New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

SGLang Model Day-0 Support

by BBuf in BBuf/AI-Infra-Auto-Driven-SKILLS

Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence.

No licenceAuto-check passedAI & LLM Engineering

Install SGLang Model Day-0 Support

skills CLI
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-model-day0-support -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-model-day0-support --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/model-optimization/sglang-model-day0-support .claude/skills/sglang-model-day0-support && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sglang-model-day0-support
GitHub stars
938
Token cost
~2.3k tokens
SKILL.md length
1,032 words
Files
19 (incl. scripts, references, assets)
Skills in repo
10
Repo updated
First seen
Licence
None found

At a glance

Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence.

  • Works in 9 steps: Lock the release cut → Build the architecture gap map → Classify the work → …
  • Planning SGLang support for a newly released LLM, VLM or MoE model
  • SKILL.md covers Start Here, Workflow, Reference Routing and Completion Contract
  • Calls python3; reaches github.com

What it does

A model launch becomes a reviewable support program instead of a single launch command. You lock immutable revisions of the model, weights, tokenizer or processor, SGLang, dependencies and image, then fill in a scope contract and release lock that separate Day-0 commitments from deferred work and mark unavailable weights or hardware as blocked rather than passed.

Next comes an architecture gap map against the public model configuration, a PR dependency graph and a validation matrix, and no model code is written until those agree. Templates for these documents live in `assets/day0-bundle/`. Reference notes cover evidence audits before citing PRs and sanitizing private material, plus case studies for DeepSeek and Kimi releases. The skill can also review whether an existing support PR is ready to release.

When your agent uses it

  • Planning SGLang support for a newly released LLM, VLM or MoE model
  • Mapping a model's attention or decoding design onto SGLang runtime work
  • Checking whether a model-support pull request is ready for release
  • Removing private development evidence before posting a public PR

Example prompts

  • “Draft a Day-0 scope contract and PR plan for supporting the new hybrid-attention model in SGLang.”
  • “Audit this model-support PR and tell me which validation gates are still missing.”
  • “Sanitize our internal benchmark notes before we attach them to the public pull request.”

Requirements

  • Access to the SGLang repository and the new model's public configuration

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Lock the release cut
  2. Build the architecture gap map
  3. Classify the work
  4. Design the PR DAG
  5. Build the validation matrix
  6. Execute the seven gates
  7. Synthesize the public PR
  8. Track post-Day-0 work
  9. Validate and sanitize

What it can do on your machine

Read from SKILL.md and the folder at commit 6dc9c66. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SGLang Model Day-0 Support loads about 2.3k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 1,032 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,032 words (~2,317 tokens).

“Turn a model release into a reviewable SGLang support program. Produce evidence, implementation boundaries, validation gates, and public release artifacts—not only a launch command.”

— opening of SKILL.md by BBuf
name
sglang-model-day0-support

Read the full SKILL.md on GitHub

Files

SKILL.md and 18 other files (scripts, references, assets) in skills/model-optimization/sglang-model-day0-support of BBuf/AI-Infra-Auto-Driven-SKILLS.

  • SKILL.md
  • agents/openai.yaml
  • assets/day0-bundle/architecture-gap-map.md
  • assets/day0-bundle/follow-up-ledger.md
  • assets/day0-bundle/pr-body.md
  • assets/day0-bundle/pr-dag.md
  • assets/day0-bundle/release-lock.md
  • assets/day0-bundle/sanitization-report.md
  • assets/day0-bundle/scope-contract.md
  • assets/day0-bundle/validation-matrix.md
  • references/day0-contract.md
  • references/deepseek-v4-case-study.md
  • references/deepseek-v41-case-study.md
  • references/evidence-audit.md
  • references/kimi-k3-case-study.md
  • references/sanitization.md
  • scripts
  • … and 2 more

Open the folder on GitHubat commit 6dc9c66

Compare with similar skills

SGLang Model Day-0 Support next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

SGLang Model Day-0 Support compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SGLang Model Day-0 Support this skillBBuf/AI-Infra-Auto-Driven-SKILLS938—~2.3kAutomated safety check: PassNone
Update Ollama Cloud Modelsheypinchy/pinchy182—~3.9kAutomated safety check: NotesAGPL-3.0
Vllm Daily PR Issue Trackerascend-ai-coding/awesome-ascend-skills174—~731Automated safety check: PassNone
External Gitcode Ascend Vllm Ascend Deployascend-ai-coding/awesome-ascend-skills174—~1.2kAutomated safety check: PassNone
Dsh Code ReviewZhou-Yujing114514/deepseek-harness-linux120—~2.1kAutomated safety check: PassMIT
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0

Similar skills

  • Update Ollama Cloud Models

    heypinchy/pinchy

    A skill your agent uses when a new Ollama Cloud model is announced or available (e.g.

