vllm-pr-summarylisted

# 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 /Users/shanshan-shen/.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 | | `files` | Per-file stats: filename, status, additions, deletions, patch | | `issue_comments` | General discussion comments | | `review_comments` | Inline code review comments | For large diffs, focus on the `files[].patch` fields grouped by module/directory. ## Step 3: Write the Report Save to `/Users/sh