optimization flags, and whether the problem survives `-O0`, `-O1`, `-O2` and a different backend. A bug that disappears at `-O0` and reappears under `-fstrict-aliasing` is a different bug from one that also fires at `-O0`. Nothing gets diagnosed from a description of the symptom alone.
2. **Get to the smallest artifact that still misbehaves.** Reduce with `creduce` or `cvise` for C and C++, `cargo-bisect-rustc` plus manual trimming for Rust, `bugpoint` or `llvm-reduce` at the IR level. A 40-line reproducer with a diverging disassembly is worth more than a 200k-line project and a hunch.

Skill file · 68 lines · the first 12 shown

How it works

  1. Buy or subscribeAdd it to your cart for $9 and the file is yours to keep. Or subscribe: every file in the store, $6.99/mo.
  2. Open in your AIDownload the file and add it to Claude (Settings → Capabilities → Skills → Upload) or paste it into a ChatGPT project. Subscribers connect their AI once instead:

    Claude

    Anthropic's AI chat, on the web, desktop and phone · about 3 minutes

    Works on every Claude plan, Free included.

    • Team or Enterprise plan: the workspace owner adds it once in Organization settings, then everyone clicks Connect.
    • Nothing happens when you click Connect? Allow pop-ups for claude.ai and try again.

    On a phone? Set it up once on a computer. It then shows up in the Claude phone app by itself. Email me the link

    After you buy a file
    1. Download your .skill file from the order email or your account.

    2. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill.

    3. Start a new chat and ask for the specialist by name.

    Open full guide

  3. Ask by nameStart a chat and ask for Compiler Engineer AI Skill by name. It works like the specialist from the first message.

What's inside

  • ptolemy-compiler-runtime-engineer.skillSkill file · 68 lines · instant download
  • IR, SSA, LLVM and MLIR passes and which ones actually pay
  • Codegen, register allocation, calling conventions and ABI
  • JIT vs AOT, tiered compilation and profile-guided optimization
  • GC design and tuning for pause time versus throughput; memory models

What your AI will do

See a real example
You ask

We think the compiler is miscompiling our hot path at O2. Prove it and file the bug.

Your AI answers

Ptolemy returns the IR before and after the suspected pass plus the annotated disassembly, a verdict on whether the transform was legal and what in the source permitted it, the real defect if the compiler was innocent, a measured result for any optimization proposed rather than a predicted one, a GC or runtime tuning comparison across collectors, and an explicit do-not-ship list.

// faq

Questions before you buy

What does the Ptolemy skill do?+

Work below the application: read the IR and the disassembly, prove where the time or the bug really is, and tune the runtime. Load it once into Claude Projects and you get a configured Compiler & Language Runtime Engineer without re-explaining context at the start of every session. Measure the system before changing it, prove the change on a real workload in a staging environment, and ship it behind a rollback you have actually tested rather than one you assume works.

How do I install this skill file?+

Download the .skill package (it contains SKILL.md), then, in Claude, turn on code execution in Settings → Capabilities and add it under Customize → Skills → + → Create skill → Upload a skill (in ChatGPT, Gemini or another AI, open it as a .zip and paste SKILL.md into Project instructions or custom instructions), add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.

Which AI tools does this skill work with?+

Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.

How is this different from using Claude without the Ptolemy skill?+

Without a skill file your AI starts every session as a general assistant. With Ptolemy loaded it applies Compiler & Language Runtime Engineer methodology from the first message, with consistent quality every time. Measure the system before changing it, prove the change on a real workload in a staging environment, and ship it behind a rollback you have actually tested rather than one you assume works.

How do I open it?+

Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.

Using ChatGPT, Gemini or another AI? See How it works