    182 GitHub stars~3.9k tokensUpdated 20 days ago
    AI & LLM EngineeringAuto-check: notes

  • Vllm Daily PR Issue Tracker

    ascend-ai-coding/awesome-ascend-skills

    Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode…

    174 GitHub stars~731 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • External Gitcode Ascend Vllm Ascend Deploy

    ascend-ai-coding/awesome-ascend-skills

    昇腾 NPU 平台 vLLM 大模型推理服务一键部署。触发：用户说'部署 模型名'、'NPU 部署模型'、'vllm serve'。流程：SSH检查 → NPU检查 → 配置发现(必须验证) → 用户确认 → 部署 → cron监控 → 验证。约束：(1) 配置必须从官方文档验证，禁止猜测；(2) 后台启动必须用cron监控，禁止手动轮询。支持…

    174 GitHub stars~1.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Dsh Code Review

    Zhou-Yujing114514/deepseek-harness-linux

    A skill your agent uses when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality…

    120 GitHub stars~2.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Perfup

    raullenchai/Rapid-MLX

    Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

    4k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from BBuf/AI-Infra-Auto-Driven-SKILLS

All 10 skills in this repo

  • LLM Serving Capacity Planner

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Reads SGLang or vLLM startup logs to show where GPU memory went and estimates how many concurrent requests fit at common token lengths.

    938 GitHub stars~2.5k tokensUpdated 5 days ago
    Auto-check passed

  • LLM Torch Profiler Trace Analysis

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

    938 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed

  • Model Architecture Diagram Finder

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.

    938 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed

  • Model Compute Simulator

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Builds an operator-level compute template for an LLM and estimates FLOPs and MFU for a serving shape, with tensor shapes and parallelism what-if checks.

    938 GitHub stars~4.5k tokensUpdated 5 days ago
    Auto-check passed

  • SGLang Maintainer-Style Review

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs.

    938 GitHub stars~4.6k tokensUpdated 5 days ago
    Auto-check passed

  • Torch Profiler Layer Track

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Adds verified layer guides such as L0 and L1 and compact GPU lanes to an existing Torch Profiler Chrome trace, changing how it looks but not how it ran.

    938 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about SGLang Model Day-0 Support

What does SGLang Model Day-0 Support do?

Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence. A model launch becomes a reviewable support program instead of a single launch command. You lock immutable revisions of the model, weights, tokenizer or processor, SGLang, dependencies and image, then fill in a scope contract and release lock that separate Day-0 commitments from deferred work and mark unavailable weights or hardware as blocked rather than passed.

When should I use SGLang Model Day-0 Support?

SGLang Model Day-0 Support fits situations like: planning SGLang support for a newly released LLM, VLM or MoE model; mapping a model's attention or decoding design onto SGLang runtime work; checking whether a model-support pull request is ready for release; removing private development evidence before posting a public PR.

How do I install SGLang Model Day-0 Support in Claude Code?

Run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-model-day0-support -a claude-code`. Or copy the skill folder (skills/model-optimization/sglang-model-day0-support in BBuf/AI-Infra-Auto-Driven-SKILLS) into .claude/skills/sglang-model-day0-support in your project. Claude Code loads it when a task matches its description.

How do I install SGLang Model Day-0 Support in Codex?

Run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-model-day0-support -a codex`. Or copy the skill folder (skills/model-optimization/sglang-model-day0-support in BBuf/AI-Infra-Auto-Driven-SKILLS) into .agents/skills/sglang-model-day0-support in your project. Codex loads it when a task matches its description.

Can I use SGLang Model Day-0 Support in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-model-day0-support -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sglang-model-day0-support, .gemini/skills/sglang-model-day0-support, .github/skills/sglang-model-day0-support and .opencode/skills/sglang-model-day0-support in your project.

What does SGLang Model Day-0 Support need to run?

Going by SKILL.md and its folder, SGLang Model Day-0 Support needs the command-line tools its instructions call (python3). Our summary lists: Access to the SGLang repository and the new model's public configuration.

Does SGLang Model Day-0 Support access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is SGLang Model Day-0 Support safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does SGLang Model Day-0 Support use?

No licence was found for SGLang Model Day-0 Support or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does SGLang Model Day-0 Support use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.

What are the alternatives to SGLang Model Day-0 Support?

Skills that share tags, products or a category with SGLang Model Day-0 Support: Update Ollama Cloud Models (heypinchy/pinchy, 182 stars), Vllm Daily PR Issue Tracker (ascend-ai-coding/awesome-ascend-skills, 174 stars), External Gitcode Ascend Vllm Ascend Deploy (ascend-ai-coding/awesome-ascend-skills, 174 stars) and Dsh Code Review (Zhou-Yujing114514/deepseek-harness-linux, 120 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SGLang Model Day-0 Support?

BBuf (a GitHub user) maintains it in BBuf/AI-Infra-Auto-Driven-SKILLS, which has 938 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.

Source: BBuf/AI-Infra-Auto-Driven-SKILLS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.