LLM Pipeline Profiler Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.
Performance optimization guidelines for Splitrail. An agent skill from Piebald-AI/splitrail.
Install Performance
$ npx skills add Piebald-AI/splitrail --skill performance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Piebald-AI/splitrail performance --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/Piebald-AI/splitrail.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/performance .claude/skills/performance && 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 "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .claude/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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/Piebald-AI/splitrail/tree/main/.claude/skills/performanceType 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 Piebald-AI/splitrail --skill performance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Piebald-AI/splitrail performance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Piebald-AI/splitrail.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/performance .agents/skills/performance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .agents/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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 Piebald-AI/splitrail --skill performance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Piebald-AI/splitrail performance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Piebald-AI/splitrail.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/performance .cursor/skills/performance && 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 "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .cursor/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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/Piebald-AI/splitrail.git --path .claude/skills/performance--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 Piebald-AI/splitrail --skill performance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Piebald-AI/splitrail performance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Piebald-AI/splitrail.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/performance .gemini/skills/performance && 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 "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .gemini/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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 Piebald-AI/splitrail performanceInstalls 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 Piebald-AI/splitrail --skill performance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Piebald-AI/splitrail.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/performance .github/skills/performance && 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 "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .github/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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 Piebald-AI/splitrail --skill performance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Piebald-AI/splitrail performance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Piebald-AI/splitrail.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/performance .opencode/skills/performance && 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 "performance" agent skill from https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/performance into .opencode/skills/performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance", 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
performance- GitHub stars
- 222
- Token cost
- ~245 tokens
- SKILL.md length
- 100 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Performance optimization guidelines for Splitrail. An agent skill from Piebald-AI/splitrail.
- Works in 4 steps: Prefer parallel processing for I/O-bound… → Use parking_lot locks over std::sync for… → Avoid loading all messages into memory… → …
- Optimizing parsing
- SKILL.md covers Techniques Used and Guidelines
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Performance is an agent skill from Piebald-AI/splitrail. Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Its SKILL.md is about 250 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Performance optimization. It works with Qwen. The repository describes itself as: Fast, cross-platform, real-time token usage tracker and cost monitor for Claude Code / Codex CLI / Antigravity CLI / Qwen Code / Cline / Zoo Code / Kilo Code / GitHub Copilot /… The licence is MIT.
When your agent uses it
- Optimizing parsing
- Reducing memory usage
- Improving throughput
Example prompts
- “/performance”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Prefer parallel processing for I/O-bound operations
- Use parking_lot locks over std::sync for better performance
- Avoid loading all messages into memory when not needed
- Use BTreeMap for date-ordered data (sorted iteration)
What it can do on your machine
Read from SKILL.md and the folder at commit d9cbe50. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Performance loads about 245 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 100 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from Piebald-AI/splitrail at commit d9cbe50, republished under its MIT licence (© Piebald-AI). 100 words, ~245 tokens.
Download SKILL.mdSave it as
.claude/skills/performance/SKILL.md (or your agent's skills folder).- name
- performance
- description
- Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Performance Considerations
Techniques Used
- Parallel analyzer loading -
futures::join_all()for concurrent stats loading - Parallel file parsing -
rayonfor parallel iteration over files - Fast JSON parsing -
simd_jsonexclusively for all JSON operations (note:rmcpcrate re-exportsserde_jsonfor MCP server types) - Fast directory walking -
jwalkfor parallel directory traversal - Lazy message loading - TUI loads messages on-demand for session view
See existing analyzers in src/analyzers/ for usage patterns.
Guidelines
- Prefer parallel processing for I/O-bound operations
- Use
parking_lotlocks overstd::syncfor better performance - Avoid loading all messages into memory when not needed
- Use
BTreeMapfor date-ordered data (sorted iteration)
© Piebald-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/performance of Piebald-AI/splitrail.
Open the folder on GitHubat commit d9cbe50
Compare with similar skills
Performance 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 |
|---|---|---|---|---|---|---|
| Performance this skillPiebald-AI/splitrail | 222 | — | ~245 | Automated safety check: Pass | MIT | |
| LLM Pipeline Profiler AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 911 | — | ~3.9k | Automated safety check: Pass | None | |
| Diffusion Perf Optvllm-project/vllm-omni | 7.1k | — | ~7.5k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Agent Feature ReproductionQwenLM/qwen-code | 28k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Diffusion Perf Opt
vllm-project/vllm-omni
Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Agent Feature Reproduction
QwenLM/qwen-code
Reproduces a feature from Codex or Claude Code in Qwen Code by running the reference agent under capture, reading the traces, then implementing matching behavior.
Py
crazyguitar/pysheeet
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC.
More from Piebald-AI/splitrail
MCP
Piebald-AI/splitrail
Guide for working with Splitrail's MCP server. An agent skill from Piebald-AI/splitrail.
Pricing
Piebald-AI/splitrail
Guide for updating model pricing in Splitrail. An agent skill from Piebald-AI/splitrail.
New Analyzer
Piebald-AI/splitrail
Guide for adding a new AI coding agent analyzer to Splitrail.
Tui
Piebald-AI/splitrail
Guide for Splitrail's terminal UI and file watching. An agent skill from Piebald-AI/splitrail.
Types
Piebald-AI/splitrail
Reference for Splitrail's core data types. An agent skill from Piebald-AI/splitrail.
Related
Works with
Categories
Questions about Performance
What does Performance do?
Performance optimization guidelines for Splitrail. An agent skill from Piebald-AI/splitrail. Performance is an agent skill from Piebald-AI/splitrail. Performance optimization guidelines for Splitrail.
When should I use Performance?
Performance fits situations like: optimizing parsing; reducing memory usage; improving throughput.
How do I install Performance in Claude Code?
Run `npx skills add Piebald-AI/splitrail --skill performance -a claude-code`. Or copy the skill folder (.claude/skills/performance in Piebald-AI/splitrail) into .claude/skills/performance in your project. Claude Code loads it when a task matches its description.
How do I install Performance in Codex?
Run `npx skills add Piebald-AI/splitrail --skill performance -a codex`. Or copy the skill folder (.claude/skills/performance in Piebald-AI/splitrail) into .agents/skills/performance in your project. Codex loads it when a task matches its description.
Can I use Performance 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 Piebald-AI/splitrail --skill performance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performance, .gemini/skills/performance, .github/skills/performance and .opencode/skills/performance in your project.
What does Performance need to run?
SKILL.md names no scripts, command-line tools or credentials: Performance is instructions for the agent only.
Does Performance access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Performance 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. Review the folder before installing.
What licence does Performance use?
Performance is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Performance use?
About 245 tokens (SKILL.md is roughly 980 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Performance?
Skills that share tags, products or a category with Performance: LLM Pipeline Profiler Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 911 stars), Diffusion Perf Opt (vllm-project/vllm-omni, 7.1k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars) and LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Performance?
Piebald-AI (a GitHub organization) maintains it in Piebald-AI/splitrail, which has 222 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.
Source: Piebald-AI/splitrail on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.