GitHub
context-engineering
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
☆ 426查看技能
数据与 AI AI 技能
发现 数据与 AI 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。
分类目录: 数据与 AI
数据与 AI 清除筛选
全部技能
GitHub
kaizen
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterat...
☆ 426查看技能
GitHub
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent fo...
☆ 426查看技能
GitHub
worktrees
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktr...
☆ 426查看技能
GitHub
thought-based-reasoning
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive gui...
☆ 426查看技能
GitHub
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure fir...
☆ 426查看技能
GitHub
notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns...
☆ 426查看技能
GitHub
software-architecture
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
☆ 426查看技能
GitHub
agent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
☆ 426查看技能
GitHub
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
☆ 426查看技能
GitHub
crdb-change
Generate CockroachDB SQL and migrations for schema changes. Use when creating migrations, updating the database schema, or when the user mentions migrations, schema changes, or dbinit.sql.
☆ 424查看技能
GitHub
create-skill
Guide for creating new skills in magenta.nvim, including file structure, frontmatter format, and TypeScript script execution
☆ 424查看技能
GitHub
doc-testing
Comprehensive guide for writing tests in magenta.nvim, including test environment setup, mock providers, driver interactions, and best practices
☆ 424查看技能
GitHub
learn
Guide for learning and researching parts of a codebase before implementing changes. Use when you need to understand code, APIs, or concepts.
☆ 424查看技能
GitHub
doc-views
Comprehensive guide for the view system in magenta.nvim, including template literal syntax, component composition, interactive bindings, and TUI-specific rendering patterns
☆ 424查看技能
GitHub
plan
Guide for creating implementation plans. Use when breaking down complex work into actionable steps.
☆ 424查看技能
GitHub
update-permissions
Add bash command permissions to project-level or user-level magenta options. Use when a command needs to be permanently allowlisted.
☆ 424查看技能
GitHub
worktree-spawn
Spawn an independent Claude instance in a git worktree to work on a task in parallel. Use when the user wants to delegate a task to run independently while continuing the current conversation.
☆ 421查看技能
GitHub
unit-test-implementation
Best practices for implementing unit tests in this TypeScript monorepo. Use when writing new tests, refactoring existing tests, or fixing failing tests. Covers mocking strategies, test organization, helper func...
☆ 421查看技能
GitHub
ci-log-reader
Investigate CI failures by following log links from ci.aztec-labs.com. Given a GitHub Actions URL, PR number, or direct CI log URL, fetch logs and recursively follow nested log links to trace the root cause of...
☆ 421查看技能
GitHub
readme-writer
Guidelines for writing module READMEs that explain how a module works to developers who need to use it or understand its internals. Use when documenting a module, package, or subsystem.
☆ 421查看技能
GitHub
noir-sync-update
Perform necessary follow-on updates as a result of updating the noir git submodule.
☆ 421查看技能
GitHub
updating-changelog
Updates changelog documentation for contract developers and node operators by analyzing branch changes relative to 'next'. Use when preparing a PR, updating migration notes, documenting breaking changes, or whe...
☆ 421查看技能
GitHub
debug-lldb
Capture and analyze thread backtraces with LLDB/GDB to debug hangs, deadlocks, UI freezes, IPC stalls, or high-CPU loops across any language or project. Use when an app becomes unresponsive, switching contexts...
☆ 420查看技能
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。