🛠️

Git 與版本控制

6462 skills in 工具 > Git 與版本控制

subagent-prompting

Apply instruction-engineering to all subagent prompts. Use BEFORE invoking the Task tool, spawning agents, or dispatching parallel workers. Ensures subagents receive persona-driven, research-backed prompts that maximize compliance and output quality. Triggers on: "use a subagent", "spawn agent", "dispatch", "Task tool", parallel agent work, or any multi-agent orchestration.

majiayu000/claude-skill-registry
0
0
更新於 11h ago

observability-patterns

Marketplace

Comprehensive observability setup patterns for Google ADK agents including logging configuration, Cloud Trace integration, BigQuery Agent Analytics, and third-party observability tools (AgentOps, Phoenix, Weave). Use when implementing monitoring, debugging agent behavior, analyzing agent performance, setting up tracing, or when user mentions observability, logging, tracing, BigQuery analytics, AgentOps, Phoenix, Arize, or Weave.

vanman2024/ai-dev-marketplace
0
0
更新於 11h ago

expert-debugging-and-lint-fixing

Systematic debugging workflow to reproduce, isolate, and fix hard software bugs, resolve related lint issues, and add tests and guardrails to prevent regressions. This skill should be used for complex bugs that teams struggle to fix, flaky/intermittent failures, production-only bugs, and environment-specific issues where code changes must be lint-clean.

auldsyababua/instructor-workflow
0
0
更新於 11h ago

repomix-config

Marketplace

Repomix AI-friendly codebase compression configuration (.repomix.config.json) template and validation logic. Achieves 70% token reduction through XML compression and repository-type-specific include patterns. Includes 5 critical standards (XML output format, include patterns by repo type, gitignore integration, exclude patterns, security checks). Use when creating or auditing .repomix.config.json files for optimal LLM context compression.

metasaver/metasaver-marketplace
0
0
更新於 11h ago

architecture-patterns

AI-friendly architecture patterns for TypeScript projects including Domain-Driven Design, Clean Architecture, Hexagonal Architecture, and Page Object Model testing patterns

majiayu000/claude-skill-registry
0
0
更新於 11h ago

lintmesh

Run multiple linters (eslint, oxlint, tsc, biome) in parallel with unified JSON output. Use when linting code, checking for errors before commits, or debugging lint failures. Triggers on "lint", "check code", "run linters", or after editing JS/TS files.

hexsprite/lintmesh
0
0
更新於 11h ago

commit-operations

View and analyze commits in GitHub repositories - commit history, diffs, and commit details using gh CLI

majiayu000/claude-skill-registry
0
0
更新於 11h ago

save-session

Use this skill when the user wants to save session progress before running /clear, or when you notice significant progress has been made that should be saved to TASKS.md and committed to git (project)

majiayu000/claude-skill-registry
0
0
更新於 11h ago

matrix-distribution

Marketplace

Parallelize operations across dynamic target lists using GitHub Actions matrix strategies with failure isolation, rate limiting, and conditional logic.

adaptive-enforcement-lab/claude-skills
0
0
更新於 11h ago

skill-developer

Anthropic 베스트 프랙티스를 따라 Claude Code 스킬을 생성하고 관리합니다. 새로운 스킬을 만들거나 skill-rules.json을 수정하고, 트리거 패턴을 이해하며, 훅을 다루고, 스킬 활성화를 디버깅하거나, 점진적 공개를 구현할 때 사용하세요. 스킬 구조, YAML 프론트매터, 트리거 타입(키워드, 의도 패턴, 파일 경로, 콘텐츠 패턴), 강제 수준(블록, 제안, 경고), 훅 메커니즘(UserPromptSubmit, PreToolUse), 세션 추적, 500줄 규칙을 다룹니다.

nfbs2000/vibe-with-google-ai-divorce-agent-inflearn
0
0
更新於 11h ago

mkdocs

Build project documentation sites with MkDocs static site generator. USE WHEN user mentions mkdocs, documentation site, docs site, project documentation, OR wants to create, configure, build, or deploy documentation using Markdown. Covers installation, configuration, theming, plugins, and deployment.

julianobarbosa/claude-code-skills
0
0
更新於 11h ago

gh-search-code

Use when searching code across GitHub repositories - provides syntax for file extensions, filenames, languages, sizes, exclusions, and using -w flag for regex search via web interface

majiayu000/claude-skill-registry
0
0
更新於 11h ago

uv

Expert Python package management with uv - fast dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.

rghamilton3/dotfiles
0
0
更新於 11h ago

tacosdedatos-illustrator

Marketplace

Create complete post banner illustrations for tacosdedatos from concept to final image. Use this skill when you need to create a banner image for a new post, generate an illustration that matches the tacosdedatos visual style, or produce publication-ready artwork. This is the main creative orchestration skill that handles the full workflow.

chekos/bns-marketplace
0
0
更新於 11h ago

searching-web

Search web, library docs, GitHub repos, and code examples. Use for "how to", "what is", documentation lookups, or fetching URL content.

majiayu000/claude-skill-registry
0
0
更新於 11h ago

git-operations

Provides Git command helpers for branch management, commit history analysis, and repository operations. Use this skill when you need to interact with Git repositories, analyze commit history, or manage branches.

B16B1RD/cc-craft-kit
0
0
更新於 11h ago

workflows-code

Orchestrator guiding developers through implementation, debugging, and verification phases across specialized code quality skills (project)

MichelKerkmeester/AI-Systems
0
0
更新於 11h ago

create-entity-viewmodel

Create a new entity ViewModel with property ViewModels following Phoenix MVVM patterns. Use when adding new data models, creating entity wrappers, or scaffolding ViewModels for entities. Handles property VM creation, label converters, base class selection, and test generation.

biggs3d/Tools
0
0
更新於 11h ago

git-worktree-workflow

Use git worktrees for parallel Claude Code workflows. Run multiple Claude instances on different features simultaneously without merge conflicts. Use for parallel development, multi-branch testing, and subagent workflows.

vamseeachanta/workspace-hub
0
0
更新於 11h ago

figure-legends

Use when editing or improving figure legends that lack complete independence, missing statistical notation (n=, P values), or insufficient panel descriptions - ensures self-contained CNS-quality legends

vitamin3615/Agent-skills
0
0
更新於 11h ago