refine-plan
Refines an existing implementation plan through discussion with the user. Takes a GitHub issue number. Use when the user wants to refine a plan, discuss a plan, change a plan, or says "refine plan X" or "let's...
发现 部署与运维 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Refines an existing implementation plan through discussion with the user. Takes a GitHub issue number. Use when the user wants to refine a plan, discuss a plan, change a plan, or says "refine plan X" or "let's...
Creates GitHub issues to capture work that needs to be done. Records intent with context about the codebase, not implementation plans. Use when the user wants to track work, create a ticket, log a task, or says...
Sets up a new Python library project using uv in the current directory. Creates project structure, installs dev dependencies, and optionally configures git remote. Use when the user wants to initialise a Python...
Splits uncommitted changes into multiple logical commits by functionality. Use when asked to organize commits, split changes, or create atomic commits.
Uses multiple parallel finder agents and multiple oracle consultations simultaneously for broad analysis. Use when asked to search from multiple angles, investigate across many files, or need parallel multi-per...
Performs sequential multi-round oracle analysis where each round builds on previous findings. Use when user specifies analysis count (e.g., "analyze 5 times"), asks to think repeatedly, or needs progressive ref...
Apply when working with Vue components, composables, stores, or styling. Ensures code matches established project patterns.
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof aga...
Use when user requests "parallel" commands, running multiple builds/tests simultaneously, or long-running tasks. Use `gob add` instead of parallel Bash tool calls - gob provides job management, output capture,...
Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fixes with tests before returning. Use one per issue from triage task list.
Analyze code review findings and create execution plan. Decides parallel vs sequential fixing based on issue severity and independence. Returns structured task list with clear fixer instructions.
Use when completing work on a task or feature. Prompts for code review before finishing. ALWAYS invoke this skill before saying work is done.
Use after completing file changes - strongest for source code (AST-aware linting, security, tests), lighter support for markdown/config. Dispatches CodeRabbit reviewer subagent. ALWAYS request review before con...
Apply when writing styles. Ensures consistency with design system and project patterns.
Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.
Specialized agent for code review, debugging critique, and quality assessment
Orchestrator agent for coordinating multiple AI agents in a persistent system
Common patterns and best practices for multi-agent coordination
Advanced memory management techniques for the OpenCode memory system
Systematic optimization hunter. Finds memory optimizations AND bugs - both are valuable. Run /validate-correctness when bugs are discovered.
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks. Bugs discovered during review are valuable - invoke /validate-correctness to validate...
Validates discovered bugs with reproducing tests and validates fixes with regression tests. Called by other skills when bugs are found during optimization hunting. Creates unit tests and fuzz tests to prove bug...
Environment validation checklist. Run this FIRST when starting a new Claude session to verify the environment is ready for optimization work. Checks build tools, test runners, benchstat, git, and database acces...
Salvages optimization work lacking benchmarks. Generates missing evidence, validates claims. Bugs discovered during rescue are valuable - invoke /validate-correctness.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。