Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shen-shanshan/vllm-dev-skills --skill vllm-dev-task-discoverygit clone --depth 1 https://github.com/shen-shanshan/vllm-dev-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-dev-task-discovery)<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-dev-task-discovery"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-dev-task-discovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-dev-task-discovery"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-dev-task-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00226 | $0.03426 |
| Opus 5 | $0.00113 | $0.01713 |
| Sonnet 5 | $0.00045 | $0.00685 |
| Haiku 4.5 | $0.00023 | $0.00343 |
Grade A, and why
vllm-dev-task-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vLLM 社区开发需求观察分析
概述
本 skill 帮助社区开发者在 vllm-project/vllm 仓库中找到可贡献的 task/idea。通过系统性搜集多渠道信息(Issue、PR、Discussion、代码 TODO、Roadmap、文档),生成按类型归类的结构化需求清单报告。
工作流
用户指定目标模块/特性/模型 → 多源数据搜集 → 需求提炼与分类 → 评估与标注 → 生成报告
第一步:明确目标范围
从用户输入中提取关键信息:
- 目标模块/特性/模型:例如 "多模态"、"Prefix Caching"、"Qwen3-VL"、"Scheduler"、"V1 Engine"
- Top N:用户可指定生成 top N 个 task,默认 20~100(建议默认 30)
- 任务类型偏好(可选):特性开发 / 模型支持 / 性能优化 / Bugfix / 文档补充 / 代码重构
如果用户描述模糊,用简短问题确认范围(例如"你指的是多模态中的视觉编码器 ViT 部分,还是整个多模态 pipeline?")。
第二步:多源数据搜集
必须从以下所有渠道平行搜集信息。每个渠道的搜索关键词应基于用户指定的目标模块确定。
2.1 Open Issues(未关闭的 Issue)
# 搜索开放 issue(最近更新的优先)
gh search issues --repo vllm-project/vllm --state open --limit 50 --sort updated --match title,body "<关键词1>" "<关键词2>"
# 按 label 筛选
gh issue list --repo vllm-project/vllm --state open --limit 50 --label "<相关label>" --sort updated
# 获取 issue 详情(含评论区)
gh issue view --repo vllm-project/vllm <issue-number> --comments
关注以下信号:
- label 为
good first issue/good second issue/help wanted的 issue - 评论区中有 maintainer 明确指出的待做事项
- 近 30 天内活跃的 issue
- 带有
roadmap/feature request/buglabel 的 issue
2.2 近期合并的 PR
# 搜索近期合并的 PR(了解模块正在做什么)
gh search prs --repo vllm-project/vllm --state merged --limit 30 --sort updated --match title,body "<关键词>"
# 按 label 筛选 PR
gh pr list --repo vllm-project/vllm --state merged --limit 30 --label "<相关label>" --sort updated
关注以下信号:
- PR 中 maintainer 提到的"后续可以做的优化"(follow-up)
- PR 评论区中标记为 TODO 的讨论项
- 合并后仍存在的已知限制
2.3 GitHub Discussions
# 搜索讨论
gh search discussions --repo vllm-project/vllm --match title,body "<关键词>" --limit 20
关注:
- 社区用户提出的需求或痛点
- maintainer 对某些特性规划的表态
- Roadmap 讨论
2.4 仓库 Roadmap 与里程碑
# 获取里程碑信息
gh api repos/vllm-project/vllm/milestones --jq '.[] | select(.state=="open") | {title, description, due_on}'
# 搜索 Roadmap 相关 issue
gh issue list --repo vllm-project/vllm --state open --label roadmap --limit 20
关注:
- 带有季度/版本里程碑的 issue
- 带
roadmap/priority/p0/p1label 的 issue
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 330 lines · 226 tokens per session scan A eb9e93466255
vllm-dev-task-discovery is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 226 tokens to every session and 3,426 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.