slime
RL post-training for LLMs with Megatron and SGLang.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,662 results
torchtitan
Pretrain LLMs at scale with PyTorch 4D parallelism.
trl-fine-tuning
TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.
dotnet-csharp-async-patterns
Writing async/await code. Task patterns, ConfigureAwait, cancellation, and common agent pitfalls.
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
inline-sandcastle
Run the sandcastle implement→review pipeline inside one agent instead of Docker sandboxes. The runner (you) spawns a coder, then a reviewer, as real subagents…
agents-sdk
Build stateful AI agents using the Cloudflare Agents SDK. Load when creating agents with persistent state, scheduling, RPC, MCP servers, email handling, or…
vectorize
Vector database for embeddings and semantic search at the edge. Load when building RAG pipelines, implementing semantic search, storing embeddings from Workers…
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network…
workers-ai
Run AI inference at the edge with OpenAI SDK and Workers AI. Load when generating text with LLMs, extracting structured JSON from text, building chat…
clinical-knowledge
Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal…
agent-availability-report
Generate a production availability report for NVIDIA Elements packages, skill registry, and documentation.
agent-dependencies
Perform one conservative dependency or toolchain upgrade in the Elements monorepo and open a validated pull request. Use for nightly or unattended dependency…
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or…
cdf-event-video-generation
Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation.…
warp-changelog-audit
Use when auditing and recovering Warp changelog fragments, finalizing a release changelog, or synchronizing a tagged release back to main.
warp-release-audit
Use when generating a Warp pre-release or release-candidate audit report from Towncrier fragments and release history.
warp-release-notes
Use when drafting GitHub release notes for a Warp feature or bugfix release from Towncrier fragments or a tagged final changelog.
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
catalog-funnel
Build and manage marketing catalogs, landing pages, and multi-step funnels with your AI agent. Create catalogs from JSON schemas, publish them instantly, run…
agent-profile-from-sessions
Use when the user keeps re-explaining the same preferences to a coding agent across chats (design taste, video style, review rules, how work should be…
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
writing-fragments
Writing, explore — mine raw fragments, no structure yet.