New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prevent Triton Ascend Ub Overflow

by Krusty84 in Krusty84/triton-ascend-agent-dev-kit

Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Prevent Triton Ascend Ub Overflow

skills CLI
$ npx skills add Krusty84/triton-ascend-agent-dev-kit --skill prevent-triton-ascend-ub-overflow -a claude-code

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

GitHub CLI
$ gh skill install Krusty84/triton-ascend-agent-dev-kit prevent-triton-ascend-ub-overflow --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/Krusty84/triton-ascend-agent-dev-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prevent-triton-ascend-ub-overflow .claude/skills/prevent-triton-ascend-ub-overflow && 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
prevent-triton-ascend-ub-overflow
GitHub stars
106
Token cost
~558 tokens
SKILL.md length
195 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
Apache-2.0

At a glance

Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations.

  • Works in 5 steps: List all simultaneously live tensors and… → Select a BLOCK_SIZE that fits the UB… → Replace one load over the maximum… → …
  • An agent ports a GPU kernel that loads a long sequence
  • SKILL.md covers Goal, Workflow, Implementation Pattern and Ascend Guardrails, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prevent Triton Ascend Ub Overflow is an agent skill from Krusty84/triton-ascend-agent-dev-kit. Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations. Use when an agent ports a GPU kernel that loads a long sequence or metadata array at once, compilation reports UB pressure, or runtime shapes such as KV-page allocation exceed safe on-chip capacity.

Its SKILL.md is about 560 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. The repository describes itself as: A toolkit for AI agents used for development on Triton-Ascend for Ascend NPU. The licence is Apache-2.0.

When your agent uses it

  • An agent ports a GPU kernel that loads a long sequence
  • Metadata array at once
  • Compilation reports UB pressure
  • Runtime shapes such as KV-page allocation exceed safe on-chip capacity

Example prompts

  • “/prevent-triton-ascend-ub-overflow”

Requirements

  • Python 3

Workflow steps

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

  1. List all simultaneously live tensors and estimate their bytes, including padding and multibuffer copies.
  2. Select a BLOCK_SIZE that fits the UB budget with safety margin.
  3. Replace one load over the maximum logical length with a compile-time loop over BLOCK_SIZE tiles.
  4. Recompute global offsets from the loop index and apply a runtime validity mask.
  5. Store each completed tile before advancing so earlier tiles do not remain live.

What it can do on your machine

Read from SKILL.md and the folder at commit 4ab5ee7. 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 (its code samples are python).

    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

Prevent Triton Ascend Ub Overflow loads about 558 tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 195 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~558

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 Krusty84/triton-ascend-agent-dev-kit at commit 4ab5ee7, republished under its Apache-2.0 licence (© Krusty84). 195 words, ~558 tokens.

Download SKILL.mdSave it as .claude/skills/prevent-triton-ascend-ub-overflow/SKILL.md (or your agent's skills folder).
name
prevent-triton-ascend-ub-overflow
description
Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations. Use when an agent ports a GPU kernel that loads a long sequence or metadata array at once, compilation reports UB pressure, or runtime shapes such as KV-page allocation exceed safe on-chip capacity.

Prevent Triton-Ascend UB Overflow

Goal

Keep each live tile within Ascend UB while preserving the semantics of a larger logical operation.

Workflow

  1. List all simultaneously live tensors and estimate their bytes, including padding and multibuffer copies.
  2. Select a BLOCK_SIZE that fits the UB budget with safety margin.
  3. Replace one load over the maximum logical length with a compile-time loop over BLOCK_SIZE tiles.
  4. Recompute global offsets from the loop index and apply a runtime validity mask.
  5. Store each completed tile before advancing so earlier tiles do not remain live.

Implementation Pattern

python
block_offsets = tl.arange(0, BLOCK_SIZE)
num_loops = tl.cdiv(MAX_EXTEND_TOKENS, BLOCK_SIZE)

for i in range(num_loops):
    token_offsets = i * BLOCK_SIZE + block_offsets
    mask = token_offsets < valid_tokens
    pages = tl.load(
        free_pages + page_start + token_offsets // page_size,
        mask=mask,
    )
    slots = pages * page_size + token_offsets % page_size
    tl.store(output + output_start + token_offsets, slots, mask=mask)

Ascend Guardrails

  • Base BLOCK_SIZE on bytes of all live values, not only the primary input.
  • Account for 32-byte padding, float32 promotions, temporary results, and multibuffering.
  • Keep MAX_EXTEND_TOKENS a compile-time upper bound and valid_tokens the runtime limit.
  • Apply the same tail condition to every load and store.
  • Avoid retaining a full logical result in a tl.zeros tensor after tiling; stream completed outputs to global memory.
  • Re-evaluate the budget whenever dtype, tile rank, or compiler options change.

Verification

Test valid lengths around BLOCK_SIZE boundaries and the maximum supported length. Compare with the untiled reference and profile memory/compiler behavior for progressively larger inputs.

© Krusty84, Apache-2.0. 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 skills/prevent-triton-ascend-ub-overflow of Krusty84/triton-ascend-agent-dev-kit.

Open the folder on GitHubat commit 4ab5ee7

Compare with similar skills

Prevent Triton Ascend Ub Overflow 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.

