Agent skill

Aipc Toolkit

by qualcomm in qualcomm/qai-appbuilder

AIPC, AI Porting Conversion. An agent skill from qualcomm/qai-appbuilder.

Custom licenceAuto-check: notesAI & LLM Engineering

Install Aipc Toolkit

skills CLI
$ npx skills add qualcomm/qai-appbuilder --skill aipc-toolkit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qualcomm/qai-appbuilder aipc-toolkit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qualcomm/qai-appbuilder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/skills/qai-runner-skill .claude/skills/aipc-toolkit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
aipc-toolkit
GitHub stars
246
Token cost
~5.7k tokens
SKILL.md length
2,361 words
Files
56 (incl. scripts, references, assets)
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

AIPC, AI Porting Conversion. An agent skill from qualcomm/qai-appbuilder.

  • Works in 6 steps: NEVER create local files, folders, or… → ALWAYS run qai_project_setup.py — never… → Verify after the script: CLAUDE.md must… → …
  • Initializing an AIPC project
  • SKILL.md covers Trigger Phrases, When to Use, Required Guardrails and Quick Start, plus 3 more sections
  • Calls python, rsync and uv; reaches astral.sh

What it does

Aipc Toolkit is an agent skill from qualcomm/qai-appbuilder. AIPC, AI Porting Conversion. Tools and workflows for QAIRT/AIPC project setup, model conversion, inspection, operator patching, quantization, context-binary generation, and inference on Qualcomm platforms. Use this skill when creating or initializing an AIPC project, exporting AI models to ONNX, converting ONNX models to QNN or SNPE/DLC, converting models to FP16/FP32, patching unsupported operators, generating context binaries, or implementing inference for QNN/SNPE DLC.

Its SKILL.md is about 5.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 58 other files, including scripts, reference files and assets (for example `README.md`, `assets/plan.md` and `assets/qai_AGENTS.md`).

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with ONNX. The repository describes itself as: QAI AppBuilder is designed to help developers easily execute models on WoS and Linux platforms. It encapsulates the Qualcomm® AI Runtime SDK APIs into a set of simplified…

When your agent uses it

  • Initializing an AIPC project
  • Exporting AI models to ONNX
  • Converting ONNX models to QNN
  • Converting models to FP16/FP32

Example prompts

  • “/aipc-toolkit”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. NEVER create local files, folders, or scripts yourself. Do not write any project files manually or spawn agents to do so.
  2. ALWAYS run qai_project_setup.py — never write AGENTS.md, CLAUDE.md, or plan.md manually.
  3. Verify after the script: CLAUDE.md must be a symlink to AGENTS.md. Note: On Windows systems where symlink creation is restricted by local…
  4. Before auto-filling plan.md, inform the user that some Config values require their input (model name, target device, env script path…
  5. Then auto-fill derived and default values from the user's answers.
  6. Never shortcut: manual file creation produces an incomplete scaffold (missing CLAUDE.md, wrong template, no sentinel). The script is the…

What it can do on your machine

Read from SKILL.md and the folder at commit 700121f. 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 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • rsync
    • uv
    • ssh
    • python3
    • curl
    • sh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • astral.sh

    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

Aipc Toolkit loads about 5.7k tokens when it runs, and up to ~127k if it reads all its reference files. Until then it costs about 122 tokens; SKILL.md has 2,361 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~5.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~127k

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.

  • NotePipes a well-known installer script into a shellSKILL.md:99
    curl -LsSf https://astral.sh/uv/install.sh | sh   # install uv if not present

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,361 words (~5,690 tokens).

“Always activate this skill when the user mentions:”

— opening of SKILL.md by qualcomm, Custom licence
name
aipc-toolkit

Read the full SKILL.md on GitHub

Files

SKILL.md and 55 other files (scripts, references, assets) in tools/skills/qai-runner-skill of qualcomm/qai-appbuilder.

  • SKILL.md
  • README.md
  • README.md.bak
  • assets/plan.md
  • assets/qai_AGENTS.md
  • references/accuracy_checking.md
  • references/evolve.md
  • references/genie_llm_contract.md
  • references/host_context_binary_gen.md
  • references/inference.md
  • references/model-architectures/model_split.md
  • references/model-architectures/model_split.md.bak
  • references/model-architectures/multi_component_pipeline.md
  • references/model-architectures/multi_component_pipeline.md.bak
  • references/model_export_validation.md
  • references/model_quantization.md
  • references/model_quantization_aimet.md
  • references/on_device_context_binary.md
  • … and 38 more

Open the folder on GitHubat commit 700121f

Compare with similar skills

Aipc Toolkit 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.

