Skip to main content
ClaudeWave
ES, Spanish
Skill136 estrellas del repoactualizado 29d ago

setup-knowledge-base

setup-knowledge-base automates the creation of a structured knowledge base system within a project by guiding users through discovering the KB's purpose, intended audience, and logical categories before scaffolding the necessary directories, configuration files, and Python utility scripts. Use this when starting a new knowledge base from scratch or adding one to an existing project that needs organized, evidence-backed documentation management.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit /tmp/setup-knowledge-base && cp -r /tmp/setup-knowledge-base/plugins/knowledge-base/skills/setup-knowledge-base ~/.claude/skills/setup-knowledge-base
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Knowledge Base Setup

Interactive setup that creates a structured, evidence-backed knowledge base in your project.

## When to Use

- Starting a new knowledge base from scratch
- Adding a KB to an existing project

## Step 1: Discover Purpose

Ask the user (one question at a time, use AskUserQuestion):

1. **What is this KB for?** (e.g., product documentation, security/compliance, company knowledge, sales enablement, internal policies)
2. **Who will query it?** (e.g., you personally, your team, AI agents answering questions)
3. **What categories make sense?** Suggest 3-5 based on the domain, let the user adjust.

Example category suggestions by domain:
- **Product docs**: technical, integrations, deployment, security, faq
- **Company knowledge**: general, policies, processes, teams, faq
- **Sales enablement**: product, competitive, customer-success, pricing, faq
- **Security/compliance**: security, compliance, technical, general, faq

## Step 2: Confirm Plan

Before creating anything, present the plan to the user:

```
I'll create this structure in your project:

kb/
  .kb-config.yaml
  index.md
  scopes/
    _default.yaml
    README.md
  {category1}/
  {category2}/
  {category3}/
scripts/
  kb-index.py
  kb-verify.py
  kb-validate.py
  kb-search.py
CLAUDE.md (or append to existing)

Ready to proceed?
```

Wait for user confirmation.

## Step 3: Scaffold the KB

Read the template files from this plugin and adapt them for the user's project:

1. **Read** `templates/kb/.kb-config.yaml` from this plugin. Create `kb/.kb-config.yaml` in the user's project, replacing the placeholder categories with the ones chosen in Step 1. Replace `{{today}}` with today's date.

2. **Read** `templates/kb/index.md` from this plugin. Create `kb/index.md`, adding seed keywords for each chosen category. For example, if the user chose "security" and "technical", add initial keyword entries:

   ```
   | encryption, certificates, access | security/ |
   | API, architecture, deployment | technical/ |
   ```

3. **Read** `templates/kb/scopes/_default.yaml` from this plugin. Copy to `kb/scopes/_default.yaml`.

4. **Read** `templates/kb/scopes/README.md` from this plugin. Copy to `kb/scopes/README.md`.

5. Create empty directories for each chosen category: `kb/{category1}/`, `kb/{category2}/`, etc.

6. **Read** `scripts/kb-index.py` from this plugin. Copy to `scripts/kb-index.py` in the user's project.

7. **Read** `scripts/kb-verify.py` from this plugin. Copy to `scripts/kb-verify.py` in the user's project.

8. **Read** `scripts/kb-validate.py` from this plugin. Copy to `scripts/kb-validate.py` in the user's project.

9. **Read** `scripts/kb-search.py` from this plugin. Copy to `scripts/kb-search.py` in the user's project.

## Step 4: Create Project CLAUDE.md

**Read** `templates/CLAUDE.md` from this plugin. Create (or append to existing) `CLAUDE.md` in the user's project root. Replace `{{category}}` placeholders with the actual categories chosen in Step 1.

## Step 5: Populate from Sources

The KB structure is ready, but empty. Ask the user:

**"Do you have existing knowledge sources you'd like to import? (Notion pages, Slack channels, Confluence, local files)"**

- If **yes**: run `/kb-refresh` to populate the KB from those sources. It handles source discovery, scraping, and entry creation.
- If **no** or **skip**: create one example entry in the first category to demonstrate the format. **Read** `templates/kb/example/sample-entry.md` from this plugin for the format, but write an entry relevant to the user's domain rather than copying the sample.

## Step 6: Verify

Run the index script to confirm everything is wired up:

```bash
python3 scripts/kb-index.py
```

Regenerate the "All Files by Category" section of `kb/index.md` from the current entries:

```bash
python3 scripts/kb-index.py --write
```

Validate KB health (frontmatter, categories, related links):

```bash
python3 scripts/kb-validate.py
```

If `kb-index.py` lists the entries and `kb-validate.py` reports "All entries valid", setup is complete.

## Step 7: Summary

Tell the user:
- What was created and where
- How to add new entries (create .md files with YAML frontmatter in the right `kb/{category}/` folder; nested sub-folders like `kb/security/access/` are supported)
- How to query the KB (`/kb-answer`)
- How to import documents or bulk-import a directory (`/kb-import`)
- How to add more sources or refresh existing ones (`/kb-refresh`)
- How to list all entries (`python3 scripts/kb-index.py`)
- How to search (`python3 scripts/kb-search.py "keyword"`)
ai-firstifySkill

Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, improve, 'ai-firstify', or start a new project. Performs deep analysis across 7 dimensions, actively restructures existing projects, or guides new project setup through discovery questions. Based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp.

analyze-performanceSkill

Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.

brainstorm-linkedinSkill

Generate LinkedIn post ideas from external sources (files, URLs, research). Use when the user provides source material (PDFs, URLs, articles) to brainstorm topics. NOT for writing or developing drafts - use write-linkedin-post instead.

brainstorm-opinionSkill

Generate opinion piece ideas from recent LinkedIn posts (last 30 days). Use when asked to find opinion topics, brainstorm article ideas, or cross-pollinate content between LinkedIn and opinion pieces.

build-mcpSkill

Build an MCP server end to end, tailored to how it will be used. Use when asked to build an MCP, create an MCP server, wrap an API as a tool, make a tool for Claude, expose a service to an agent, build a Claude connector, or turn a service into MCP tools. Asks up front who the server is for (just me, my org, or public) and what it wraps, then walks through analyze, build, deploy, scale, and distribute with steps tailored to that answer. Builds on the example-skills:mcp-builder skill for implementation depth.

content-studioSkill

Entry point for the TechWolf content-studio plugin. Use to understand the workflow, pick the right content skill, or start setup for a new author/repository.

customer-statusSkill

Synthesised view of account health and activity for managers overseeing customer-facing teams (Sales, CS, Professional Services, Presales). Scans project channels, email threads, and Notion pages to surface status, risks, and upcoming milestones, without requiring the manager to trawl through individual channels. Supports proactive account management.

kb-answerSkill

|