Prevent Triton Ascend Ub Overflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prevent Triton Ascend Ub Overflow this skillKrusty84/triton-ascend-agent-dev-kit106—~558Automated safety check: PassApache-2.0
Agent BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.9k14 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.9k GitHub starsUsed in 14 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • Planning With Files

    jarrodwatts/claude-code-config

    Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

    1.1k GitHub starsUsed in 5 repos~967 tokens
    AI & LLM EngineeringAuto-check passed

More from Krusty84/triton-ascend-agent-dev-kit

All 23 skills in this repo

  • Triton-Ascend Token Pool Assignment

    Krusty84/triton-ascend-agent-dev-kit

    Implements request-to-token-pool copies for Triton kernels on Ascend NPUs, replacing loop-carried vector offsets with fixed-offset block loops that compile reliably.

    106 GitHub stars~564 tokensUpdated 1 mo ago
    Auto-check passed

  • Triton-Ascend Batch Token Reorder

    Krusty84/triton-ascend-agent-dev-kit

    Writes a Triton kernel pattern for Ascend NPU that gathers several indexed token rows per program into an on-chip buffer and stores one contiguous output tile, for MoE-style token reordering.

    106 GitHub stars~597 tokensUpdated 1 mo ago
    Auto-check passed

  • Triton-Ascend Binned MoE Routing

    Krusty84/triton-ascend-agent-dev-kit

    Builds Triton-Ascend kernels that pack sorted token assignments into fixed expert-capacity tensors, restore top-k outputs and compute router-weight gradients on Ascend NPUs.

    106 GitHub stars~662 tokensUpdated 1 mo ago
    Auto-check passed

  • Triton-Ascend Fused Attention

    Krusty84/triton-ascend-agent-dev-kit

    Guides building a FlashAttention-v2-style fused forward attention kernel for Triton-Ascend on Ascend NPU, with online softmax, causal staging and float32 accumulation.

    106 GitHub stars~753 tokensUpdated 1 mo ago
    Auto-check passed

  • Triton-Ascend Fused Softmax

    Krusty84/triton-ascend-agent-dev-kit

    Builds a fused row-wise softmax kernel for Triton-Ascend that reads and writes each row once, handling padding, strides and masked loads on Ascend NPUs.

    106 GitHub stars~636 tokensUpdated 1 mo ago
    Auto-check passed

  • Build Triton Ascend Layer Norm

    Krusty84/triton-ascend-agent-dev-kit

    Build a fused forward LayerNorm kernel for Triton-Ascend with row-wise mean and variance reductions, float32 accumulation, affine weight and bias, and masked feature tiles.

    106 GitHub stars~659 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Prevent Triton Ascend Ub Overflow

What does Prevent Triton Ascend Ub Overflow do?

Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations. Prevent Triton Ascend Ub Overflow is an agent skill from Krusty84/triton-ascend-agent-dev-kit. Prevent Triton-Ascend Unified Buffer overflow by streaming large logical vectors through bounded compile-time tiles with masked loop iterations.

When should I use Prevent Triton Ascend Ub Overflow?

Prevent Triton Ascend Ub Overflow fits situations like: an agent ports a GPU kernel that loads a long sequence; metadata array at once; compilation reports UB pressure; runtime shapes such as KV-page allocation exceed safe on-chip capacity.

How do I install Prevent Triton Ascend Ub Overflow in Claude Code?

Run `npx skills add Krusty84/triton-ascend-agent-dev-kit --skill prevent-triton-ascend-ub-overflow -a claude-code`. Or copy the skill folder (skills/prevent-triton-ascend-ub-overflow in Krusty84/triton-ascend-agent-dev-kit) into .claude/skills/prevent-triton-ascend-ub-overflow in your project. Claude Code loads it when a task matches its description.

How do I install Prevent Triton Ascend Ub Overflow in Codex?

Run `npx skills add Krusty84/triton-ascend-agent-dev-kit --skill prevent-triton-ascend-ub-overflow -a codex`. Or copy the skill folder (skills/prevent-triton-ascend-ub-overflow in Krusty84/triton-ascend-agent-dev-kit) into .agents/skills/prevent-triton-ascend-ub-overflow in your project. Codex loads it when a task matches its description.

Can I use Prevent Triton Ascend Ub Overflow 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 Krusty84/triton-ascend-agent-dev-kit --skill prevent-triton-ascend-ub-overflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prevent-triton-ascend-ub-overflow, .gemini/skills/prevent-triton-ascend-ub-overflow, .github/skills/prevent-triton-ascend-ub-overflow and .opencode/skills/prevent-triton-ascend-ub-overflow in your project.

What does Prevent Triton Ascend Ub Overflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Prevent Triton Ascend Ub Overflow is instructions for the agent only. Our summary lists: Python 3.

Does Prevent Triton Ascend Ub Overflow 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 Prevent Triton Ascend Ub Overflow 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 Prevent Triton Ascend Ub Overflow use?

Prevent Triton Ascend Ub Overflow is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prevent Triton Ascend Ub Overflow use?

About 558 tokens (SKILL.md is roughly 2.2k 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 Prevent Triton Ascend Ub Overflow?

Skills that share tags, products or a category with Prevent Triton Ascend Ub Overflow: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prevent Triton Ascend Ub Overflow?

Krusty84 (a GitHub user) maintains it in Krusty84/triton-ascend-agent-dev-kit, which has 106 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on August 15, 2026.

Source: Krusty84/triton-ascend-agent-dev-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.