flagos-ai/skills

1

kernelgen-flagos Unified GPU kernel operator generation and optimization skill. Automatically detects the target repository type (Flag…

flagos-ai/skills

81

2

model-migrate-flagos Migrate a model from the latest vLLM upstream repository into the vllm-plugin-FL project (pinned at vLLM v0.13.0). Us…

flagos-ai/skills

49

3

gpu-container-setup-flagos Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate G…

flagos-ai/skills

45

4

skill-creator-flagos Create new skills, modify existing skills, and validate skill quality for the FlagOS skills repository. Use this skil…

flagos-ai/skills

45

5

tle-developer-flagos Self-contained orchestration skill for writing high-performance TLE kernels and shipping TLE feature changes with rep…

flagos-ai/skills

44

6

flagrelease-entrance-flagos Full FlagRelease pipeline orchestrator. Runs the complete LLM deployment, verification, and benchmarking pipeline for…

flagos-ai/skills

42

7

install-stack-flagos Install the 5-package multi-chip software stack (vLLM, FlagTree, FlagGems, FlagCX, vllm-plugin-FL) inside a GPU conta…

flagos-ai/skills

42

8

model-verify-flagos Verify the serving stack with a user-specified target model. Runs twice: first with FlagGems/FlagCX disabled (isolate…

flagos-ai/skills

42

9

perf-test-flagos Run accuracy benchmarks (FlagEval, when available) and performance benchmarks (vllm bench serve) against a served mod…

flagos-ai/skills

41

10

vllm-plugin-fl-setup-flagos Install and configure vLLM-Plugin-FL for multiple hardware backends including NVIDIA, Ascend and etc. Use when settin…

flagos-ai/skills

40

11

template-skill Replace with a description of the skill and when Claude should use it. This should be one or two complete sentences e…

flagos-ai/skills

39

12

flaggems-pr-submit-flagos This skill should be used when submitting FlagGems operator PRs, reviewing operator code before submission, preparing…

flagos-ai/skills

15

13

flaggems-pr-review-flagos This skill should be used when reviewing FlagGems operator PRs, performing code review, self-reviewing before submiss…

flagos-ai/skills

14

14

flagrelease Full FlagRelease pipeline orchestrator. Runs the complete LLM deployment, verification, and benchmarking pipeline for…

flagos-ai/skills

1

15

gpu-container-setup Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate G…

flagos-ai/skills

1

16

install-stack Install the 5-package multi-chip software stack (vLLM, FlagTree, FlagGems, FlagCX, vllm-plugin-FL) inside a GPU conta…

flagos-ai/skills

1

17

model-verify Verify the serving stack with a user-specified target model. Runs twice: first with FlagGems/FlagCX disabled (isolate…

flagos-ai/skills

1

18

perf-test Run accuracy benchmarks (FlagEval, when available) and performance benchmarks (vllm bench serve) against a served mod…

flagos-ai/skills

1