# 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.

63 cards · page 1 of 2

- HTML: https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [thought-based-reasoning](https://affpapa.org/en/nevibecode/skills/thought-based-reasoning.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1500 installs — 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.
- [prompt-engineering](https://affpapa.org/en/nevibecode/skills/neolabhq-prompt-engineering.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1500 installs — prompt-engineering guides prompt design for agents, subagents, and LLM integrations.
- [agent-evaluation](https://affpapa.org/en/nevibecode/skills/neolabhq-agent-evaluation.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — agent-evaluation is a Claude Code skill that provides rubrics and LLM-as-judge templates for evaluating agents, prompts, and skills by their outcomes.
- [memorize](https://affpapa.org/en/nevibecode/skills/memorize.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — memorize transfers insights from agent reflections and critique sessions into CLAUDE.md.
- [judge-with-debate](https://affpapa.org/en/nevibecode/skills/judge-with-debate.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — The judge-with-debate skill runs three independent judges who argue over a solution's score until they agree.
- [update-docs](https://affpapa.org/en/nevibecode/skills/update-docs.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — update-docs updates project documentation based on uncommitted git changes or the latest commit.
- [root-cause-tracing](https://affpapa.org/en/nevibecode/skills/root-cause-tracing.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — 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.
- [critique](https://affpapa.org/en/nevibecode/skills/critique.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — 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.
- [brainstorm](https://affpapa.org/en/nevibecode/skills/brainstorm.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — brainstorm turns rough project ideas into detailed specifications through guided dialogue.
- [multi-agent-patterns](https://affpapa.org/en/nevibecode/skills/multi-agent-patterns.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — multi-agent-patterns is a Claude Code skill for planning systems that split work across agents.
- [write-concisely](https://affpapa.org/en/nevibecode/skills/write-concisely.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — The write-concisely skill enforces classic style rules from William Strunk Jr.'s 1918 guide across human-facing docs.
- [reflect](https://affpapa.org/en/nevibecode/skills/neolabhq-reflect.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1400 installs — reflect — a skill that makes the agent reread its own answer and list the flaws before you accept the work.
- [apply-anthropic-skill-best-practices](https://affpapa.org/en/nevibecode/skills/apply-anthropic-skill-best-practices.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — apply-anthropic-skill-best-practices is a Claude Code skill for building skills with Anthropic’s authoring guidance.
- [create-agent](https://affpapa.org/en/nevibecode/skills/create-agent.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — create-agent scaffolds autonomous subagents for Claude Code with valid YAML frontmatter, isolated contexts, and triggering examples.
- [do-competitively](https://affpapa.org/en/nevibecode/skills/do-competitively.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — do-competitively runs three agents on the same task in parallel, scores their output with judges, then synthesizes the best result.
- [plan-do-check-act](https://affpapa.org/en/nevibecode/skills/plan-do-check-act.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — Walks your agent through four PDCA phases: plan, do, check, act.
- [commit](https://affpapa.org/en/nevibecode/skills/neolabhq-commit.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — Automates Git commits using conventional commit messages and matching emojis.
- [create-skill](https://affpapa.org/en/nevibecode/skills/neolabhq-create-skill.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — create-skill — a skill for Claude Code, Codex, Cursor and other agents that walks through writing a new skill using a TDD approach.
- [create-ideas](https://affpapa.org/en/nevibecode/skills/create-ideas.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — 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.
- [cause-and-effect](https://affpapa.org/en/nevibecode/skills/cause-and-effect.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — cause-and-effect runs structured Ishikawa diagram investigations on development bottlenecks.
- [fix-tests](https://affpapa.org/en/nevibecode/skills/fix-tests.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — fix-tests — a skill for Claude Code, Codex, Cursor and other platforms that repairs failing tests after business logic changes or refactoring.
- [test-prompt](https://affpapa.org/en/nevibecode/skills/test-prompt.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — test-prompt — a skill that runs the RED-GREEN-REFACTOR cycle on any prompt using isolated subagents.
- [tree-of-thoughts](https://affpapa.org/en/nevibecode/skills/tree-of-thoughts.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — tree-of-thoughts runs a hard task through three parallel agents, a pruning vote and a synthesis pass.
- [create-rule](https://affpapa.org/en/nevibecode/skills/create-rule.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — create-rule — a skill that walks you through writing a rule file in .claude/rules/ so your agent stops repeating the same mistake.
- [launch-sub-agent](https://affpapa.org/en/nevibecode/skills/launch-sub-agent.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — launch-sub-agent dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification.
- [do-and-judge](https://affpapa.org/en/nevibecode/skills/do-and-judge.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — 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 thresh…
- [review-pr](https://affpapa.org/en/nevibecode/skills/neolabhq-review-pr.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — review-pr reviews an open GitHub pull request and leaves inline comments on the diff.
- [analyse](https://affpapa.org/en/nevibecode/skills/analyse.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — analyse selects a Kaizen technique for your target, running code exploration via Gemba Walk, workflow reviews with VSM, or waste audits using Muda.
- [judge](https://affpapa.org/en/nevibecode/skills/judge.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — 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.
- [add-task](https://affpapa.org/en/nevibecode/skills/add-task.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — add-task turns your request into a task file under .specs/tasks/draft/, with a verb-first title, a type and your original wording.
- [do-in-parallel](https://affpapa.org/en/nevibecode/skills/do-in-parallel.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — do-in-parallel runs isolated tasks across separate files concurrently via sub-agents and validates work with automated judges.
- [analyse-problem](https://affpapa.org/en/nevibecode/skills/analyse-problem.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — The analyse-problem skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan.
- [do-in-steps](https://affpapa.org/en/nevibecode/skills/do-in-steps.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — 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.
- [setup-serena-mcp](https://affpapa.org/en/nevibecode/skills/setup-serena-mcp.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — setup-serena-mcp is a Claude Code skill that configures the Serena MCP server for semantic code exploration and symbol editing.
- [write-tests](https://affpapa.org/en/nevibecode/skills/write-tests.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — The write-tests skill reads your uncommitted and untracked git changes and writes tests for them.
- [implement-task](https://affpapa.org/en/nevibecode/skills/implement-task.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — implement-task runs a task step by step, one agent per step, then one reviewer per phase and fixes until it passes.
- [why](https://affpapa.org/en/nevibecode/skills/neolabhq-why.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — Conducts iterative Five Whys root cause analysis for technical bugs and incidents.
- [review-local-changes](https://affpapa.org/en/nevibecode/skills/review-local-changes.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — review-local-changes reviews uncommitted working-tree changes and returns a list of issues with improvement suggestions.
- [plan-task](https://affpapa.org/en/nevibecode/skills/plan-task.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — plan-task turns a rough task spec into a plan with acceptance criteria, an architecture overview and verifiable phases, each gated by a judge.
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/neolabhq-subagent-driven-development.md) — skill · NeoLabHQ · Claude Code, Codex, Cursor +5 · 1300 installs — subagent-driven-development runs an implementation plan through fresh subagents and puts code review between tasks, so context stays clean and issues surface early.

Next: https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md?page=2

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
