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 (91)
Use this agent when adding LLM-as-Judge verification sections to implementation steps in task files. Produces structured per-step evaluation specifica...
bashmarkdowntexttsyamlUse this agent when breaking down architecture into implementation steps with success criteria, dependencies, and risk assessment. Transforms architec...
markdownUse this agent when reorganizing implementation steps for maximum parallel execution with explicit dependency tracking and agent assignments. Transfor...
bashmarkdownUse this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed change...
markdownUse this agent when implementing tasks from task files with implementation steps. Executes code changes following acceptance criteria, leveraging exis...
markdowntexttypescriptUse this agent when synthesizing research findings, codebase analysis, and business requirements into architectural solutions for task specifications.
markdowntypescriptCreates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps use...
bashjavascriptmarkdowntexttypescriptUse this agent to verify implementation against verification specification AND review code quality. Receives the task specification path and step numb...
markdowntsyamlUse this agent when researching unknown technologies, libraries, frameworks, and dependencies to gather relevant resources and documentation for imple...
bashmarkdownUse this agent when refining task descriptions and creating acceptance criteria for implementation tasks.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative que...
Generate ideas in one shot using creative sampling
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
bashjsonmarkdowntextImplement a task with automated LLM-as-Judge verification per step
bashjsonmarkdowntextcreates draft task file in .specs/tasks/draft/ with original user intent
bashmarkdownGuide for setup Serena MCP server for semantic code retrieval and editing capabilities
markdowntextGuide for setup Context7 MCP server to load documentation for specific technologies.
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 arXiv paper search MCP server using Docker MCP
markdowntext
Recent Commits
- 555b9522026-07-21Merge pull request #97 from NeoLabHQ/feature/vg/add-support-for-triage-review-commit-modeVladislav Goncharov
- e4192022026-07-21feat(review): add commit mode to triage-review commandleovs09
- a0bfff12026-07-14Merge pull request #96 from NeoLabHQ/feature/vg/add-triage-review-skillVladislav Goncharov
- fe274022026-07-14feat(review-triage): add support for branch based diffsleovs09
- 3bea63b2026-07-13fix: move change list aggregation logic to skill itselfleovs09
- 31c6c802026-07-13fix: correct the agents output tablesleovs09
- e52d5492026-07-13feat: copy base triage review skill draftleovs09
- e61511b2026-07-06Merge pull request #95 from NeoLabHQ/fix/vg/use-foreground-agents-only-during-reviewVladislav Goncharov
- e7413552026-07-06bump: 3.3.1leovs09
- ce5a5822026-07-06fix(review): launch foreground agents onlyleovs09