Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Hub Builder

ASecurity

Build on and extend Claude Code Hub. Use when the user wants to patch or fork a built-in tool (Kanban, Cost, Marketplace, Memory), write a new app for a hub tab, connect apps through topics and actions, make a custom color theme, configure the hub (flags, config dirs, token), or fix a hub problem.

10 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentsrustsecurity

Works with

claude codeterminal

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/2/2026

$npx -y skills add NikiforovAll/claude-code-hub --skill hub-builder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hub Builder?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Hub Builder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nikiforovall-hub-builder/badge)](https://www.skillsdirectory.com/skills/nikiforovall-hub-builder)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: hub-builder
description: Build on and extend Claude Code Hub. Use when the user wants to patch or fork a built-in tool (Kanban, Cost, Marketplace, Memory), write a new app for a hub tab, connect apps through topics and actions, make a custom color theme, configure the hub (flags, config dirs, token), or fix a hub problem.
---

# Hub builder

Claude Code Hub runs Kanban, Cost, Marketplace and Memory as tabs of one window, and apps talk to it through the hub protocol. The docs site is the reference. Find the case below, fetch its page, and work from what the page says.

The site documents the latest stable release. When the user's hub behaves differently from a page, trust the installed hub and say which version it is (`npm ls -g claude-code-hub`).

## Docs

Base URL: `https://nikiforovall.blog/claude-code-hub/`

The files under `references/` ship with the installed hub, so they match its version. Read them before the site.

| Case | Page |
|---|---|
| Extend the hub: patch or fork a built-in tool, write a new app, configure the `apps` entry, the manifest, the SDK, topics, actions, capabilities | [`references/extensibility.md`](references/extensibility.md). It names the docs page for each part |
| The wire messages of the hub protocol | `reference/protocol/`, then `reference/architecture/` for processes and ports |
| Start the hub, open it with its token, install it as an app | `getting-started/` |
| Flags, environment variables, `config.json`, the files the hub writes | `reference/configuration/` |
| Switch between Claude config dirs | `guides/config-dirs/` |
| The hub token, or exposing the hub to a network | `reference/security/` |
| Keys the hub binds and keys the tools keep | `reference/shortcuts/` |
| The embedded terminal in Kanban | `guides/terminal/` |
| The project palette | `guides/projects/` |
| Something is broken | `reference/troubleshooting/` |
| Make a custom color theme, or change a built-in one | [`references/themes.md`](references/themes.md) |

Attribution

NikiforovAllNikiforovAll
View sourceSee grades on GitHubMore from NikiforovAll →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →