ArmDeveloperEcosystem

Review Arm Learning Paths for structural soundness, task ownership, scope discipline, progression, validation, further reading placement, recap sections, and performance-learning integrity. Use when asked to review, create, reorganize, or assess the structure of content under content/learning-paths.

Review and improve Arm Learning Paths and install guides for SEO, GEO, AEO, search snippets, AI-agent selection, and answer-engine readiness. Use when asked to optimize discoverability, search intent, AI-readable structure, page titles, headings, summaries, or content selection signals beyond only front matter descriptions.

Review and improve writing style, voice, tone, readability, inclusive language, Arm terminology, heading style, word choice, and AI-sounding prose in Arm Learning Paths and install guides. Use when asked to polish prose, make content less AI-generated, improve clarity, or align with Arm editorial style.

Add or update structured Markdown and Hugo components in Arm Learning Paths and install guides. Use when asked to turn selected text into a link, table, notice, tab pane, code pane, shortcode block, or other repo-specific Markdown component while preserving surrounding content.

Toggle draft mode on a Learning Path _index.md. Use when: marking a learning path as draft, hiding a learning path from publication, adding draft: true to front matter, unpublishing or disabling a learning path, removing draft, publishing a learning path, taking a learning path out of draft.

Review and improve code samples, commands, command output, and fenced code blocks in Arm Learning Paths and install guides. Use when checking editorial formatting, technical accuracy, runnable commands, output lead-ins, code fence integrity, language tags, or token-heavy and unexplained code or output blocks.

Review and improve accessible Markdown link text in Arm Learning Paths and install guides. Use when asked to find vague links, fix link text such as here or click here, verify internal links, improve screen-reader clarity, or make links descriptive and task-focused.

Add or improve SEO-friendly front matter description fields for Arm Learning Paths and install guides. Use when asked to add missing descriptions, update weak metadata descriptions, optimize search snippets, or ensure Learning Path pages and install guides have accurate description metadata.

Build SME2-on and SME2-off ExecuTorch runner binaries for the profiling kit. Use when Codex needs macOS or Android executor_runner binaries, when executorch was refreshed, when CMake presets changed, when runners are missing, or before running SME2-on versus SME2-off profiling experiments.

Run SME2-on versus SME2-off profiling experiments for an exported ExecuTorch .pte model on macOS or Android. Use when Codex needs to create or edit pipeline JSON configs, execute timing or XNNPACK trace runs, compare runner variants, collect ETDump artifacts, rerun analysis-only mode, or validate profiling output directories.

Set up or repair the SME2 ExecuTorch profiling workspace. Use when Codex needs to create the repo-local Python virtual environment, clone or refresh the required executorch checkout, install ExecuTorch for profiling, handle setup failures, or validate that the workspace is ready before building runners, exporting models, or profiling.

Run or audit the end-to-end SME2 ExecuTorch profiling smoke test. Use when Codex needs to prove a fresh workspace works, validate setup/build/export/pipeline wiring with toy_cnn, check generated artifacts before a PR or demo, or diagnose which workflow stage is broken.

Analyze existing SME2 ExecuTorch profiling outputs. Use when Codex needs to regenerate ETDump CSV files, compute robust latency statistics, compare SME2-on versus SME2-off timeline CSVs, identify operator-category bottlenecks, inspect portable versus delegated behavior, or derive XNNPACK kernel evidence from xnntrace logs.

Export a registered PyTorch model to an ExecuTorch .pte artifact for SME2 profiling. Use when Codex needs to convert toy_cnn, EfficientSAM, EdgeTAM image encoder, or another registered model to portable ExecuTorch format with XNNPACK or portable backend, choose dtype or quantization settings, save graph metadata, or prepare artifacts for profiling.

Generate Markdown reports from SME2 ExecuTorch profiling outputs. Use when Codex needs a shareable performance report, macOS and Android combined report, latency and operator-category summary, SME2-on versus SME2-off speedup write-up, or report validation before publishing results.

Onboard the EdgeTAM image encoder as a model_profiling registry entry for ExecuTorch export and SME2 profiling. Use when Codex needs to clone or wire the EdgeTAM source, preserve third-party license notices, create an EagerModelBase wrapper, register edgetam_image_encoder, download or verify checkpoints, or prepare the image encoder for export.