vllm-pr-desc-generator

vllm-pr-desc-generator is a skill for Claude Code, Codex from shen-shanshan/vllm-dev-skills. It costs 118 tokens per session (1,194 once invoked), scanned A, original, Apache-2.0.

A tool for writing vLLM-style pull request descriptions from changes in the vllm-project/vllm GitHub repository. Pull requests are proposed code changes; the output uses the sections Purpose, Test Plan, and Test Result.

In plain words
What is it for?
Use it with a vLLM pull request URL or number to fetch its data, analyze the changes, and save a Markdown description in the outputs folder.
Why use it?
It saves time when turning a pull request's code changes into a consistent review description. It gathers the pull request details and diff so the summary is based on the actual changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/shanshan-shen/.claude/skills/vllm-pr-desc-generator/scripts/fetch_pr_data.py.

Good fit Use it with a vLLM pull request URL or number to fetch its data, analyze the changes, and save a Markdown description in the outputs folder.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vllm-pr-desc-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator/github.svg)](https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator)
Your own site
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator/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.

agentmods 80×15 button for vllm-pr-desc-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-pr-desc-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01194
Opus 5 $0.00059 $0.00597
Sonnet 5 $0.00024 $0.00239
Haiku 4.5 $0.00012 $0.00119

Measured 12d ago against content hash dc55c919fcb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vllm-pr-desc-generator 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_pr_data.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/vllm-pr-desc-generator/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vllm-pr-desc-generator

Generate a vLLM-style PR description from code changes and save to ./outputs/.

Take ./references/example-pr-desc.md as a style reference for the output.

Workflow

  1. Parse PR number — extract from URL or direct number
  2. Fetch PR data — run scripts/fetch_pr_data.py
  3. Read the JSON — load into context
  4. Analyze code changes — understand the diff, purpose, and impact
  5. Generate PR description — write vLLM-format description
  6. Save — write to ./outputs/pr-<NUMBER>-desc.md
  7. Confirm — tell the user the output path

Step 1: Parse PR Number

Extract <PR_NUMBER> from user input. Accepted formats:

  • https://github.com/vllm-project/vllm/pull/1234512345
  • vllm PR 12345 or PR #1234512345
  • Plain number 1234512345

For PRs from other repos (e.g., vllm-project/vllm-ascend), adjust the --repo flag in the fetch script accordingly. Default repo is vllm-project/vllm.

Step 2: Fetch PR Data

python3 /Users/shanshan-shen/.claude/skills/vllm-pr-desc-generator/scripts/fetch_pr_data.py <PR_NUMBER> \
    --output /tmp/vllm_pr_<PR_NUMBER>.json

Optional flags:

  • --token <token> — GitHub PAT (not needed if gh CLI is authenticated)
  • --max-diff-chars <N> — limit diff size (default 80 000)

Step 3: Analyze Code Changes

Read /tmp/vllm_pr_<PR_NUMBER>.json. Focus on:

  • diff and files: Understand what code changed, which modules are affected
  • pr.title: Infer the PR category prefix (e.g., [Feature], [BugFix], [Misc], [CI/Build], [Doc])
  • pr.body: Check if the author already provided context or linked issues
  • issue_comments / review_comments: Extract reviewer feedback, design decisions, test suggestions

Categorize the change type:

  • Feature: New functionality, new model support, new API
  • BugFix: Correctness fix, crash fix, regression fix
  • Refactor: Code reorganization without behavior change
  • Performance: Optimization, memory reduction, throughput improvement
  • Docs: Documentation only
  • CI/Build: Build system, CI pipeline, dependency changes

Read the full file on GitHub · 111 lines

Files

What ships with it

7 files 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.

Changes

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.

  1. 12d ago First seen · 111 lines · 118 tokens per session scan A dc55c919fcb2

Subscribe to this mod's changes

vllm-pr-desc-generator is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (17 stars, last pushed 3d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,194 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

contribute-to-eliza

Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…

elizaOS/eliza · 68 tokens

github

Interact with GitHub using the gh CLI to manage repositories, issues, pull requests, CI/CD workflow runs, and API queries. Use when the user asks to create, list, view, merge, or close pull requests and issues; check CI status or workflow run logs; query the GitHub API for repository data; or perform any GitHub…

elizaOS/eliza · 104 tokens

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens

git-checkpoint

Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.

agentscope-ai/agentscope-java · 39 tokens

csv

CSV data processing — view, filter, convert, merge tabular data. Zero barrier — use with x-cmd, Python, or awk. Use for "csv", "data", "table", "spreadsheet", "conversion".

x-cmd/x-cmd · 49 tokens