Aipc Toolkit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aipc Toolkit this skillqualcomm/qai-appbuilder246—~5.7kAutomated safety check: NotesCustom licence
Quark Torch Quant Perfamd/Quark181—~3kAutomated safety check: PassMIT
Quark Onnx Autosearch Proamd/Quark181—~3.4kAutomated safety check: PassMIT
Quark Onnx Quant Planamd/Quark181—~4.8kAutomated safety check: PassMIT
Quark Onnx Result Validatoramd/Quark181—~2.5kAutomated safety check: PassMIT
Quark Onnx Routeramd/Quark181—~2.7kAutomated safety check: PassMIT

Similar skills

  • Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

    181 GitHub stars~3k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • L3 recipe that runs quark.onnx.AutoSearchPro end-to-end on a user .onnx model: intake → preset selection (or custom search space) → calibration / eval data reader → standalone autosearch script…

    181 GitHub stars~3.4k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • Build a Quark ONNX PTQ quantization plan from modelanalysis.json and user intent.

    181 GitHub stars~4.8k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • Validate Quark ONNX quantization output using four lightweight checks: auxiliary file copy alignment, expected non-quantized initializer MD5 byte-identity (inline rawdata + external-data byte…

    181 GitHub stars~2.5k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • Route Quark ONNX user goals to the correct atomic skill. An agent skill from amd/Quark.

    181 GitHub stars~2.7k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • Detect upstream Quark ONNX changes that affect the ONNX skill family and classify required updates.

    181 GitHub stars~3.3k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

More from qualcomm/qai-appbuilder

All 13 skills in this repo
  • Model Hub

    qualcomm/qai-appbuilder

    Model Hub — download pre-exported models from Qualcomm AI Hub, run inference on-device, and export them to App Builder as ready-to-import Packs.

    246 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Model Builder

    qualcomm/qai-appbuilder

    QAI ModelBuilder. An agent skill from qualcomm/qai-appbuilder.

    246 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • App Builder

    qualcomm/qai-appbuilder

    App Builder — generate complete, runnable fullstack WebUI applications (FastAPI backend + pure HTML/CSS/JS frontend) around on-device AI Model Packs (OCR, TTS, ASR, Super-Resolution, etc.).

    246 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Ppt Gen

    qualcomm/qai-appbuilder

    Generate fully editable, high-quality PPTX with python-pptx based on the user's topic, materials, or business goals; defaults to a general-purpose "dark gilded elegant" visual system, with adaptive…

    246 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Read Arxiv Paper

    qualcomm/qai-appbuilder

    Fetch and summarize academic papers from arxiv.org. An agent skill from qualcomm/qai-appbuilder.

    246 GitHub stars~308 tokensUpdated yesterday
    Auto-check passed
  • Browser Automation

    qualcomm/qai-appbuilder

    A skill your agent uses when working with the browser tool — navigating or inspecting a page, clicking through a flow, filling and submitting a form, acting inside a logged-in session, or…

    246 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Aipc Toolkit

What does Aipc Toolkit do?

AIPC, AI Porting Conversion. An agent skill from qualcomm/qai-appbuilder. Aipc Toolkit is an agent skill from qualcomm/qai-appbuilder. AIPC, AI Porting Conversion.

When should I use Aipc Toolkit?

Aipc Toolkit fits situations like: initializing an AIPC project; exporting AI models to ONNX; converting ONNX models to QNN; converting models to FP16/FP32.

How do I install Aipc Toolkit in Claude Code?

Run `npx skills add qualcomm/qai-appbuilder --skill aipc-toolkit -a claude-code`. Or copy the skill folder (tools/skills/qai-runner-skill in qualcomm/qai-appbuilder) into .claude/skills/aipc-toolkit in your project. Claude Code loads it when a task matches its description.

How do I install Aipc Toolkit in Codex?

Run `npx skills add qualcomm/qai-appbuilder --skill aipc-toolkit -a codex`. Or copy the skill folder (tools/skills/qai-runner-skill in qualcomm/qai-appbuilder) into .agents/skills/aipc-toolkit in your project. Codex loads it when a task matches its description.

Can I use Aipc Toolkit 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 qualcomm/qai-appbuilder --skill aipc-toolkit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aipc-toolkit, .gemini/skills/aipc-toolkit, .github/skills/aipc-toolkit and .opencode/skills/aipc-toolkit in your project.

What does Aipc Toolkit need to run?

Going by SKILL.md and its folder, Aipc Toolkit needs the command-line tools its instructions call (python, rsync, uv, ssh, python3 and curl). Our summary lists: Python 3.

Does Aipc Toolkit access the network?

SKILL.md names 1 domain. In commands or code: astral.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Aipc Toolkit safe to install?

Our automated static check of SKILL.md found notes only (pipes a well-known installer script into a shell), nothing it rates as a warning. 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 Aipc Toolkit use?

Aipc Toolkit 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 Aipc Toolkit use?

About 5.7k tokens (SKILL.md is roughly 23k 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 122k tokens, read only when the agent opens those files.

What are the alternatives to Aipc Toolkit?

Skills that share tags, products or a category with Aipc Toolkit: Quark Torch Quant Perf (amd/Quark, 181 stars), Quark Onnx Autosearch Pro (amd/Quark, 181 stars), Quark Onnx Quant Plan (amd/Quark, 181 stars) and Quark Onnx Result Validator (amd/Quark, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aipc Toolkit?

qualcomm (a GitHub organization) maintains it in qualcomm/qai-appbuilder, which has 246 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.

Source: qualcomm/qai-appbuilder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.