원클릭으로 Manus에서 모든 스킬 실행

시작하기

tt-bug-report

스타330

포크50

업데이트2026년 3월 31일 16:27

File a bug report with a reproducer against Tenstorrent repos (tt-lang, tt-metal, tt-xla)

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

tenstorrent

tenstorrent/tt-forge

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Task

File a bug report for a Tenstorrent issue. Gather context, minimize the reproducer, and create a GitHub issue in the right repo.

Where to File

Component	Repo
TT-Lang (DSL, compiler, kernels)	`tenstorrent/tt-lang`
TTNN (ops, tensor APIs, device)	`tenstorrent/tt-metal`
TT-Metal (low-level C++ kernels)	`tenstorrent/tt-metal`
TT-XLA (PyTorch/JAX frontend)	`tenstorrent/tt-xla`

If it's unclear which repo the bug belongs to, ask the user.

Input

$ARGUMENTS

Process

Step 1: Describe the Problem

Determine the type of issue and gather relevant info:

For crashes or incorrect results:

A reproducer script (even a non-minimal one is valuable)
Actual vs expected output

For compiler errors (tt-lang):

The full error message
Compiler flags used
MLIR before and after passes (/tmp/ttlang_initial.mlir, /tmp/ttlang_final.mlir)
Any other context that seems relevant

Step 2: Minimize the Reproducer

Ask the user if it's OK to upload the reproducer to the issue and spend some iterations trying to minimize it. If they agree, try to reduce it to the smallest script that still triggers the bug. Any reproducer is better than none -- if you can't minimize further, use what you have.

Step 3: File the Issue

Use gh to create an issue in the appropriate repo:

gh issue create --repo <owner/repo> \
  --title "[external bug report][from claude] <short title>" \
  --body "$(cat <<'EOF'
<body>
EOF
)"

The body should include:

Description of the problem
Reproducer (if available)
Error output / MLIR snippets (if applicable)
Environment context (simulator vs HW, etc.)

Output

Return the issue URL to the user.

이 저장소의 다른 Skills

같은 저장소

tt-connect-remote-device

tenstorrent/tt-forge

Set up and verify remote connection to Tenstorrent hardware. Provides tools for running kernels, copying files, and reading logs on remote devices.

2026-03-31330

tt-enable-tracing

tenstorrent/tt-forge

TTNN trace capture and replay for eliminating dispatch overhead. Essential for real-time inference and multi-chip performance.

2026-03-31330

tt-lang-profile-optimize

tenstorrent/tt-forge

Profile and optimize TT-Lang kernels for performance. Covers auto-profiling, perf summary, signposts, and optimization workflow.

2026-03-31330

tt-lang

tenstorrent/tt-forge

Comprehensive TT-Lang DSL reference including programming model, APIs, hardware constraints, and guides for translating CUDA, Triton, PyTorch, or TTNN kernels

2026-03-31330

ttnn

tenstorrent/tt-forge

TTNN operations library reference for Tenstorrent hardware. Covers tensor APIs, ops catalog, model conversion from PyTorch, and memory/layout configuration.

2026-03-31330

name	tt-bug-report
description	File a bug report with a reproducer against Tenstorrent repos (tt-lang, tt-metal, tt-xla)
argument-hint	<description of the problem>

Task

File a bug report for a Tenstorrent issue. Gather context, minimize the reproducer, and create a GitHub issue in the right repo.

Where to File

Component	Repo
TT-Lang (DSL, compiler, kernels)	`tenstorrent/tt-lang`
TTNN (ops, tensor APIs, device)	`tenstorrent/tt-metal`
TT-Metal (low-level C++ kernels)	`tenstorrent/tt-metal`
TT-XLA (PyTorch/JAX frontend)	`tenstorrent/tt-xla`

If it's unclear which repo the bug belongs to, ask the user.

Input

$ARGUMENTS

Process

Step 1: Describe the Problem

Determine the type of issue and gather relevant info:

For crashes or incorrect results:

A reproducer script (even a non-minimal one is valuable)
Actual vs expected output

For compiler errors (tt-lang):

The full error message
Compiler flags used
MLIR before and after passes (/tmp/ttlang_initial.mlir, /tmp/ttlang_final.mlir)
Any other context that seems relevant

Step 2: Minimize the Reproducer

Step 3: File the Issue

Use gh to create an issue in the appropriate repo:

gh issue create --repo <owner/repo> \
  --title "[external bug report][from claude] <short title>" \
  --body "$(cat <<'EOF'
<body>
EOF
)"

The body should include:

Description of the problem
Reproducer (if available)
Error output / MLIR snippets (if applicable)
Environment context (simulator vs HW, etc.)

Output

Return the issue URL to the user.