Skip to content

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.

1,274
Stars
91
Skill Files
135
Forks
74
PRs Merged
8
Contributors
4
Issues Open
16
Issues Closed
2026-07-21
Last Activity

Skill Analysis

639
Avg Lines / Skill
3,756
Avg Words / Skill
1339
Code Blocks
310
Total Files
8.61 MB
Repo Size
0
Reference Files
Skill lines16 min / 391 median / 6068 max
Code languagesbash, dot, gitconfig, javascript, json, jsonc, language, markdown, md, mermaid, python, suggestion, text, ts, typescript, xml, yaml
Frontmatter keysallowed-tools, argument-hint, color, description, model, name, tools
Has CLAUDE.mdYes
Has LicenseYes
File typesmd (266), json (20), ts (6), sh (3), png (2), yaml (1), lockb (1), gif (1)

Skills (91)

  • qa-engineer
    2243 lines16705 words40 blocks

    Use this agent when adding LLM-as-Judge verification sections to implementation steps in task files. Produces structured per-step evaluation specifica...

    bashmarkdowntexttsyaml
  • tech-lead
    692 lines4242 words7 blocks

    Use this agent when breaking down architecture into implementation steps with success criteria, dependencies, and risk assessment. Transforms architec...

    markdown
  • team-lead
    775 lines4022 words20 blocks

    Use this agent when reorganizing implementation steps for maximum parallel execution with explicit dependency tracking and agent assignments. Transfor...

    bashmarkdown
  • code-explorer
    1003 lines5182 words21 blocks

    Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed change...

    markdown
  • developer
    2203 lines10698 words57 blocks

    Use this agent when implementing tasks from task files with implementation steps. Executes code changes following acceptance criteria, leveraging exis...

    markdowntexttypescript
  • software-architect
    828 lines4713 words21 blocks

    Use this agent when synthesizing research findings, codebase analysis, and business requirements into architectural solutions for task specifications.

    markdowntypescript
  • tech-writer
    1145 lines5625 words20 blocks

    Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps use...

    bashjavascriptmarkdowntexttypescript
  • code-reviewer
    1649 lines11007 words31 blocks

    Use this agent to verify implementation against verification specification AND review code quality. Receives the task specification path and step numb...

    markdowntsyaml
  • researcher
    772 lines3433 words24 blocks

    Use this agent when researching unknown technologies, libraries, frameworks, and dependencies to gather relevant resources and documentation for imple...

    bashmarkdown
  • business-analyst
    115 lines776 words

    Use this agent when refining task descriptions and creating acceptance criteria for implementation tasks.

  • brainstorm
    57 lines471 words

    Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative que...

  • create-ideas
    16 lines131 words

    Generate ideas in one shot using creative sampling

  • plan-task
    1230 lines5819 words28 blocks

    Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task

    bashjsonmarkdowntext
  • implement-task
    1900 lines9546 words42 blocks

    Implement a task with automated LLM-as-Judge verification per step

    bashjsonmarkdowntext
  • add-task
    204 lines807 words6 blocks

    creates draft task file in .specs/tasks/draft/ with original user intent

    bashmarkdown
  • setup-serena-mcp
    121 lines689 words4 blocks

    Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

    markdowntext
  • setup-context7-mcp
    57 lines270 words2 blocks

    Guide for setup Context7 MCP server to load documentation for specific technologies.

    markdowntext
  • build-mcp
    359 lines1787 words1 blocks

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. ...

    xml
  • setup-codemap-cli
    244 lines886 words11 blocks

    Guide for setup Codemap CLI for intelligent codebase visualization and navigation

    bashjsonmarkdowntext
  • setup-arxiv-mcp
    117 lines583 words5 blocks

    Guide for setup arXiv paper search MCP server using Docker MCP

    markdowntext

Recent Commits

-341 contributions across all repos
JulAugSepOctNovDecJanFebMarAprMayJunJul
Less
More
  • 555b9522026-07-21
    Merge pull request #97 from NeoLabHQ/feature/vg/add-support-for-triage-review-commit-mode
    Vladislav Goncharov
  • e4192022026-07-21
    feat(review): add commit mode to triage-review command
    leovs09
  • a0bfff12026-07-14
    Merge pull request #96 from NeoLabHQ/feature/vg/add-triage-review-skill
    Vladislav Goncharov
  • fe274022026-07-14
    feat(review-triage): add support for branch based diffs
    leovs09
  • 3bea63b2026-07-13
    fix: move change list aggregation logic to skill itself
    leovs09
  • 31c6c802026-07-13
    fix: correct the agents output tables
    leovs09
  • e52d5492026-07-13
    feat: copy base triage review skill draft
    leovs09
  • e61511b2026-07-06
    Merge pull request #95 from NeoLabHQ/fix/vg/use-foreground-agents-only-during-review
    Vladislav Goncharov
  • e7413552026-07-06
    bump: 3.3.1
    leovs09
  • ce5a5822026-07-06
    fix(review): launch foreground agents only
    leovs09