Agent skill

Update Component Reference

by NikiforovAll in NikiforovAll/claude-code-rules

This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

Apache-2.0Auto-check passedAgent Workflows

Install Update Component Reference

skills CLI
$ npx skills add NikiforovAll/claude-code-rules --skill update-component-reference -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NikiforovAll/claude-code-rules update-component-reference --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NikiforovAll/claude-code-rules.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/update-component-reference .claude/skills/update-component-reference && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
update-component-reference
GitHub stars
141
Token cost
~2.1k tokens
SKILL.md length
235 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
Apache-2.0

At a glance

This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

  • Works in 4 steps: Determine Target Directory → Determine sidebar_position → Create Component Documentation File → …
  • Wants to add components (commands
  • SKILL.md covers When to Use, Prerequisites Checklist, Implementation Process and Use Cases, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Update Component Reference is an agent skill from NikiforovAll/claude-code-rules. This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers, Hooks and plugins and Markdown. It works with Model Context Protocol. The repository describes itself as: Learn practical techniques to enhance your AI-assisted development workflow with Claude Code. The licence is Apache-2.0.

When your agent uses it

  • Wants to add components (commands
  • MCP servers) to the Component Reference section of the website

Example prompts

  • “/update-component-reference”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Determine Target Directory
  2. Determine sidebar_position
  3. Create Component Documentation File
  4. Write MDX Content

What it can do on your machine

Read from SKILL.md and the folder at commit 281c063. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mdx, json and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Component Reference loads about 2.1k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 235 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NikiforovAll/claude-code-rules at commit 281c063, republished under its Apache-2.0 licence (© NikiforovAll). 235 words, ~2,060 tokens.

Download SKILL.mdSave it as .claude/skills/update-component-reference/SKILL.md (or your agent's skills folder).
name
update-component-reference
description
This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

Update Component Reference Skill

Add documentation for Claude Code components (commands, agents, skills, hooks, MCP servers) to the website's Component Reference section.

When to Use

Use this skill when the user requests to:

  • Add a new component to the Component Reference documentation
  • Document a newly created command, agent, skill, hook, or MCP server
  • Update component documentation in the reference section

Prerequisites Checklist

Before documenting a component, ensure:

  1. Component exists in the appropriate plugin directory:

    • Commands: plugins/handbook/commands/{name}.md
    • Agents: plugins/handbook/agents/{name}.md
    • Skills: plugins/handbook/skills/{name}/SKILL.md
    • Hooks: plugins/{plugin-name}/hooks/hooks.json and hook scripts
    • MCP Servers: plugins/{plugin-name}/.mcp.json
  2. For skills only: Component is registered in plugin.json:

    json
    {
      "skills": [
        "./skills/skill-creator",
        "./skills/{new-skill-name}"
      ]
    }
  3. Verify plugin name: Check .claude-plugin/plugin.json for the badge (e.g., "handbook", "handbook-dotnet")

Implementation Process

Step 1: Determine Target Directory

Component documentation goes in: website/docs/component-reference/{type}/

  • Commands → website/docs/component-reference/commands/
  • Agents → website/docs/component-reference/agents/
  • Skills → website/docs/component-reference/skills/
  • Hooks → website/docs/component-reference/hooks/
  • MCP Servers → website/docs/component-reference/mcp-servers/

All category directories and _category_.json files already exist for these types.

Step 2: Determine sidebar_position

Read existing .mdx files in the target directory to find the highest sidebar_position and add 1.

Example:

bash
grep -h "sidebar_position:" website/docs/component-reference/skills/*.mdx | sort -n
Step 3: Create Component Documentation File

Filename convention: Use kebab-case matching the component name

  • Command /commit → commit.mdx
  • Agent @backend-architect → backend-architect.mdx
  • Skill skill-creator → skill-creator.mdx
  • Hook csharp-formatter → csharp-formatter.mdx
  • MCP Server context7 → context7.mdx
Step 4: Write MDX Content

Use the appropriate template based on component type:

Commands Template
mdx
---
title: "/command-name"
sidebar_position: N
---

import CommandNameSource from '!!raw-loader!../../../../plugins/handbook/commands/command-name.md'
import CodeBlock from '@theme/CodeBlock';

# Use `/command-name`

<span className="badge badge--handbook">handbook</span>

Brief description of what this command does (1-2 sentences).

More detailed explanation of the command's purpose and benefits.

## Command Specification

<CodeBlock language="markdown">
{CommandNameSource}
</CodeBlock>

## Additional sections as needed
- Example usage
- Tips and tricks
- Related commands
Agents Template
mdx
---
title: "@agent-name"
sidebar_position: N
---

import AgentNameSource from '!!raw-loader!../../../../plugins/handbook/agents/agent-name.md'
import CodeBlock from '@theme/CodeBlock';

# Use `@agent-name` agent

<span className="badge badge--handbook">handbook</span>

Brief description of what this agent specializes in (1-2 sentences).

