Agent Framework
jihadkhawaja/Egroo
Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
Install Perfup
$ npx skills add raullenchai/Rapid-MLX --skill perfup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install raullenchai/Rapid-MLX perfup --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/raullenchai/Rapid-MLX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/perfup .claude/skills/perfup && 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 "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .claude/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfupType 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 raullenchai/Rapid-MLX --skill perfup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install raullenchai/Rapid-MLX perfup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raullenchai/Rapid-MLX.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/perfup .agents/skills/perfup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .agents/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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 raullenchai/Rapid-MLX --skill perfup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install raullenchai/Rapid-MLX perfup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raullenchai/Rapid-MLX.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/perfup .cursor/skills/perfup && 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 "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .cursor/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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/raullenchai/Rapid-MLX.git --path .claude/skills/perfup--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 raullenchai/Rapid-MLX --skill perfup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install raullenchai/Rapid-MLX perfup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raullenchai/Rapid-MLX.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/perfup .gemini/skills/perfup && 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 "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .gemini/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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 raullenchai/Rapid-MLX perfupInstalls 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 raullenchai/Rapid-MLX --skill perfup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/raullenchai/Rapid-MLX.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/perfup .github/skills/perfup && 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 "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .github/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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 raullenchai/Rapid-MLX --skill perfup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install raullenchai/Rapid-MLX perfup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/raullenchai/Rapid-MLX.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/perfup .opencode/skills/perfup && 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 "perfup" agent skill from https://github.com/raullenchai/Rapid-MLX/tree/main/.claude/skills/perfup into .opencode/skills/perfup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "perfup", 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
perfup- GitHub stars
- 3.9k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 635 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
- Works in 6 steps: Research → Prioritize → PoC Experiment Loop → …
- Tasks that involve LLM inference and serving
- SKILL.md covers Key Files, The 6 Phases, Results TSV Format and Focus Areas, plus 1 more section
- Calls gh and git
What it does
Perfup is an agent skill from raullenchai/Rapid-MLX. Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
Its SKILL.md is about 1.6k 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 AI & LLM Engineering, covering LLM inference and serving, Performance optimization and Pull requests. It works with Anthropic API, Model Context Protocol, Ollama and OpenAI. The repository describes itself as: Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding…
When your agent uses it
- Tasks that involve LLM inference and serving
- Tasks that involve Performance optimization
- Tasks that involve Pull requests
Example prompts
- “/perfup”
Requirements
- Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, Task, WebSearch, WebFetch, Skill, TaskCreate, TaskUpdate, TaskList, TaskGet, EnterPlanMode, ExitPlanMode, AskUserQuestion
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Research
- Prioritize
- PoC Experiment Loop
- Full Implementation
- Review Loop
- PR & Ship
What it can do on your machine
Read from SKILL.md and the folder at commit bf3f199. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteEditGlobGrepTaskWebSearchWebFetchSkill
…and 7 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
ghgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Perfup loads about 1.6k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 635 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Task, WebSearch, WebFetch, Skill, TaskCreate, TaskUpdate, TaskL
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 635 words (~1,644 tokens).
“Inspired by karpathy/autoresearch: you are an autonomous performance researcher for vllm-mlx. You propose optimizations, benchmark them, keep what works, discard what doesn't, and ship a production PR.”
- name
- perfup
- allowed-tools
- Bash, Read, Write, Edit, Glob, Grep, Task, WebSearch, WebFetch, Skill, TaskCreate, TaskUpdate, TaskList, TaskGet, EnterPlanMode, ExitPlanMode, AskUserQuestion
- disable-model-invocation
- true
Files
Just SKILL.md in .claude/skills/perfup of raullenchai/Rapid-MLX.
Open the folder on GitHubat commit bf3f199
Compare with similar skills
Perfup 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 |
|---|---|---|---|---|---|---|
| Perfup this skillraullenchai/Rapid-MLX | 3.9k | — | ~1.6k | Automated safety check: Notes | Custom licence | |
| Agent Frameworkjihadkhawaja/Egroo | 178 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Mesh APImr-tbot/mesh-api | 180 | — | ~1.8k | Automated safety check: Pass | GPL-3.0 | |
| Facturasgustavoeenriquez/MakerAi | 212 | — | ~127 | Automated safety check: Pass | MIT | |
| VllmPrism-Shadow/penguin-harness | 2.5k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Tanstack AIsecondsky/claude-skills | 227 | — | ~3.6k | Automated safety check: Notes | MIT |
Similar skills
Mesh API
mr-tbot/mesh-api
Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.
Facturas
gustavoeenriquez/MakerAi
Úsalo cuando el usuario pida redactar una factura, una cuenta de cobro o una nota de cobro.
Vllm
Prism-Shadow/penguin-harness
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
Tanstack AI
secondsky/claude-skills
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama.
Forkmind
ccplugins/awesome-claude-code-plugins
A skill your agent uses when debugging, comparing, or regression-testing LLM / agent calls — when the user wants to capture LLM traffic, see a conversation as a branchable DAG, fork an alternative…
Related
Categories
Questions about Perfup
What does Perfup do?
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR. Perfup is an agent skill from raullenchai/Rapid-MLX.
When should I use Perfup?
Perfup fits situations like: tasks that involve LLM inference and serving; tasks that involve Performance optimization; tasks that involve Pull requests.
How do I install Perfup in Claude Code?
Run `npx skills add raullenchai/Rapid-MLX --skill perfup -a claude-code`. Or copy the skill folder (.claude/skills/perfup in raullenchai/Rapid-MLX) into .claude/skills/perfup in your project. Claude Code loads it when a task matches its description.
How do I install Perfup in Codex?
Run `npx skills add raullenchai/Rapid-MLX --skill perfup -a codex`. Or copy the skill folder (.claude/skills/perfup in raullenchai/Rapid-MLX) into .agents/skills/perfup in your project. Codex loads it when a task matches its description.
Can I use Perfup 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 raullenchai/Rapid-MLX --skill perfup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/perfup, .gemini/skills/perfup, .github/skills/perfup and .opencode/skills/perfup in your project.
What does Perfup need to run?
Going by SKILL.md and its folder, Perfup needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Glob, Grep, Task, WebSearch, WebFetch, Skill, TaskCreate, TaskUpdate, TaskList, TaskGet, EnterPlanMode, ExitPlanMode, AskUserQuestion.
Does Perfup access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Perfup safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Perfup use?
Perfup has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Perfup use?
About 1.6k tokens (SKILL.md is roughly 6.6k 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 Perfup?
Skills that share tags, products or a category with Perfup: Agent Framework (jihadkhawaja/Egroo, 178 stars), Mesh API (mr-tbot/mesh-api, 180 stars), Facturas (gustavoeenriquez/MakerAi, 212 stars) and Vllm (Prism-Shadow/penguin-harness, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Perfup?
raullenchai (a GitHub user) maintains it in raullenchai/Rapid-MLX, which has 3,945 GitHub stars. The repository was last updated on October 9, 2026.
Source: raullenchai/Rapid-MLX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.