Add tribal knowledge base and /executorch-kb skill (#19003)

[abhinaykukkadapu]

Summary:

Inspired from LLMWiki: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f

ExecuTorch maintainers and backend owners repeatedly answer the same questions
across GitHub issues. Tribal knowledge (backend quirks, quantization
recipes, SoC constraints, debugging methodology) lives in scattered
threads and people's heads.

WHAT: A synthesized knowledge base from 2,200+ GitHub issues and 99
discussions, accessible via the /executorch-kb Claude Code skill. Covers QNN,
XNNPACK, Vulkan, CoreML, Arm, and Cadence backends plus cross-cutting
topics (export, quantization, troubleshooting).

Components:

• .wiki/ — 20 articles (4,284 lines), 7 rules files (436 lines),
  synthesis guide, and version tracking
• .claude/skills/executorch-kb/ — /executorch-kb skill with query, lint, save, resync, stats
• All file paths and imports verified against codebase
• Official doc URLs for synthesis-time and query-time validation

Backend	Articles	Lines
QNN	5	1,170
XNNPACK	2	436
Vulkan	2	384
CoreML	1	276
Arm	2	550
Cadence	1	124
Export	2	377
Quantization	2	329
Troubleshooting	3	638
Total	20	4,284

Usage:
/executorch-kb Search (e.g., /executorch-kb QNN V68 layer_norm error)

Prototyped with Claude Code.

Reviewed By: psiddh

Differential Revision: D101099089

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19003

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

⏳ 9 Pending, 2 Unrelated Failures

As of commit 4028985 with merge base 1d37abd ():

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-models-linux (mv2, xnnpack-quantization-delegation, linux.2xlarge) / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.
• pull / test-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, linux.2xlarge, executorch-u... / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[meta-codesync]

@abhinaykukkadapu has exported this pull request. If you are a Meta employee, you can view the originating Diff in D101099089.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[digantdesai]

When does this list get "refreshed"?

[abhinaykukkadapu]

Same as the date above, i ran resync on the 15th.