MAUI PR Performance Analysis
dotnet/maui
Interprets pinned managed benchmark evidence for a dotnet/maui pull request and writes a narrative for the performance review workflow, without running or publishing anything.
Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs.
Install SGLang Maintainer-Style Review
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sglang-humanize-review .claude/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .claude/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/sglang-humanize-review .agents/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .agents/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/sglang-humanize-review .cursor/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .cursor/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git --path skills/sglang-humanize-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/sglang-humanize-review .gemini/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .gemini/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/sglang-humanize-review .github/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .github/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BBuf/AI-Infra-Auto-Driven-SKILLS sglang-humanize-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/sglang-humanize-review .opencode/skills/sglang-humanize-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sglang-humanize-review" agent skill from https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/sglang-humanize-review into .opencode/skills/sglang-humanize-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sglang-humanize-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sglang-humanize-review- GitHub stars
- 938
- Token cost
- ~4.6k tokens
- SKILL.md length
- 2,185 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- None found
At a glance
Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs.
- Works in 7 steps: Inspect the actual diff first. → Read references/corpus-summary.md. → Exhaustively sweep the corpus, then… → …
- Reviewing an SGLang pull request in the style of its maintainers
- SKILL.md covers Overview, Corpus Tools, Review Workflow and SGLang Review Heuristics From…, plus 4 more sections
- Runs Python scripts from its folder; calls python3, gh and git
What it does
The skill reviews SGLang code using a bundled corpus of public pull request reviews from the sgl-project/sglang repository, from the first public PR through 2026-07-27. The corpus is organized as episodes: inline review threads with diff context, top-level PR conversation, and review submissions that keep their state, each with reviewer identity, original text and language, timestamps and multi-round replies.
Every review begins with a comprehension pass: a short summary of the change plus a Mermaid flowchart of how the code runs, with the PR's added or modified steps marked. Feedback then covers correctness, tests, performance, GPU and runtime risks, API compatibility and maintainability. corpus-summary.md is read first for counts and category distribution, and bundled scripts collect, query and summarize the corpus.
The text is candid about limits. The snapshot contains some bot-authored PRs that were kept as captured, later collection excludes bot accounts, the corpus was not recrawled in the latest refresh, and reviews after 2026-07-27 must be read live from GitHub. For kernel replacements, check that the real model actually executes the candidate before counting end-to-end tests as coverage.
When your agent uses it
- Reviewing an SGLang pull request in the style of its maintainers
- Checking a local SGLang patch for GPU, runtime and API compatibility risks
- Looking up how maintainers discussed a similar change in past reviews
Example prompts
- “Review this SGLang PR the way a maintainer would, starting with a flowchart of the change.”
- “Check my local SGLang patch for tests and performance concerns that reviewers usually raise.”
- “Find past review threads about attention backend changes and summarize what maintainers asked for.”
Requirements
- An SGLang diff, PR or local change to review
- Python to run the bundled corpus query scripts
- Network access to GitHub for reviews newer than the bundled corpus
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Inspect the actual diff first.
- Read references/corpus-summary.md.
- Exhaustively sweep the corpus, then synthesize the historical review
- Add cross-skill evidence when the diff touches an area covered elsewhere in
- Explain the PR before judging it (PR comprehension pass).
- Produce a code-review response.
- If no issue is found, say so clearly.
What it can do on your machine
Read from SKILL.md and the folder at commit 6dc9c66. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3ghgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
SGLang Maintainer-Style Review loads about 4.6k tokens when it runs, and up to ~5.8M if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 2,185 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 2,185 words (~4,596 tokens).
“Use the maintained source contracts when applying historical evidence to a current branch. The review/history corpora retain their own capture dates; they do not certify today's dispatch or numerical defaults. For kernel replacements, verify that the real model executes the…”
- name
- sglang-humanize-review
Files
SKILL.md and 6 other files (scripts, references) in skills/sglang-humanize-review of BBuf/AI-Infra-Auto-Driven-SKILLS.
