Skip to main content
affpapa.org
RU EN
skill CX Codex

analyse — Claude Code skill: what it does, how to install

Selects a Kaizen technique for your target, running code exploration via Gemba Walk, workflow reviews with VSM, or waste audits using Muda.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NeoLabHQ/context-engineering-kit --skill analyse -a claude-code
Open on GitHub

What analyse does

The skill inspects your input target and assigns the matching Kaizen review technique. It uses a Gemba Walk to inspect actual code paths, Value Stream Mapping to trace multi-stage delivery pipelines, or Muda analysis to spot technical debt. You can override the automatic selection by supplying the METHOD variable with gemba, vsm, or muda.

Execution follows a five-step sequence. The assistant identifies the target, explains why the method applies, walks you through the inspection, and delivers findings with actionable next steps. During a Gemba Walk, it compares prior assumptions against real implementation details, surfacing hidden dependencies and documentation drifts.

If you trigger the command without an argument, the assistant prompts for a target. Manually forcing the method prevents classification missteps when your review touches both application logic and CI/CD automation at the same time.

What it helps with

  • trace gaps between written documentation and actual code implementation
  • map deployment pipelines to locate bottlenecks and idle handoff times
  • pinpoint code duplication, over-engineering, and technical debt
  • explore legacy components before scheduling refactoring work

Example prompts for the agent

  • /analyse authentication implementation
  • /analyse deployment workflow
  • /analyse codebase for inefficiencies

How to install analyse

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill analyse -a claude-code

2Manually: put the files in place

~/.claude/skills/analyse/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/analyse/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about analyse

How to install analyse in Claude Code?

Run npx skills add NeoLabHQ/context-engineering-kit --skill analyse -a claude-code to install the skill for Claude Code. Alternatively, place the skill file directly at ~/.claude/skills/analyse/SKILL.md.

What does the analyse skill do?

It evaluates what you want to inspect and guides you through an appropriate Kaizen technique. Depending on the target, it runs a code-level Gemba Walk, a process-oriented Value Stream Map, or a Muda waste assessment.

Can you override the automatic method selection?

Yes, set the METHOD variable to gemba, vsm, or muda to bypass automatic selection and enforce your preferred Kaizen technique.

Similar skills

Everything for Code review and refactoring →
production-audit affaan-m Checks whether an app is ready to ship and what will break in production. Runs on local evidence, so repo data stays on your machine. CX Codex +1 4,700installs code-security semgrep Security guidelines for writing safe code and catching vulnerabilities across 15+ languages. Helps inspect database queries, network calls, and infrastructure configurations. CX Codex +1 2,600installs pohuy smixs pohuy makes agent replies use idiomatic Russian profanity while keeping technical details exact. Use it for debugging, reviews, logs, and deployments. CX Codex +1 738installs operating-kit Sharrmavishal A set of agents for the whole working cycle: session start and end, pre-ship code review, deploy with live verification, and production log checks. CX Codex ★ 41,729repo stars github-actions-hardening official github Reviews .github/workflows/*.yml against the Actions threat model linters miss: attacker-controlled text pasted into run:, privileged triggers running fork code, unpinned actions. 2,200installs groove-utilities-task-analyse andreadellacorte Pulls tasks from your project backend and groups them by status, so you have something to write into daily memory. CX Codex +1 588installs

From the same set55

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 1,200installs 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 1,200installs launch-sub-agent Dispatches a focused sub-agent with isolated context, automated model routing, and mandatory self-critique verification. CX Codex +1 1,200installs do-and-judge This skill sends a task to an implementation sub-agent, checks the result with an independent judge, and retries with feedback when needed. CX Codex +1 1,200installs judge The 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 1,200installs 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 1,200installs 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 1,200installs analyse-problem This skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor