Skip to content
Agentmart
Submit a tool

ascend-npu-run-eval

Execute and evaluate generated operator artifacts.

Skill by Piagari

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying ascend-npu-run-eval?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/piagari-ascend-npu-run-eval-a08a06

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Execute and evaluate generated operator artifacts. Use when you need to run generated test cases, run generated benchmark cases, fast-screen a candidate operator against a baseline, profile benchmark harnesses, summarize profiling data, or compare performance artifacts, including during optimization workflows.

Use cases: testing, data

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ascend-npu-run-eval

What's inside

Skill name
ascend-npu-run-eval
Description
Execute and evaluate generated operator artifacts. Use when you need to run generated test cases, run generated benchmark cases, fast-screen a candidate operator against a baseline, profile benchmark harnesses, summarize profiling data, or compare performance artifacts, including during optimization workflows.
License
Apache-2.0
Instructions
28 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (29)

  • SKILL.md
  • compare-perf.md · references/
  • probe-bench.md · references/
  • profile-bench.md · references/
  • profile-report.md · references/
  • run-bench.md · references/
  • run-test.md · references/
  • bench_contract.py · scripts/
  • bench_runner.py · scripts/
  • bench_runtime.py · scripts/
  • cli.py · scripts/
  • compare_result.py · scripts/
  • debug_device.py · scripts/
  • dtype_close_compare.py · scripts/
  • env_registry.py · scripts/
  • npu_affinity.py · scripts/
  • npu_compare.py · scripts/
  • npu_compare_common.py · scripts/
  • npu_contract_compare.py · scripts/
  • perf_artifacts.py · scripts/
  • probe_runner.py · scripts/
  • profile_csv_parser.py · scripts/
  • profile_runner.py · scripts/
  • remote_execution_env.py · scripts/
  • result_payload.py · scripts/
  • run_runtime.py · scripts/
  • simulator_runner.py · scripts/
  • test_runner.py · scripts/
  • torch_npu_warnings.py · scripts/

SKILL.md (first lines)

# Run-Eval Router

Use the bundled helper script in this skill. Treat
`<ascend-npu-run-eval-skill-path>` as the staged path to the
`ascend-npu-run-eval` skill for the active backend:

```bash
python3 <ascend-npu-run-eval-skill-path>/scripts/cli.py <subcommand> ...
```

For `probe-bench`, use the surface that actually exposes that subcommand in the current workspace. If the staged `cli.py` in this skill has not been updated yet, use the workspace's public `helix probe-bench` command instead of guessing helper internals.

Read only the focused guide for the subcommand you are about to run:

- `run-test-baseline` / `run-test-convert` / `run-test-optimize`: [references/run-test.md](references/run-test.md)
- `run-bench`: [references/run-bench.md](references/run-bench.md)
- `probe-bench`: [references/probe-bench.md](references/probe-bench.md)
- `profile-bench`: [references/profile-bench.md](references/profile-bench.md)
- `profile-report`: [references/profile-report.md](references/profile-report.md)
- `compare-perf`: [references/compare-perf.md](references/compare-perf.md)

During normal use:

- call `python3 <ascend-npu-run-eval-skill-path>/scripts/cli.py <subcommand> ...` directly
- do not read unrelated command guides
- do not reread Python files under `<ascend-npu-run-eval-skill-path>/scripts/` unless you need to debug, patch, or verify helper behavior

From Piagari/helix, Apache-2.0.

More from Piagari/helix

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 16, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Piagari/helix
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Piagari

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ascend-npu-run-eval running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ascend-npu-run-eval?

CallGet help
Cite this page

ascend-npu-run-eval skill. Agent Mart. https://agentmart.dev/skills/piagari-ascend-npu-run-eval-a08a06 (last updated 2026-10-24)