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 5.5 | $0.00090 | $0.01370 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 226 tokens to every session and 3,426 once invoked, about $0.0009 per session on Opus 5.5. 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
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
code-mate-antigravity
Run Antigravity CLI non-interactively for coding tasks. Use when the user asks to delegate work to Antigravity.
docs-governance
Use when writing, restructuring, auditing, or reviewing Cherry Studio repository documentation, READMEs, JSDoc, comments, Agent instructions, or paired English/Chinese docs, including source-linked documentation impact checks.
find-simplifications
Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.
issue-reporter
A tool for submitting a GitHub Issue, Bug Report, or Feature Request when the user explicitly asks for one. A GitHub Issue is a tracked report or request in a software project.