GitHub organization
Agent skills by alibaba
- skills
- 26
- repositories
- 6
Repositories by alibaba
- atrex-kernel-agentAn end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU kernel through a structured, profile-driven workflow.154 stars · 7 skills
- skill-upAn evaluation and evolution tool for Agent Skills.1.1k stars · 7 skills
- neugThe one data index for your agentic applications168 stars · 6 skills
- UnifiedModelThe semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.412 stars · 2 skills
- loongsuite-pilotLocal-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.198 stars · 2 skills
- open-code-reviewSecure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.44k stars · 2 skills
Skills by alibaba, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes. | alibaba/ | 44k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | Has the host agent do the code review itself while the ocr CLI handles file selection and rule lookup, covering workspace changes, branch ranges or single commits. | alibaba/ | 44k | — | ~2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 3 | Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments. | alibaba/ | 412 | — | ~1.9k | Automated safety check: Pass | Unknown | 13 days ago |
| 4 | 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… | alibaba/ | 154 | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 5 | 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。 | alibaba/ | 198 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 6 | Triggered when the user submits code or requests a code review. | alibaba/ | 1.1k | — | ~505 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 7 | Loads one entity-linked Skill through UModel, follows its inline SKILL.md and applies attached knowledge items under their apply policies. | alibaba/ | 412 | — | ~1k | Automated safety check: Pass | Unknown | 13 days ago |
| 8 | Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki. | alibaba/ | 154 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 9 | Triggered when the user needs to convert data formats, such as CSV to JSON, JSON to YAML, or XML to JSON. | alibaba/ | 1.1k | — | ~332 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 10 | Choose and run ACU-only, adaptive PPU in-kernel timeline, or optional bounded joint analysis for a PPU kernel. | alibaba/ | 154 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 11 | Triggered when the user needs to organize project files, analyze directory structure, or generate a project report. | alibaba/ | 1.1k | — | ~374 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 12 | Analyze new commits and generate related test cases. An agent skill from alibaba/neug. | alibaba/ | 168 | — | ~287 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 13 | Quickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula solving. | alibaba/ | 1.1k | — | ~252 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 14 | 基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。 | alibaba/ | 198 | — | ~944 | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 15 | 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… | alibaba/ | 154 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 16 | 16.Sync Modules Cerate or Update a GitHub Issue for each Module in the task document. | alibaba/ | 168 | — | ~575 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 17 | 17.Sync Tasks Cerate or Update a GitHub Issue for each Task in the task document. | alibaba/ | 168 | — | ~487 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 18 | 18.Gen Plan Generate a structured implementation plan from an evidence draft. | alibaba/ | 154 | — | ~3.4k | Automated safety check: Pass | MIT | 8 days ago |
| 19 | Triggered when the user submits code or requests a comprehensive code quality analysis. | alibaba/ | 1.1k | — | ~306 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 20 | Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel. | alibaba/ | 154 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 21 | 21.Mood Booster Triggered when the user expresses boredom, low mood, frustration, irritation, or a need to relax. | alibaba/ | 1.1k | — | ~372 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 22 | Run the evidence loop of one long-horizon GPU kernel optimization episode. | alibaba/ | 154 | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 23 | 23.Create PR Submit a new Pull Request to the project. An agent skill from alibaba/neug. | alibaba/ | 168 | — | ~303 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 24 | Check comments from the Pull Request on the GitHub and update code. | alibaba/ | 168 | — | ~386 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 25 | 25.Sdd Riper SDD-RIPER workflow executor with phase gating. An agent skill from alibaba/skill-up. | alibaba/ | 1.1k | — | ~117 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 26 | 26.Create Issue Submit a new issue to the project. | alibaba/ | 168 | — | ~736 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
Questions, answered from the data.
What is the best skill by alibaba?
Open Code Review CLI from alibaba/open-code-review ranks first of the 26 skills by alibaba listed here, with the highest score: its repository has 44k GitHub stars, its SKILL.md loads about 3.1k tokens and it passes the automated safety check with no findings. Next come Open Code Review Delegate and UModel Root Cause Analysis.
Are alibaba's skills official?
None yet. All 26 skills by alibaba listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.