Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
⚡️ A curated library of Agent Skills focused on Jetpack Compose performance.
| Date | Stars |
|---|---|
| 2026-07-31 | 458 |
| 2026-08-06 | 465 |
| 2026-08-14 | 478 |
| 2026-08-18 | 486 |
| 2026-08-19 | 488 |
| 2026-08-20 | 489 |
| 2026-08-22 | 490 |
| 2026-08-23 | 492 |
| 2026-08-24 | 493 |
| 2026-08-25 | 492 |
| 2026-08-26 | 491 |
| 2026-08-27 | 492 |
| 2026-08-28 | 492 |
| 2026-08-29 | 493 |
| 2026-08-31 | 495 |
| 2026-09-03 | 496 |
| 2026-09-06 | 497 |
| 2026-09-07 | 499 |
| 2026-09-09 | 500 |
| 2026-09-10 | 502 |
| 2026-09-13 | 503 |
| 2026-09-14 | 505 |
| 2026-09-16 | 506 |
| 2026-09-18 | 507 |
| 2026-09-19 | 508 |
| 2026-09-20 | 508 |
Today
— stars today
This week
+5 stars this week
This month
+19 stars this month
Momentum
0.0
growth rate 0.99%/day
# Compose Performance Skills
If you have used [`android/skills`](https://github.com/android/skills), you already know the shape of an Agent Skill: a Markdown file an agent loads on demand to perform one focused task. That library covers Android development at large. This repository goes narrow and deep on a single axis: Jetpack Compose performance. The skills here cover stability, recomposition, lazy layouts, custom modifiers, side effects, baseline profiles, R8, hot reload with Compose HotSwan, and the measurement loop that ties them together. The goal is to give a coding agent enough operational knowledge to diagnose and fix Compose performance issues without guessing, and to give the developer reading the diff a citation trail back to primary sources.
<a href="https://howcomposeworks.com/">
<img src="https://github.com/user-attachments/assets/0f0f72fc-49ce-48b5-b3dd-f2c04e907f80" width="13%" align="right"/>
</a>
## 📗 Jetpack Compose Mechanisms Book
[Jetpack Compose Mechanisms](https://howcomposeworks.com/) takes you from "how to use Compose" into "how Compose actually works," tracing the AOSP source line by line through the compiler, runtime, and UI layers beneath every Composable, with practical, production-ready examples from the author's own Compose tooling and libraries. It then ties all three layers together into deep, real-world performance tuning, from stability inference to the skip decision. Fully updated for Kotlin 2.4.0 and Compose Compiler 2.4.0.
## What this repo is
This is a curated library of Agent Skills focused on Jetpack Compose performance. Every skill is grounded in primary sources: Android Developers documentation, the Compose compiler, posts by Ben Trengrove, Chris Banes, Manuel Vivo, and the skydoves open source projects, and blog posts. Every API reference is pinned to a version.
The skills follow the open Agent Skills standard published at [agentskills.io](https://agentskills.io), the same `SKILL.md` format used by Anthropic's Skills API, Android Studio Agent mode, and Gemini. The library was iterated against Claude Code, where the SKILL.md files load directly; other compatible runtimes have not been individually end to end tested.
Note that the [Android CLI](https://developer.android.com/tools/agents/android-cli) itself manages only Google's [first party skill catalog](https://github.com/android/skills) (`android skills add --skill <name>`); this repo is a community library outside that catalog and is loaded by agent runtimes from project local directories rather than installed via the CLI.
## What is a Skill
A Skill is a single Markdown file (`SKILL.md`) plus optional `references/` material that teaches an agent how to perform one focused task. It declares trigger vocabulary in YAML frontmatter and a numbered workflow in the body. The agent reads the frontmatter, decides whether the skill applies to the current task, then follows the workflow inside `SKILL.md` step by step.
A skill is not documentation for humans. It is operational instructions for an LLM. That changes the writing voice: terse, imperative, RIGHT and WRONG snippet pairs, MUST and MUST NOT directives in bold caps, and a Verification checklist that proves the work was done. Prose is kept short. Code samples carry the load.
## Directory layout
```
compose-performance-skills/
├── README.md # this file
├── INDEX.md # symptom to skill lookup table
├── LICENSE # Apache-2.0
└── <category>/<slug>/
├── SKILL.md # the skill (required)
└── references/ # optional, one level deep
└── <topic>.md
```
Conventions:
- **Category**: lowercase, one of `stability`, `recomposition`, `lists`, `modifiers`, `side-effects`, `measurement`, `build`, `audit`, `hot-reload`.
- **Slug**: gerund form, lowercase, hyphenated, max 64 chars (`diagnosing-compose-stability`, `migrating-to-modifier-node`).
- **`SKILL.md`**: uppercase. Every skill body stays under 50Excerpt of 15,097 characters
Read on GitHub
8
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a288b38303098eb6, llm:Repository topics and description: 'Agent Skills', 'Jetpack Compose performance', 'android', 'kotlin', 'compose', 'llm-tools', 'agent-skills' — 'A curated library of Agent Skills focused on Jetpack Compose performance.'
matched fp:a288b38303098eb6, llm:Repository topics and description: 'Agent Skills', 'Jetpack Compose performance', 'android', 'kotlin', 'compose', 'llm-tools', 'agent-skills' — 'A curated library of Agent Skills focused on Jetpack Compose performance.'
matched fp:a288b38303098eb6, llm:Repository topics and description: 'Agent Skills', 'Jetpack Compose performance', 'android', 'kotlin', 'compose', 'llm-tools', 'agent-skills' — 'A curated library of Agent Skills focused on Jetpack Compose performance.'