216 件 ・ 関連度順
概要と使いどころ
安装、卸载 LoongSuite Pilot（面向研发团队的 AI Coding 数据采集工具， 支持 Cursor / Qoder / Claude Code / Codex）。当用户提到 loongsuite-pilot 安装、 pilot 部署、Node.js 前置条件、nvm 配置、Linux 7U glibc 补丁、SSH 远程安装、 新增或追加 SLS flusher、自定义 SLS/WebTracking 上报配置时， 务必使用本 Skill——即使用户只问“怎么装”也应触发。安装完成后可在 ~/.loongsuite-pilot/skills/loongsuite-pilot-ops/references/ 目录下找到诊断排查与观测面板的详细参考文档。
日本語の概要は準備中です。原文の説明を表示しています。
当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用；尤其适用于线上大盘、强对比的分析看板、已校验的查询包，或需要专业中文标签与指标定义的运维向大盘。
日本語の概要は準備中です。原文の説明を表示しています。
loongsuite-pilot-ops
日本語の概要は準備中です。原文の説明を表示しています。
Mine a per-kernel optimization trace — a git repository capturing successive versions of one kernel being optimized — into structured, gate-validated optimization-experience records for the GPU kernel wiki. Use when asked to distill an optimization run, a kernel_opt trace directory or a version ladder into wiki records; to report what such a run actually achieved; to build, extend, re-run or validate the staging store behind those records; or to explain how a trace-derived record's number, snippet or provenance was established.
日本語の概要は準備中です。原文の説明を表示しています。
Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki. Use when asked to turn vibe-coding sessions, Codex rollout logs, or Claude Code project transcripts into wiki records; to summarise what a kernel-optimization session achieved; to build or extend a session-trace store; or to re-run and validate one. Also use when asked how a session-derived record's number, snippet, or provenance was established.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a structured implementation plan from an evidence draft. Validate paths, obtain configured independent Codex and Qoder reviews, synthesize available advice against repository evidence, preserve the draft, and produce testable acceptance criteria and validation steps.
日本語の概要は準備中です。原文の説明を表示しています。
Quickly extract a typed GPU-Wiki query intent from prose. Never inspect or query a knowledge store.
日本語の概要は準備中です。原文の説明を表示しています。
Choose and run ACU-only, adaptive PPU in-kernel timeline, or optional bounded joint analysis for a PPU kernel. Use for device-level bottleneck diagnosis, kernel-internal critical-path questions, or evidence that genuinely needs both; do not require all three modes.
日本語の概要は準備中です。原文の説明を表示しています。
Run the evidence loop of one long-horizon GPU kernel optimization episode. Use this skill to reconstruct the incumbent, profile and localize a bottleneck, research progressively, plan one coherent direction, implement and repair, validate development correctness and performance, and record every decisive experiment in the episode journal.
日本語の概要は準備中です。原文の説明を表示しています。
Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel. Use this skill to understand compute semantics, determine the target platform and framework, search reference implementations, and produce a correct V0 baseline with performance records for later profile-driven optimization.
日本語の概要は準備中です。原文の説明を表示しています。
Let AKA autonomously add, run, inspect, and revise intra-kernel timeline probes for standalone CUDA/inline PTX or CuTe DSL when ordinary benchmark, NSYS, or NCU evidence cannot answer a specific kernel-internal timing question.
日本語の概要は準備中です。原文の説明を表示しています。
Submit a new issue to the project.
日本語の概要は準備中です。原文の説明を表示しています。
Cerate or Update a GitHub Issue for each Task in the task document.
日本語の概要は準備中です。原文の説明を表示しています。
Cerate or Update a GitHub Issue for each Module in the task document.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection, auto-merge candidates, labeling). Also covers creating, inspecting, and repairing a CodeScope index. Use for: code structure, who calls what, why something changed, similar functions, module boundaries, bug tracing, class relationships, PR risk/conflicts, or any question benefiting from a code knowledge graph. Applies when a `.codegraph` index exists in the workspace, or when the user wants to create one.
日本語の概要は準備中です。原文の説明を表示しています。
Submit a new Pull Request to the project.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze new commits and generate related test cases.
日本語の概要は準備中です。原文の説明を表示しています。
Create or update the feature specification from a natural language feature description.
日本語の概要は準備中です。原文の説明を表示しています。
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Check comments from the Pull Request on the GitHub and update code.
日本語の概要は準備中です。原文の説明を表示しています。
Vulnerability audit and dataflow analysis built on the neug CPG engine. file_audit (default, recommended): first builds a function-level summary graph (tier1) over the entire project, then incrementally builds detailed CPGs (tier2) on demand for chosen functions; both tiers coexist in a single neug database (unified schema, cross-layer refines edges; C/Java/Python/Rust). All capabilities are exposed as CLI tool subcommands (audit/overview/build/query/methods/paths), so an agent can drive the audit step by step via shell; the audit subcommand can also run the built-in LLM loop. The same tooling also supports a dataflow analysis mode (Workflow C): no vulnerability hunting, only variable-level dataflow tracing for functions of interest, producing dataflow_analysis.json. repo_audit: multi-round LLM/Cypher audit over a full-repo CPG. Use when the user asks to audit a codebase/project for vulnerabilities, scan a project with CPG/neug, run repo_audit/file_audit, find source-to-sink taint paths, or analyze dataflow inside a function. Supports C, Java, Python, and Rust.
日本語の概要は準備中です。原文の説明を表示しています。
Execute the implementation planning workflow using the plan template to generate design artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Search and analyze products on the Chinese 1688 wholesale platform (Alibaba domestic B2B market) for sourcing, supplier discovery, and product selection. Trigger when the user mentions 1688 product search, finding suppliers on 1688, wholesale product queries, factory sourcing, dropshipping supplier search, 1688 keyword product selection, wholesale price comparison, filtering by sales volume, any product research on the 1688 platform, 1688 search, 1688 product selection, find suppliers, factory lookup, wholesale pricing, supplier search, domestic sourcing, 1688 products. Even if the user does not explicitly say "1688", if their need involves searching for wholesale products, finding domestic suppliers, or sourcing from the domestic Chinese market, this skill should also be triggered.
日本語の概要は準備中です。原文の説明を表示しています。
Perform image-based product search on the 1688 platform. Use an image URL to find visually similar supplier products, returning title, price, minimum order quantity, monthly sales, repurchase rate, trade score, and seller identity. Triggered when users mention 1688 image search, 1688 visual search, find supplier by image, reverse image search 1688, 1688 product sourcing by image, or Alibaba 1688 image search. Even if the user does not explicitly mention "image search," this skill should be triggered whenever a user provides an image URL and wants to find matching or similar products on the 1688 wholesale platform.
日本語の概要は準備中です。原文の説明を表示しています。