Skip to main content
在 Manus 中运行任何 Skill
一键导入
sublimotion
GitHub 创作者资料

sublimotion

按仓库查看 1 个 GitHub 仓库中的 13 个已收集 skills。

已收集 skills
13
仓库
1
更新
2026-07-06
仓库分布

Skills 分布在哪些仓库

按已收集 skill 数展示主要仓库,并显示它们在该创作者目录中的占比和职业覆盖。

仓库浏览

仓库与代表性 skills

benchmark-runner
软件开发工程师

Plan, execute, and analyze LLM serving benchmarks across vLLM and SGLang configurations. Use when user says "run benchmarks", "benchmark config", "QPS sweep", "compare serving configs", "custbench", "benchmark analysis", or "generate benchmark report". Do NOT use for writing Terraform (use terraform-automation), deployment validation (use deployment-orchestrator), or GPU hardware diagnostics (use gpu-infra-troubleshooting).

2026-07-06
agent-runtime
软件开发工程师

Launch and manage detached agent runs on EKS via the agent-runner CLI. Use when the user says "launch an agent run", "agent runtime", "agent-runner", "run this spec on the cluster", "check run status", "agent run logs", or "stop a run". Do NOT use for writing the agent-runner code itself (edit the sibling ../agent-runner repo), Terraform of the foundation (use terraform-automation), or GPU serving deployments (use infra-deployer).

2026-06-19
cherry-pick-eval
软件开发工程师

Evaluate upstream PRs or commits individually against the K2.6 baseline. Tests each change in isolation using the same L0-L4 pipeline, identifying which are helpful, harmful, or neutral for our specific workload. Use when new upstream PRs land (Alpha-MoE, Mega MoE, FP8 fusion) or when evaluating a bundle of commits. Never assume a bundle is net-positive — the EFA harness found bundled expert commits regressed LL performance by 10%.

2026-06-19
diagnose-bottleneck
软件开发工程师

Analyze a failed or underperforming kernel candidate using ncu profile data and telemetry history. Produces a structured diagnosis (what's wrong, why, what to try next) and updates the constraint database. Use after /verify-kernel returns a failure or an L3/L4 regression, or when the agent needs guidance on which optimization direction to pursue.

2026-06-19
generate-candidate
软件开发工程师

Generate an optimized kernel candidate using the current state vector approach. Injects all active constraints from the database, uses the specified DSL (Triton/TileLang/CUDA), and targets the highest-headroom region identified by profiling. Use after profiling identifies a target, or when the previous candidate fails and the state vector has advanced.

2026-06-19
manage-constraints
软件开发工程师

View, query, add, or demote constraints in the kernel optimization constraint database. The database is append-only — constraints are never deleted, only demoted in severity if contradicted by evidence. Use to inspect what the agent has learned, manually inject domain knowledge, or query relevant constraints before generating a candidate.

2026-06-19
profile-kernel
软件开发工程师

Profile a GPU kernel or full serving pipeline using NSight Compute. Produces roofline classification (compute/memory/latency-bound), identifies top-N kernels by wall-clock time, and maps each to pipeline stage (MoE dispatch, MLA decode, attention, comm). Use when starting optimization, after a new baseline is established, or when the freeze manager redirects to a new target region.

2026-06-19
verify-kernel
软件开发工程师

Run the cascaded L0-L4 verification pipeline on a kernel candidate. Each level gates the next — a candidate that fails L1 never wastes time on L4. Records telemetry at every stage regardless of pass/fail. Use after /generate-candidate produces a new kernel, or when evaluating an upstream PR cherry-pick.

2026-06-19
当前展示该仓库 Top 8 / 13 个已收集 skills。
已展示 1 / 1 个仓库
已展示全部仓库