TheBotique

huawei-cloud-ascend-profiler-db-explorer

Convert natural language questions into safe executable SQL to query Ascend PyTorch Profiler / msprof database for operator time consumption, communication, dispatch, and other performance data. Supports table schema extraction from official documentation. Use this skill when the user wants to: (1)

as observed 2026-11-05T14:44:09.628Z
Identifier
huawei-cloud-ascend-profiler-db-explorer
Source
ClawHub
Version observed
1.0.2
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-08-28T22:54:51.336Z
Observations recorded
3
Installs (reported upstream)
1
Weekly downloads (upstream)
289
Declared license
MIT-0

Observation history

2026-11-05T14:44:09.628Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "- Initial release of Huawei Cloud Ascend Profiler DB Explorer.\n- Converts natural language questions into safe, executable SQL for Ascend PyTorch Profiler and msprof databases.\n "Added explicit scope limits for schema queries and database types, and clarified that the skill is read-only and must reject write requests. Removed `skill-card.md`.\n\n- Supports
latestVersion "1.0.1" "1.0.2"
2026-09-21T23:20:53.794Z

Fields that differed: license changelog description latestVersion

FieldBeforeAfter
license null "MIT-0"
changelog "- Initial release of the huawei-cloud-ascend-profiler-db-explorer skill \n- Converts natural language profiling questions into safe SQL queries for Ascend PyTorch Profiler / mspr "- Initial release of Huawei Cloud Ascend Profiler DB Explorer.\n- Converts natural language questions into safe, executable SQL for Ascend PyTorch Profiler and msprof databases.\n
description "Convert natural language questions into safe executable SQL to query\nAscend PyTorch Profiler / msprof database for operator time consumption,\ncommunication, dispatch, and other null
latestVersion "1.0.0" "1.0.1"

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.