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

Rank Triton Ascend Costmodel

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

Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Rank Triton Ascend Costmodel

skills CLI
$ npx skills add Krusty84/triton-ascend-agent-dev-kit --skill rank-triton-ascend-costmodel -a claude-code

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

GitHub CLI
$ gh skill install Krusty84/triton-ascend-agent-dev-kit rank-triton-ascend-costmodel --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/rank-triton-ascend-costmodel .claude/skills/rank-triton-ascend-costmodel && 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
rank-triton-ascend-costmodel
GitHub stars
106
Token cost
~721 tokens
SKILL.md length
221 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning.

  • Works in 6 steps: Define the Triton kernel,… → Build a separate ASTSource and TTIR… → Enable the costmodel backend in Ascend… → …
  • An agent needs to prefilter a large configuration space
  • 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

Rank Triton Ascend Costmodel is an agent skill from Krusty84/triton-ascend-agent-dev-kit. Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning. Use when an agent needs to prefilter a large configuration space, construct costmodelbench items, bind runtime TTIR arguments or program IDs, or interpret predicted latency values.

Its SKILL.md is about 720 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 needs to prefilter a large configuration space
  • Construct costmodelbench items
  • Bind runtime TTIR arguments
  • Interpret predicted latency values

Example prompts

  • “/rank-triton-ascend-costmodel”

Requirements

  • Python 3

Workflow steps

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

  1. Define the Triton kernel, pointer/runtime signature, and candidate constexpr values.
  2. Build a separate ASTSource and TTIR string for every candidate.
  3. Enable the costmodel backend in Ascend compiler options.
  4. Create one item per candidate with a unique config name, TTIR, and optional arg_bindings.
  5. Call costmodel_bench, sort the returned microsecond predictions, and shortlist candidates.
  6. Verify and benchmark the shortlist on real NPU inputs.

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

Rank Triton Ascend Costmodel loads about 721 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 221 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~721

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). 221 words, ~721 tokens.

Download SKILL.mdSave it as .claude/skills/rank-triton-ascend-costmodel/SKILL.md (or your agent's skills folder).
name
rank-triton-ascend-costmodel
description
Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning. Use when an agent needs to prefilter a large configuration space, construct costmodel_bench items, bind runtime TTIR arguments or program IDs, or interpret predicted latency values.

Rank Triton-Ascend Configs with Costmodel

Goal

Predict latency for several compile-time kernel configurations and retain the most promising candidates for real correctness checks and benchmarking.

Workflow

  1. Define the Triton kernel, pointer/runtime signature, and candidate constexpr values.
  2. Build a separate ASTSource and TTIR string for every candidate.
  3. Enable the costmodel backend in Ascend compiler options.
  4. Create one item per candidate with a unique config name, TTIR, and optional arg_bindings.
  5. Call costmodel_bench, sort the returned microsecond predictions, and shortlist candidates.
  6. Verify and benchmark the shortlist on real NPU inputs.

Implementation Pattern

python
from triton.backends.ascend.runtime.costmodel_runtime import costmodel_bench
from triton.backends.compiler import GPUTarget
from triton.compiler import ASTSource
from triton.compiler.code_generator import ast_to_ttir
from triton.compiler.compiler import make_backend
from triton._C.libtriton import ir
from triton._C.libtriton.ascend import ir as ascend_ir

source = ASTSource(kernel, signature, constants, attrs=None)
backend = make_backend(GPUTarget("npu", "", 32))
options = backend.parse_options({
    "compile_mode": "simd",
    "enable_costmodel_backend": True,
    **source.parse_options(),
})
context = ir.context()
ir.load_dialects(context)
ascend_ir.load_dialects(context)
ttir = str(ast_to_ttir(kernel, source, context, options, {}, {}))

items = [{
    "config": "block256",
    "ttir": ttir,
    "arg_bindings": "arg3=98432,pid_x=0",
}]
latencies_us = costmodel_bench(items)

Ascend Guardrails

  • Exclude constexpr parameters from the runtime signature and pass their values through ASTSource constants.
  • Regenerate TTIR for every constexpr configuration; changing only the item name does not change the compiled program.
  • Map argN by the insertion order of runtime arguments in signature. Recheck the index whenever the signature changes.
  • Bind pid_x when the kernel uses tl.program_id(0), and bind num_programs_x when it uses tl.num_programs(0).
  • Use unique config names because they become keys in the returned dictionary.
  • Treat predicted latency as a ranking signal, not proof of correctness or measured hardware performance.

Verification

Assert that every requested config has a finite returned latency, sort ascending, and compare the top candidates with actual NPU benchmarks. Keep a slower predicted candidate when needed to detect costmodel ranking errors.

© 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/rank-triton-ascend-costmodel of Krusty84/triton-ascend-agent-dev-kit.

Open the folder on GitHubat commit 4ab5ee7

Compare with similar skills

Rank Triton Ascend Costmodel 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.

Rank Triton Ascend Costmodel compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rank Triton Ascend Costmodel this skillKrusty84/triton-ascend-agent-dev-kit106—~721Automated 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 Rank Triton Ascend Costmodel

What does Rank Triton Ascend Costmodel do?

Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning. Rank Triton Ascend Costmodel is an agent skill from Krusty84/triton-ascend-agent-dev-kit. Generate TTIR for Triton-Ascend kernel configurations and rank them with the Ascend costmodel backend before empirical autotuning.

When should I use Rank Triton Ascend Costmodel?

Rank Triton Ascend Costmodel fits situations like: an agent needs to prefilter a large configuration space; construct costmodelbench items; bind runtime TTIR arguments; interpret predicted latency values.

How do I install Rank Triton Ascend Costmodel in Claude Code?

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

How do I install Rank Triton Ascend Costmodel in Codex?

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

Can I use Rank Triton Ascend Costmodel 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 rank-triton-ascend-costmodel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rank-triton-ascend-costmodel, .gemini/skills/rank-triton-ascend-costmodel, .github/skills/rank-triton-ascend-costmodel and .opencode/skills/rank-triton-ascend-costmodel in your project.

What does Rank Triton Ascend Costmodel need to run?

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

Does Rank Triton Ascend Costmodel 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 Rank Triton Ascend Costmodel 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 Rank Triton Ascend Costmodel use?

Rank Triton Ascend Costmodel 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 Rank Triton Ascend Costmodel use?

About 721 tokens (SKILL.md is roughly 2.9k 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 Rank Triton Ascend Costmodel?

Skills that share tags, products or a category with Rank Triton Ascend Costmodel: 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 Rank Triton Ascend Costmodel?

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.