From ai-infra-auto-driven-skills
Manually review and document GitHub PR diffs for model optimization history documents in SGLang, vLLM, or similar serving frameworks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-infra-auto-driven-skills:model-pr-diff-dossierThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill before publishing any model PR optimization history document that
Use this skill before publishing any model PR optimization history document that cites framework PRs.
Do not summarize a PR with only a title-level sentence. Do not use a script or bulk generator to fill motivation, implementation notes, or code excerpts.
For every PR cited as model optimization evidence, the document must include or link to a diff-reviewed PR card with:
#123 text.gh pr diff, or the local framework repository commit. Read the changed source files, not just the PR title.references/card-schema.md when you need the exact card shape. The card must name concrete files/functions/classes and include a short real code excerpt.A model PR history is not ready if any PR card says only "follow-up", "bugfix", "docs", or "optimization" without:
npx claudepluginhub bbuf/ai-infra-auto-driven-skills --plugin ai-infra-auto-driven-skillsGenerates structured PR descriptions from a git diff, commit list, or change summary. Covers what changed, why, and how to test.
Generates PR descriptions, review checklists, risk assessments, test coverage analysis, and automation for efficient code reviews. Use for pull request enhancement workflows.
Reads a GitHub pull request and posts a plain-English explanation as a PR comment, summarizing what it changes and why.