Repository
sohu-mptc/FlashRec agent skills
- skills
- 5
- GitHub stars
- 107
GitHub description: “FlashRec is a CUDA-graph engine for generative recommendation: wide beam search (3–5 SID steps, n=50–512+) over a trie-constrained catalog, in-process FP8 serving, and ranked beams on /v1/chat/completions.”
- Stars
- 107 (5 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Sep 2026
Install all skills
npx skills add sohu-mptc/FlashRecAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in sohu-mptc/FlashRec, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Deploy and serve GenRec checkpoints with FlashRec (install, serve.sh, SID trie, wide-beam knobs, health/curl, FP8, profiling). | sohu-mptc/ | 107 | — | ~974 | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 2 | Run RecIF beam×concurrency eval and FlashRec vs SGLang/vLLM/TRT-LLM baselines. | sohu-mptc/ | 107 | — | ~915 | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 3 | Build SID trie catalogs for FlashRec from OpenOneRec RecIF packed mappings. | sohu-mptc/ | 107 | — | ~468 | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 4 | Capture torch.profiler traces on a running FlashRec server. An agent skill from sohu-mptc/FlashRec. | sohu-mptc/ | 107 | — | ~312 | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 5 | 给 FlashRec 引擎接入一个新模型架构（新的 HF checkpoint / 非 Qwen3 结构）。涵盖模型定义、权重合并加载、FP8 双路径、融合 kernel 接线、CUDA graph 兼容、精度校验、以及压测+trace 验证闭环。当用户要"增加/支持/接入新模型"时使用。 | sohu-mptc/ | 107 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
Questions, answered from the data.
What is the best skill in sohu-mptc/FlashRec?
Model Deploy from sohu-mptc/FlashRec ranks first of the 5 skills in sohu-mptc/FlashRec listed here, with the highest score: its repository has 107 GitHub stars, its SKILL.md loads about 974 tokens and it passes the automated safety check with no findings. Next come Recif Eval and Sid Catalog.
Are the skills in sohu-mptc/FlashRec official?
None yet. All 5 skills in sohu-mptc/FlashRec listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from sohu-mptc/FlashRec?
Run npx skills add sohu-mptc/FlashRec in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.