More detailed explanation of the agent's capabilities and when to use it.

## Agent Specification

<CodeBlock language="markdown">
{AgentNameSource}
</CodeBlock>

## Additional sections as needed
- Key strengths
- Example use cases
- Related agents
Skills Template
mdx
---
title: "skill-name"
sidebar_position: N
---

import SkillNameSource from '!!raw-loader!../../../../plugins/handbook/skills/skill-name/SKILL.md'
import CodeBlock from '@theme/CodeBlock';

# Use `skill-name` skill

<span className="badge badge--handbook">handbook</span>

Brief description of what this skill provides (1-2 sentences).

More detailed explanation of the skill's purpose and capabilities.

## When to Use This Skill

Use the `skill-name` skill when you want to:

- Primary use case
- Secondary use case
- Additional scenarios

## Skill Specification

<CodeBlock language="markdown">
{SkillNameSource}
</CodeBlock>

## Additional sections as needed
- Key concepts
- Example workflows
- Related skills
Hooks Template
mdx
---
title: "Hook Name"
sidebar_position: N
---

# Hook Name

<span className="badge badge--{plugin-name}">{plugin-name}</span>

Brief description (1-2 sentences).

## Configuration

```json
{ hook config from hooks.json }

Use Cases

  • Bullet points

Installation

Setup notes.

  • Links

#### MCP Servers Template

```mdx
---
title: "server-name"
sidebar_position: N
---

# Server Name MCP Server

<span className="badge badge--{plugin-name}">{plugin-name}</span>

Brief description (1-2 sentences).

