From 4c2cdcbdc0035094d8ac49a765f0413ae65bd7f7 Mon Sep 17 00:00:00 2001 From: redwood56 Date: Thu, 16 Jul 2026 23:58:32 +0000 Subject: [PATCH] docs: surface bundled Agent Skills in README Add a top-level Agent Skills section listing the five bundled SKILL.md files, plus a Reference-table row and a clearer AGENTS.md label. --- README.md | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index eb537010..b9585825 100644 --- a/README.md +++ b/README.md @@ -30,11 +30,12 @@ - [JSONL Dataset](./docs/dataset_jsonl.md) - [Inference](./docs/inference.md) - [Policy Server](./docs/action_policy_droid_server.md) +- [Agent Skills](#agent-skills) - Reference - [Code Structure](./docs/code_structure.md) - [Environment Variables](./docs/environment_variables.md) - [FAQ](./docs/faq.md) - - [AGENTS.md](./AGENTS.md) + - [AGENTS.md — repo map for coding agents](./AGENTS.md) ## Setup @@ -87,13 +88,35 @@ python -m cosmos_framework.scripts.inference \ See [Policy Server](./docs/action_policy_droid_server.md) for the full guide. +## Agent Skills + +Coding agents (Claude Code, Codex CLI, Cursor, and other AGENTS.md-aware +tools) can load task-specific instructions for this repo from the bundled +AgentSkills. Each skill is a self-contained `SKILL.md` that the agent +invokes automatically when the user's request matches its description. + +Skills live in [`.agents/skills/`](./.agents/skills) (canonical) and are +mirrored under [`.claude/skills/`](./.claude/skills) for Claude Code: + +| Skill | When it activates | +| -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | +| [`cosmos3-setup`](./.agents/skills/cosmos3-setup/SKILL.md) | Installation, environment setup, checkpoint downloads, Docker. | +| [`cosmos3-codebase-nav`](./.agents/skills/cosmos3-codebase-nav/SKILL.md) | "Where is X" / "where do I change parameter Y" questions across `cosmos_framework/`. | +| [`cosmos3-inference`](./.agents/skills/cosmos3-inference/SKILL.md) | Running offline or online inference, parallelism, sampling parameters. | +| [`cosmos3-post-training`](./.agents/skills/cosmos3-post-training/SKILL.md) | SFT post-training end-to-end: data prep, DCP conversion, launch, export. | +| [`cosmos3-env-troubleshoot`](./.agents/skills/cosmos3-env-troubleshoot/SKILL.md) | Diagnosing install/runtime errors (ImportError, CUDA, Docker, checkpoint failures). | + +See [`AGENTS.md`](./AGENTS.md) for the canonical repo map that agents load +first; the skills above are referenced from there. + ## Reference -| Topic | What it covers | -| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ | -| [Setup](./docs/setup.md) | Hardware/software prerequisites, `uv` install paths, CUDA variants, Docker base image, and base-checkpoint downloading. | -| [Code Structure](./docs/code_structure.md) | Repository layout and a per-subpackage tour of `cosmos_framework/` — where each concern lives and where to add new code. | -| [Training](./docs/training.md) | Launching multi-GPU and multi-node runs; parallelism strategies; mixed precision; resuming. | -| [Inference (from a trained checkpoint)](./docs/inference.md) | Loading a trained checkpoint into one of the inference backends. | -| [Policy Server](./docs/action_policy_droid_server.md) | Running the server-client pipeline for Cosmos3-Nano-Policy-DROID. | -| [FAQ](./docs/faq.md) | Troubleshooting (OOM, NCCL hangs, slow training), environment variables, and common pitfalls. | +| Topic | What it covers | +| ------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------- | +| [Setup](./docs/setup.md) | Hardware/software prerequisites, `uv` install paths, CUDA variants, Docker base image, and base-checkpoint downloading. | +| [Code Structure](./docs/code_structure.md) | Repository layout and a per-subpackage tour of `cosmos_framework/` — where each concern lives and where to add new code. | +| [Training](./docs/training.md) | Launching multi-GPU and multi-node runs; parallelism strategies; mixed precision; resuming. | +| [Inference (from a trained checkpoint)](./docs/inference.md) | Loading a trained checkpoint into one of the inference backends. | +| [Policy Server](./docs/action_policy_droid_server.md) | Running the server-client pipeline for Cosmos3-Nano-Policy-DROID. | +| [FAQ](./docs/faq.md) | Troubleshooting (OOM, NCCL hangs, slow training), environment variables, and common pitfalls. | +| [AGENTS.md](./AGENTS.md) + [Agent Skills](#agent-skills) | Repo map and task-specific `SKILL.md` files loaded automatically by AGENTS.md-aware coding agents (Claude Code, Codex CLI, Cursor, etc.). |