Skip to main content
NeVibeCode · repository · 63 items

context-engineering-kit: a set by neolabhq

The neolabhq/context-engineering-kit repository on GitHub: 63 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

About the repository

GitHub
neolabhq/context-engineering-kit
Stars
★ 1,845
Installs across cards
78,010
License
GPL-3.0
Source updated
2026-08-26
In the catalog since
2026-10-25
thought-based-reasoning skill thought-based-reasoning — a skill for Claude and other AI coders that gives the model a method for working through hard problems in explicit steps. Useful when a plain prompt returns the wrong answer. CX Codex +1 1,500installs prompt-engineering skill prompt-engineering guides prompt design for agents, subagents, and LLM integrations. Helpful when building production templates, chain-of-thought prompts, or agent hooks. CX Codex +1 1,500installs agent-evaluation skill agent-evaluation is a Claude Code skill that provides rubrics and LLM-as-judge templates for evaluating agents, prompts, and skills by their outcomes. CX Codex +1 1,400installs memorize skill memorize transfers insights from agent reflections and critique sessions into CLAUDE.md. Keeps your context file sharp by structuring lessons instead of bloating it with raw logs. CX Codex +1 1,400installs judge-with-debate skill The judge-with-debate skill runs three independent judges who argue over a solution's score until they agree. Useful when a single pass feels too thin for a real verdict. CX Codex +1 1,400installs update-docs skill update-docs updates project documentation based on uncommitted git changes or the latest commit. Keeps README files, docs/, and JSDoc comments synchronized with your codebase. CX Codex +1 1,400installs root-cause-tracing skill root-cause-tracing — a skill that walks the agent backward through the call stack until it finds the original trigger, then fixes there instead of at the crash site. CX Codex +1 1,400installs critique skill The critique skill runs finished work past several AI judges: they review it independently, debate their findings, and agree on a shared list of issues. CX Codex +1 1,400installs brainstorm skill brainstorm turns rough project ideas into detailed specifications through guided dialogue. It compares six architectural options before any code or implementation planning begins. CX Codex +1 1,400installs multi-agent-patterns skill multi-agent-patterns is a Claude Code skill for planning systems that split work across agents. It activates when a task breaks into subtasks or one agent runs into context limits. CX Codex +1 1,400installs write-concisely skill The write-concisely skill enforces classic style rules from William Strunk Jr.'s 1918 guide across human-facing docs. It strips filler words and switches passive phrasing into active voice. CX Codex +1 1,400installs reflect skill reflect — a skill that makes the agent reread its own answer and list the flaws before you accept the work. CX Codex +1 1,400installs apply-anthropic-skill-best-practices skill apply-anthropic-skill-best-practices is a Claude Code skill for building skills with Anthropic’s authoring guidance. It applies when a skill needs a detailed structure. CX Codex +1 1,300installs create-agent skill create-agent scaffolds autonomous subagents for Claude Code with valid YAML frontmatter, isolated contexts, and triggering examples. CX Codex +1 1,300installs do-competitively skill do-competitively runs three agents on the same task in parallel, scores their output with judges, then synthesizes the best result. Built for work where quality beats speed. CX Codex +1 1,300installs plan-do-check-act skill Walks your agent through four PDCA phases: plan, do, check, act. Useful when you want to improve a process instead of guessing at it. CX Codex +1 1,300installs commit skill Automates Git commits using conventional commit messages and matching emojis. It checks the active branch, runs pre-commit linters, and suggests splitting complex diffs into atomic commits. CX Codex +1 1,300installs create-skill skill create-skill — a skill for Claude Code, Codex, Cursor and other agents that walks through writing a new skill using a TDD approach. CX Codex +1 1,300installs create-ideas skill The create-ideas skill makes the model return six candidate answers with probabilities: three likely ones and three pulled from the tails of the distribution. CX Codex +1 1,300installs cause-and-effect skill cause-and-effect runs structured Ishikawa diagram investigations on development bottlenecks. Pinpoints root causes across technical and team factors. CX Codex +1 1,300installs fix-tests skill fix-tests — a skill for Claude Code, Codex, Cursor and other platforms that repairs failing tests after business logic changes or refactoring. It spawns parallel agents per failing file and loops until every test goes green. CX Codex +1 1,300installs test-prompt skill test-prompt — a skill that runs the RED-GREEN-REFACTOR cycle on any prompt using isolated subagents. Covers Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. CX Codex +1 1,300installs tree-of-thoughts skill tree-of-thoughts runs a hard task through three parallel agents, a pruning vote and a synthesis pass. Useful when the right approach isn't obvious up front. CX Codex +1 1,300installs create-rule skill create-rule — a skill that walks you through writing a rule file in .claude/rules/ so your agent stops repeating the same mistake. CX Codex +1 1,300installs launch-sub-agent skill launch-sub-agent dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification. CX Codex +1 1,300installs do-and-judge skill do-and-judge — a skill for Claude Code, Cursor, Codex and other AI coders: dispatches a sub-agent for the task, verifies the result through an LLM judge, and retries up to three times if the score falls below the threshold. CX Codex +1 1,300installs review-pr skill review-pr reviews an open GitHub pull request and leaves inline comments on the diff. Handy when the work sits in a PR, not in your local tree. CX Codex +1 1,300installs analyse skill analyse selects a Kaizen technique for your target, running code exploration via Gemba Walk, workflow reviews with VSM, or waste audits using Muda. CX Codex +1 1,300installs judge skill The judge skill runs a two-stage review of work from the current conversation: one sub-agent sets the criteria, another scores the result with evidence. CX Codex +1 1,300installs add-task skill add-task turns your request into a task file under .specs/tasks/draft/, with a verb-first title, a type and your original wording. The first step of a spec-driven workflow. CX Codex +1 1,300installs do-in-parallel skill do-in-parallel runs isolated tasks across separate files concurrently via sub-agents and validates work with automated judges. Fits batch refactoring and doc generation. CX Codex +1 1,300installs analyse-problem skill The analyse-problem skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan. CX Codex +1 1,300installs do-in-steps skill do-in-steps splits a complex task into dependent steps, runs them in order, and has a separate judge check each step before the next one starts. CX Codex +1 1,300installs setup-serena-mcp skill setup-serena-mcp is a Claude Code skill that configures the Serena MCP server for semantic code exploration and symbol editing. It is used to set up project context. CX Codex +1 1,300installs write-tests skill The write-tests skill reads your uncommitted and untracked git changes and writes tests for them. Useful when the logic is done but coverage is not. CX Codex +1 1,300installs implement-task skill implement-task runs a task step by step, one agent per step, then one reviewer per phase and fixes until it passes. CX Codex +1 1,300installs why skill Conducts iterative Five Whys root cause analysis for technical bugs and incidents. Helps uncover process and system gaps instead of settling for superficial patches. CX Codex +1 1,300installs review-local-changes skill review-local-changes reviews uncommitted working-tree changes and returns a list of issues with improvement suggestions. Handy right before you commit. CX Codex +1 1,300installs plan-task skill plan-task turns a rough task spec into a plan with acceptance criteria, an architecture overview and verifiable phases, each gated by a judge. CX Codex +1 1,300installs subagent-driven-development skill subagent-driven-development runs an implementation plan through fresh subagents and puts code review between tasks, so context stays clean and issues surface early. CX Codex +1 1,300installs

1–40 of 63

More in NeVibeCode

Project sponsors

Companies that keep this analytics open