## Configuration

```json
{ config from .mcp.json }

Coverage

  • Bullet list

Example Usage

"Example query"

Installation

Setup notes.

  • Links

### Step 5: Verify Import Paths (Commands, Agents, Skills Only)

**Note**: Hooks and MCP Servers show configuration directly (no raw-loader imports needed).

For commands, agents, and skills, double-check the raw-loader import path:

- Commands: `'!!raw-loader!../../../../plugins/handbook/commands/{name}.md'`
- Agents: `'!!raw-loader!../../../../plugins/handbook/agents/{name}.md'`
- Skills: `'!!raw-loader!../../../../plugins/handbook/skills/{name}/SKILL.md'` ⚠️ Note the `/SKILL.md` suffix

The path goes up 4 directories (`../../../../`) from the `.mdx` file to reach the repo root.

## Common Pitfalls

1. **Forgetting plugin.json registration for skills**
   - Skills MUST be in plugin.json or they won't be available
   - Commands, agents, hooks, and MCP servers are auto-discovered

2. **Incorrect import paths**
   - Skills use `/SKILL.md` suffix: `skills/{name}/SKILL.md`
   - Commands and agents use `.md` directly: `commands/{name}.md`
   - Hooks and MCP servers don't use raw-loader (show config directly)

3. **Wrong relative path depth (commands, agents, skills only)**
   - Always use 4 levels up: `../../../../`
   - Path starts from the `.mdx` file location

4. **Inconsistent naming**
   - File names should match component names exactly (kebab-case)
   - Title in frontmatter should include prefix (`/` for commands, `@` for agents)

5. **Wrong plugin badge**
   - Badge class follows pattern: `badge--{plugin-name}`
   - Badge text is the plugin name (e.g., "handbook", "handbook-dotnet")

## Quick Reference

### Import Variable Naming Convention (Commands, Agents, Skills)
Match the component name in PascalCase + "Source":
- `commit.md` → `CommitCommandSource`
- `backend-architect.md` → `BackendArchitectAgentSource`
- `skill-creator/SKILL.md` → `SkillCreatorSource`

**Note**: Hooks and MCP servers don't use imports.

### Badge
Badge format: `<span className="badge badge--{plugin-name}">{plugin-name}</span>`

Examples:
- handbook: `<span className="badge badge--handbook">handbook</span>`
- handbook-dotnet: `<span className="badge badge--handbook-dotnet">handbook-dotnet</span>`

## Adding a New Plugin

When documenting components from a **new plugin**, also update:

1. **Badge CSS**: Add style to `website/src/css/custom.css` (pick unique color)
2. **Plugin index**: Add entry to `website/docs/plugins.md` (both main list and Direct Installation section)

## Example Workflow

**User**: "Add the new @pair-programmer agent to the documentation"

1. **Verify** component exists: `plugins/handbook/agents/pair-programmer.md` ✓
2. **Check** it's an agent (auto-discovered, no plugin.json needed) ✓
3. **Find** next sidebar_position in `website/docs/component-reference/agents/`
4. **Create** `website/docs/component-reference/agents/pair-programmer.mdx`
5. **Write** content using agent template
6. **Import** using: `'!!raw-loader!../../../../plugins/handbook/agents/pair-programmer.md'`
7. **Verify** documentation renders correctly

© NikiforovAll, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/update-component-reference of NikiforovAll/claude-code-rules.

Open the folder on GitHubat commit 281c063

Compare with similar skills

Update Component Reference next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Update Component Reference compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Component Reference this skillNikiforovAll/claude-code-rules141—~2.1kAutomated safety check: PassApache-2.0
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
OpenpetsOpenPetsHQ/openpets1.3k—~2.1kAutomated safety check: PassMIT
Claude Automation Recommenderanthropics/claude-plugins-official37k3 repos~2.7kAutomated safety check: NotesApache-2.0
Mistral Vibe Plugin Creatormistralai/mistral-vibe5.1k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Openpets

    OpenPetsHQ/openpets

    A skill your agent uses whenever the user wants to build, extend, debug, test, validate, locally load, package, or publish an OpenPets plugin; work with the OpenPets Plugin SDK v3, plugin manifest…

    1.3k GitHub stars~2.1k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Claude Automation Recommender

    anthropics/claude-plugins-official

    Official

    Scans a codebase and suggests which Claude Code hooks, subagents, skills, plugins and MCP servers fit its stack, without changing any files.

    37k GitHub starsUsed in 3 repos~2.7k tokens
    Agent WorkflowsAuto-check: notes
  • Mistral Vibe Plugin Creator

    mistralai/mistral-vibe

    Official

    Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.

    5.1k GitHub stars~3.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from NikiforovAll/claude-code-rules

All 26 skills in this repo
  • Reflect Solution

    NikiforovAll/claude-code-rules

    Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool…

    141 GitHub stars~3.8k tokensUpdated 5 days ago
    Auto-check passed
  • Dotnet Analyzers

    NikiforovAll/claude-code-rules

    Run dotnet format to fix code style and analyzer diagnostics (IDE0005, CA, SA).

    141 GitHub stars~1.9k tokensUpdated 5 days ago
    Auto-check passed
  • Ilspy Decompile

    NikiforovAll/claude-code-rules

    Understand implementation details of .NET code by decompiling assemblies.

    141 GitHub starsUsed in 2 repos~760 tokens
    Auto-check passed
  • Reflect Tree

    NikiforovAll/claude-code-rules

    Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections…

    141 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed
  • Structured Plan Mode

    NikiforovAll/claude-code-rules

    This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition.

    141 GitHub stars~4.2k tokensUpdated 5 days ago
    Auto-check passed
  • Glab

    NikiforovAll/claude-code-rules

    Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line.

    141 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Categories

Questions about Update Component Reference

What does Update Component Reference do?

This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website. Update Component Reference is an agent skill from NikiforovAll/claude-code-rules. This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.

When should I use Update Component Reference?

Update Component Reference fits situations like: wants to add components (commands; MCP servers) to the Component Reference section of the website.

How do I install Update Component Reference in Claude Code?

Run `npx skills add NikiforovAll/claude-code-rules --skill update-component-reference -a claude-code`. Or copy the skill folder (.claude/skills/update-component-reference in NikiforovAll/claude-code-rules) into .claude/skills/update-component-reference in your project. Claude Code loads it when a task matches its description.

How do I install Update Component Reference in Codex?

Run `npx skills add NikiforovAll/claude-code-rules --skill update-component-reference -a codex`. Or copy the skill folder (.claude/skills/update-component-reference in NikiforovAll/claude-code-rules) into .agents/skills/update-component-reference in your project. Codex loads it when a task matches its description.

Can I use Update Component Reference in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NikiforovAll/claude-code-rules --skill update-component-reference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-component-reference, .gemini/skills/update-component-reference, .github/skills/update-component-reference and .opencode/skills/update-component-reference in your project.

What does Update Component Reference need to run?

SKILL.md names no scripts, command-line tools or credentials: Update Component Reference is instructions for the agent only.

Does Update Component Reference access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Update Component Reference safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Update Component Reference use?

Update Component Reference is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Component Reference use?

About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Component Reference?

Skills that share tags, products or a category with Update Component Reference: MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars), Crush Configuration (charmbracelet/crush, 29k stars), Openpets (OpenPetsHQ/openpets, 1.3k stars) and Claude Automation Recommender (anthropics/claude-plugins-official, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Component Reference?

NikiforovAll (a GitHub user) maintains it in NikiforovAll/claude-code-rules, which has 141 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.

Source: NikiforovAll/claude-code-rules on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.