vllm-pr-summary SKILL.md skillA
vllm-pr-summary from shen-shanshan/vllm-dev-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shen-shanshan/vllm-dev-skills/vllm-pr-summary@git:20261026.1de0d3dPins git:20261026.1de0d3d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shen-shanshan/vllm-dev-skills
- Path
skills/vllm-pr-summary/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261026.1de0d3d, committed Oct 26, 2026
- First version recorded
- Mar 16, 2026
- Size
- 5,147 bytes
- Repository stars
- 30
- License
- Apache-2.0
Fetch and analyze a Pull Request from the vllm-project/vllm GitHub repository, then generate a comprehensive Markdown report covering PR overview, code change analysis (with Mermaid architecture/flow diagrams), technical principles, discussion highlights, and risk assessment. Use when the user provides a vllm PR number and asks to summarize, analyze, review, or understand it. Triggered by requests like "帮我分析vllm的PR 12345", "总结一下vllm PR 10000", "vllm PR 9999 做了什么", "analyze vllm PR 12345".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# vllm PR Summary
Fetch and analyze a `vllm-project/vllm` PR, then write a structured Markdown report to `./outputs/`.
Take `./reference/reference.md` as a reference for the report structure and style. Include Mermaid diagrams to illustrate architecture or flow when relevant.
## Workflow
1. **Fetch PR data** — run `scripts/fetch_pr_data.py`
2. **Read the JSON** — load the saved file into context
3. **Analyze** — synthesize PR description, comments, and diff
4. **Write report** — save to `./outputs/pr-<NUMBER>-summary.md`
5. **Confirm** — tell the user the output path
## Step 1: Fetch PR Data
```bash
python3 ~/.claude/skills/vllm-pr-summary/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 2: Load and Analyze
Read `/tmp/vllm_pr_<PR_NUMBER>.json`. The JSON contains:
| Key | Content |
|-----|---------|
| `pr` | PR metadata: title, body, author, state, labels, additions/deletions, branch names, reviews |
| `diff` | Full unified diff of all changed files |
…Read the whole file at its exact version.
How to install
mdr add shen-shanshan/vllm-dev-skills/vllm-pr-summary@sha256:d0683d572af7ab53The line at the top of this page pins the label git:20261026.1de0d3d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_zmhfnz4zttsuup5a)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 16, 2026 and Oct 26, 2026, about one every 224 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.1de0d3d latest | 2026-10-26 | 1de0d3d | 5,147 B | A | view · diff |
| git:20260316.a4505ff | 2026-03-16 | a4505ff | 5,185 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5147 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
shen-shanshan/vllm-dev-skills · 30 stars · license Apache-2.0 · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_zmhfnz4zttsuup5a GET https://markdownregistry.com/api/v1/resolve?ref=shen-shanshan/vllm-dev-skills/vllm-pr-summary GET https://markdownregistry.com/api/v1/blob/d0683d572af7ab537be52f71de453b2ceb1bcdd76aa63eabbdfec38e98f87825
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.