context-engineering-kit
by NeoLabHQ
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.
About
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.
Skill Analysis
Skills (86)
Create well-formatted commits with conventional commit messages and emoji
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or com...
bashCreate pull requests using GitHub CLI with proper templates and formatting
bashMerge changes from worktrees into current branch with selective file checkout, cherry-picking, interactive patch selection, or manual merge
bashAdd line-specific review comments to pull requests using GitHub CLI API
bashjsonmarkdownCreate and setup git worktrees for parallel development with automatic dependency installation
bashAnalyze a GitHub issue and create a detailed technical specification
Compare files and directories between git worktrees or worktree and current branch
bashLoad all open issues from GitHub and save them as markdown files
markdownUse when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit ...
bashgitconfigGuide for setup arXiv paper search MCP server using Docker MCP
markdowntextGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. ...
xmlGuide for setup Codemap CLI for intelligent codebase visualization and navigation
bashjsonmarkdowntextGuide for setup Context7 MCP server to load documentation for specific technologies.
markdowntextGuide for setup Serena MCP server for semantic code retrieval and editing capabilities
markdowntextSetup TypeScript best practices and code style rules in CLAUDE.md
markdownCurates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
bashmarkdownyamlReflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
javascriptmarkdownComprehensive multi-perspective review using specialized judges with debate and consensus building
bashmarkdownUse this agent when generating evaluation rubrics, checklists, criteria, metrics, and weights for a user prompt BEFORE implementation begins. Produces...
markdownyaml
Recent Commits
- 48d6d482026-03-29Merge pull request #72 from NeoLabHQ/fix/vg/code-review-and-do-in-parallel-skillsVladislav Goncharov
- 74f43212026-03-29fix(sadd): make do in parallel perform meta-judge evaluation per taskleovs09
- 5f2a7dc2026-03-29fix(code-reivew): remove local code review tools limitationsleovs09
- d2bb7a82026-03-22Merge pull request #70 from NeoLabHQ/chore/remove-outdated-docker-scriptsVladislav Goncharov
- 4f7db102026-03-22chore: remove docker outside of docker scriptleovs09
- 6d2dec22026-03-21feat(sadd): add LLM-as-a-Meta-Judge rubrics generation stepVladislav Goncharov
- 0453f1f2026-03-21docs(code-review): add arguments decription for commandsleovs09
- 889aa4e2026-03-21docs: add deeper description of how rules workleovs09
- 0fd1b5c2026-03-21feat(sadd): use 5 why for rule creation analysis diring judgingleovs09
- 347d1ea2026-03-21docs(ddd): update docs with new rules descriptionleovs09