Validates .NET application compatibility with AWS Graviton (ARM64) architecture by checking, by content, that every resolved NuGet package (including transitive) ships an aarch64 native file for each target runtime identifier and the target's C library, glibc, libstdc++ and page size, and by checking committed native files, P/Invoke loads, x86 intrinsics, x64 project settings, Dockerfiles, Lambda descriptors and Windows-only APIs. Performs static analysis, applies ARM64-required package, code and build fixes (including the move from Windows or .NET Framework to modern .NET on Linux, after approval), documents Graviton runtime recommendations, and validates builds, publish outputs, tests and startup on ARM64. Supports PackageReference, central package management, lock files, packages.config and Paket. Use whenever a .NET workload is to run on Graviton (arm64), to assess or migrate it, even if the skill is not named; also for diagnosing DllNotFoundException and other native-library failures on arm64.
No other project uses it yet
1.1k12d agoReviewMountCreate a free account to mount
Validates Java application compatibility with AWS Graviton (ARM64) architecture by analyzing native libraries, dependencies (including transitive), and architecture-specific code. Performs static analysis, applies ARM64-required dependency updates, documents Graviton JVM flag recommendations, and validates builds on ARM64. Use whenever a Java workload is to run on Graviton (arm64), to assess or migrate it, even if the skill is not named; also for running AWS Transform Custom java-x86-to-graviton transformations.
No other project uses it yet
1.1k12d agoReviewMountCreate a free account to mount
Validates Python application compatibility with AWS Graviton (ARM64) architecture by verifying that every pinned dependency (including transitive) publishes an aarch64 wheel for the project's interpreter, and by checking native extensions, vendored binaries, hash-locked requirements, Dockerfiles and architecture-specific code. Performs static analysis, applies ARM64-required dependency and build fixes, documents Graviton runtime recommendations, and validates install, import, tests and startup on ARM64. Supports pip, pip-tools, PEP 621/setuptools, uv, Poetry and conda, with mappings for Pipenv, PDM, Hatch and vendored or Lambda layer layouts. Use whenever a Python workload is to run on Graviton (arm64), to assess or migrate it, even if the skill is not named; also for diagnosing wheel and native-library failures on aarch64.
No other project uses it yet
1.1k12d agoReviewMountCreate a free account to mount
Correct behavior is necessary but not sufficient — structural quality is a hard requirement. Don't accept a messy implementation just because it passes tests. Read the relevant doc before working in that area:
49045d agoReviewMountCreate a free account to mount
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Create GitHub issues with repo conventions, issue templates, audience control (internal/community), and issue type assignment. Also switches existing issues between internal and community. Use when user says "create an issue", "file a bug", "open an issue", "make this community", "switch issue to internal", or wants to create or manage issues.
49045d agoReviewMountCreate a free account to mount
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
AWSSkill