alibaba/skill-up

Agent Judge adds judge-level skill installation for agent-based evaluation runs. Use it when the evaluator needs reusable rubrics or domain guidance separate from the skill under test.

Agent Judge Support adds judge-side Skills to agent_judge evaluations so the reviewer agent can install and use separate rubric Skills. It is used when you need reusable, isolated review rules and audit data for scoring.

Code Quality Analyzer reviews code for correctness, maintainability, performance, and security. Use it when you want a static quality assessment, issue list, and actionable fix suggestions.

Code Quality Reviewer reviews code changes and provides a detailed quality assessment with bug findings and actionable recommendations. Use it when you need a second pass on changes before merging or shipping.

Code Review Assistant analyzes submitted code for bugs, security issues, performance problems, and error handling gaps. Use it when you want a structured review with specific findings and fix suggestions.

Code Review Helper analyzes code snippets or diffs for common issues like null pointer risks, unhandled exceptions, resource leaks, naming, and style. Use it when you want a review report with problems, suggestions, and a summary.

Code Stats analyzes a codebase and reports file counts, line counts, largest files, and size by extension. Use it when you need a quick audit of project structure or want to know how much code is in a directory.

Custom Engine is a minimal end-to-end fixture for testing local and HTTP custom agent transports. Use it to verify SessionInput and SessionResult flow through the pipeline.

Data Transformer converts between common data formats like CSV, JSON, YAML, TSV, and XML. Use it when you need to change file formats and verify the output structure.

File Organizer analyzes a project’s directory structure and key files to produce a structured report and summary. Use it when you need to understand a codebase, inventory files, or generate project documentation.

Flaky Skill may require retry under certain conditions. Use it to test how an agent handles intermittent failures and retry logic.

Git Analyzer analyzes git repositories and commit history to summarize branches, changes, and repository activity. Use it when you need a quick read on how a codebase has evolved.

MCP Case Overrides uses the configured MCP project-mgmt server's get_project tool when asked. It is used as a per-case mocked override smoke skill in skill-up end-to-end tests.

MCP Mocked Marker uses the configured MCP marker tool when asked. It is a smoke skill used by skill-up end-to-end tests.

MCP Stdio Marker uses the configured MCP marker tool when asked. It is a smoke skill used by skill-up end-to-end tests.

Mock Engine is a mock skill used for deterministic pipeline testing. Use it when you need predictable behavior in an AI workflow or agent pipeline.

Mood Booster responds when someone seems bored, frustrated, or down with comforting words and a short joke. Use it to lighten the atmosphere before ending with encouragement.

Multi-Turn Session Fixture is a placeholder skill used as an end-to-end test fixture for multi-turn sessions. It is used for testing or validating session flows rather than for a production workflow.

Quick Calculator produces accurate results for arithmetic, unit conversion, and formula solving. Use it when someone asks to compute a value or check a numerical expression.

Sandbox MCP uses configured MCP tools to create a sandbox, execute code, and shut it down. Use it when you need isolated code execution for agent workflows or verification tasks.

Sdd Riper executes the SDD workflow with strict phase gating. It is used to guide research, design, planning, implementation, and review in order.

Skill Up creates, runs, validates, and diagnoses Agent Skill evaluations with the skill-up CLI. Use it to scaffold evals, add cases, author judges, run reports, and iterate from failures or imported evals.json files.

Todo Manager helps manage to-do items by adding, deleting, completing, and listing tasks. Use it when you need a simple persistent task list in a workspace.