Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

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

Explores codebase architecture and runtime execution paths before you edit code. Helps determine module ownership, layering, and placement for new features.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add cursor/plugins --skill how -a claude-code
Open on GitHub

What how does

The skill inspects codebases to answer architectural and operational questions. It produces a walkthrough suited for an onboarding engineer without turning into an annotated line-by-line code dump. For understanding the historical rationale behind decisions, the documentation recommends using the why skill instead.

Execution depends on complexity. Narrow questions run through a single explainer subagent. Broader cross-cutting features get split into two to four distinct angles, handing exploration to parallel Task subagents before synthesizing findings into standard sections: Overview, Key Concepts, How It Works, Where Things Live, and Gotchas.

Every spawned subagent runs with readonly: true, keeping repository files untouched during codebase exploration. Model assignments pull from the pstack-models.mdc rule, defaulting to grok-4.7-xhigh-fast for exploration and claude-opus-5-5-xhigh for explanation.

What it helps with

  • build a mental model of an unfamiliar subsystem
  • decide which package or layer should own new logic
  • trace cross-service execution flow before refactoring
  • identify architectural gotchas across complex code paths

Example prompts for the agent

  • How does the authentication subsystem work across modules?
  • Which package owns webhook validation, and is this the right layer?
  • Walk me through the billing subsystem architecture before I change it.

How to install how

1Skills CLI (Vercel)

npx skills add cursor/plugins --skill how -a claude-code

2Manually: put the files in place

~/.claude/skills/how/SKILL.md

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

From the same set18

The whole set →
unslop cursor This skill removes common AI writing patterns, filler, and vague phrasing while keeping the meaning and intended tone. Use it when polishing text. Claude Code CX Codex Cursor +1 27,700installs thermo-nuclear-code-quality-review cursor Runs a strict maintainability audit of code changes, abstractions, large files, and branching complexity. Use it when a routine review needs deeper structural scrutiny. Claude Code CX Codex Cursor +1 22,200installs deslop cursor Inspects branch diffs against main to remove AI-generated code clutter and inconsistent styling. Ideal for polishing branch changes before pull request review. Claude Code CX Codex Cursor +1 9,300installs why cursor The skill investigates why code took its current shape by checking Git history and available MCP sources, then returns cited findings about decisions and tradeoffs. Claude Code CX Codex Cursor +1 5,700installs fix-merge-conflicts cursor Resolves merge conflicts in a branch, then checks the build and tests before wrapping up. Use it when several conflicted files need focused fixes without a refactor. Claude Code CX Codex Cursor +1 2,700installs thermo-nuclear-review cursor A skill for comprehensive analysis of branch changes: checks code for bugs, broken functionality, security vulnerabilities, and feature-gate leaks. Use when you need thorough review before merge. Claude Code CX Codex Cursor +1 2,700installs review-and-ship cursor This skill automates code review before shipping: checks for bugs, tests, and intent fit, then commits and opens a PR. Use it to verify your work is ready before merge. Claude Code CX Codex Cursor +1 2,500installs weekly-review cursor This skill pulls your commits from the past 7–10 days, groups them by work type, and produces a brief report for status updates and retrospectives. Requires a configured git with email set. Claude Code CX Codex Cursor +1 2,400installs

Similar

orca-jira stablyai This skill handles Jira work through Orca CLI: JQL search, workflow transitions, completion comments with PR or MR links, and follow-up issues. Claude Code CX Codex Cursor +1 580installs block-no-verify-hook cskwork This skill adds a PreToolUse hook that blocks git bypass flags such as --no-verify. Use it when pre-commit checks must run before an agent can execute a command. Claude Code CX Codex Cursor 6,500installs angular-new-app Angular Team @ Google A skill that scaffolds new Angular applications via the Angular CLI. Verifies your setup, generates the project with appropriate flags, and steers you toward Angular best practices. Claude Code CX Codex Cursor +1 19,200installs seedance-prompt-en dexhunter A skill for writing prompts to Seedance 2.0, ByteDance's video generator. Use it when you create videos from text, images, video and audio via the @ reference system. Claude Code CX Codex Cursor +1 3,100installs hermes-agent-skill-authoring Hermes Agent Guides you through authoring Hermes Agent SKILL.md files in a repository, including frontmatter and layout. Useful when a skill must ship with the package. Claude Code CX Codex Cursor +1 516installs build-graph tirth8205 Builds or updates a repository knowledge graph for code review. Use it during first setup, after a branch switch, or following a large refactor. Claude Code CX Codex Cursor +1 1,300installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about how

How to install how in Claude Code?

Run npx skills add cursor/plugins --skill how -a claude-code in your terminal.

What does the how skill do?

It investigates code repositories using Task subagents to produce architectural walkthroughs, component ownership maps, and subsystem overviews.

Which models does how use for subagents?

It reads definitions from the pstack-models.mdc rule. Defaults are grok-4.7-xhigh-fast for explorer subagents and claude-opus-5-5-xhigh for the explainer.

See also

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