- SKILL.md
- references/corpus-summary.md
- references/sglang-review-corpus.jsonl.gz
- references/sglang-review-corpus.metadata.json
- scripts/collect_sglang_review_corpus.py
- scripts/query_sglang_review_corpus.py
- scripts/summarize_sglang_review_corpus.py
Open the folder on GitHubat commit 6dc9c66
Compare with similar skills
SGLang Maintainer-Style Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| SGLang Maintainer-Style Review this skillBBuf/AI-Infra-Auto-Driven-SKILLS | 938 | — | ~4.6k | Automated safety check: Pass | None | |
| MAUI PR Performance Analysisdotnet/maui | 23k | — | ~2.4k | Automated safety check: Pass | MIT | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| PR Review State Fetchprisma/orm | 48k | — | ~767 | Automated safety check: Pass | Apache-2.0 | |
| PR Finalize Reviewmicrosoft/garnet | 12k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
- Official
GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
- Official
PR Review State Fetch
prisma/orm
Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.
- Official
PR Finalize Review
microsoft/garnet
Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.
Fastlane Pull Request Review
fastlane/fastlane
Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.
More from BBuf/AI-Infra-Auto-Driven-SKILLS
All 10 skills in this repoSGLang Model Day-0 Support
BBuf/AI-Infra-Auto-Driven-SKILLS
Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence.
LLM Serving Capacity Planner
BBuf/AI-Infra-Auto-Driven-SKILLS
Reads SGLang or vLLM startup logs to show where GPU memory went and estimates how many concurrent requests fit at common token lengths.
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
Model Architecture Diagram Finder
BBuf/AI-Infra-Auto-Driven-SKILLS
Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.
Model Compute Simulator
BBuf/AI-Infra-Auto-Driven-SKILLS
Builds an operator-level compute template for an LLM and estimates FLOPs and MFU for a serving shape, with tensor shapes and parallelism what-if checks.
Torch Profiler Layer Track
BBuf/AI-Infra-Auto-Driven-SKILLS
Adds verified layer guides such as L0 and L1 and compact GPU lanes to an existing Torch Profiler Chrome trace, changing how it looks but not how it ran.
Related
Categories
Questions about SGLang Maintainer-Style Review
What does SGLang Maintainer-Style Review do?
Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs. The skill reviews SGLang code using a bundled corpus of public pull request reviews from the sgl-project/sglang repository, from the first public PR through 2026-07-27. The corpus is organized as episodes: inline review threads with diff context, top-level PR conversation, and review submissions that keep their state, each with reviewer identity, original text and language, timestamps and multi-round replies.
When should I use SGLang Maintainer-Style Review?
SGLang Maintainer-Style Review fits situations like: reviewing an SGLang pull request in the style of its maintainers; checking a local SGLang patch for GPU, runtime and API compatibility risks; looking up how maintainers discussed a similar change in past reviews.
How do I install SGLang Maintainer-Style Review in Claude Code?
Run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a claude-code`. Or copy the skill folder (skills/sglang-humanize-review in BBuf/AI-Infra-Auto-Driven-SKILLS) into .claude/skills/sglang-humanize-review in your project. Claude Code loads it when a task matches its description.
How do I install SGLang Maintainer-Style Review in Codex?
Run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a codex`. Or copy the skill folder (skills/sglang-humanize-review in BBuf/AI-Infra-Auto-Driven-SKILLS) into .agents/skills/sglang-humanize-review in your project. Codex loads it when a task matches its description.
Can I use SGLang Maintainer-Style Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill sglang-humanize-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sglang-humanize-review, .gemini/skills/sglang-humanize-review, .github/skills/sglang-humanize-review and .opencode/skills/sglang-humanize-review in your project.
What does SGLang Maintainer-Style Review need to run?
Going by SKILL.md and its folder, SGLang Maintainer-Style Review needs Python for the scripts in its folder and the command-line tools its instructions call (python3, gh and git). Our summary lists: An SGLang diff, PR or local change to review; Python to run the bundled corpus query scripts; Network access to GitHub for reviews newer than the bundled corpus.
Does SGLang Maintainer-Style Review access the network?
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is SGLang Maintainer-Style Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does SGLang Maintainer-Style Review use?
No licence was found for SGLang Maintainer-Style Review or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does SGLang Maintainer-Style Review use?
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.8M tokens, read only when the agent opens those files.
What are the alternatives to SGLang Maintainer-Style Review?
Skills that share tags, products or a category with SGLang Maintainer-Style Review: MAUI PR Performance Analysis (dotnet/maui, 23k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), GitHub Review Iteration (prisma/orm, 48k stars) and PR Review State Fetch (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains SGLang Maintainer-Style Review?
BBuf (a GitHub user) maintains it in BBuf/AI-Infra-Auto-Driven-SKILLS, which has 938 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.
Source: BBuf/AI-Infra-Auto-Driven-SKILLS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.