Binary Size Agent Skill
Analyze and reduce ExecuTorch binary size. Use when investigating binary size, running size tests, or optimizing the runtime for size-constrained deployments.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/pytorch/executorch --skill binary-sizeThe instruction itself
8 sections, as written by the authorBinary Size
Start from the main branch of executorch
Ask the user where the executorch repo is.
git checkout main && git pull
Build and measure baseline
conda activate executorch
bash test/build_size_test.sh
strip -o /tmp/size_test_stripped cmake-out/test/size_test
strip -o /tmp/size_test_all_ops_stripped cmake-out/test/size_test_all_ops
ls -la /tmp/size_test_stripped /tmp/size_test_all_ops_stripped
Produces two binaries:
cmake-out/test/size_test— ExecuTorch runtime without operator implementationscmake-out/test/size_test_all_ops— ExecuTorch runtime with portable ops
Analyze with bloaty
bloaty cmake-out/test/size_test -d symbols -n 30 # by symbol
bloaty cmake-out/test/size_test -d sections # by ELF section
bloaty <after> -- <before> # diff two builds
nm -S <binary> | sort -k2 -rn | head -30 # symbol sizes
strings <binary> | less # string literals in .rodata
Note: bloaty -d compileunits requires debug info (-g). The Release build does not include it.
Key build flags
Set by test/build_size_test.sh:
CMAKE_BUILD_TYPE=ReleaseEXECUTORCH_OPTIMIZE_SIZE=ON— enables-Os,-fno-exceptions,-fno-rtti, unwind table suppressionCXXFLAGS="-fno-exceptions -fno-rtti -Wall -Werror"
Constraints
- Use CMake to build (not Buck)
- C++17 minimum language standard
- Must build on GCC 9 (CI uses
executorch-ubuntu-22.04-gcc9-nopytorch) and Clang 12 — avoid compiler-specific flags or pragmas without version guards - Do not regress existing functionality — run tests for modified files
- Do not change build flags in
build_size_test.shfor size reductions - Do not increase latency in the core runtime
Where to look for size reductions
.text: look for large functions, template bloat, duplicate instantiations.rodata: verbose error messages, format strings, embedded file paths (__FILE__).eh_frame: should already be suppressed whenEXECUTORCH_OPTIMIZE_SIZE=ON- Static init functions (
nm -S <binary> | grep GLOBAL__sub_I): useconstexprconstructors to constant-initialize static arrays - Logging strings:
ET_LOG_ENABLED=0in Release eliminates format strings; ensure it propagates to consumers viaPUBLICcompile definitions on cmake targets - Inline header functions: watch for compile-define mismatches between library and consumer TUs (e.g.
ET_LOG_ENABLEDset in library but not in consumer)
For each change
- Create a branch:
git checkout -b binary-size-<N> - Implement, rebuild, measure stripped sizes
- Create a separate PR — one logical change per PR
- Record results in
binary-size-<N>.md:
| Binary | This change (N vs N-1) | Cumulative (N vs main) |
|---|---|---|
| size_test (stripped) | -X | -Y |
| size_test_all_ops (stripped) | -X | -Y |
- Update the CI size threshold in
.github/workflows/pull.ymlif sizes decrease
Other skills for the same job
different authors, same section of the catalogue
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
How to use it
Take pytorch/binary-size from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.