{"slug":"setup-knowledge-base","title":"setup-knowledge-base","summary":"Interactive onboarding to create a structured knowledge base. Defines categories, scaffolds the directory structure, creates the index, and optionally imports initial content. Run this first before using /kb-answer or /kb-import.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-30T16:42:42.67146Z","repo":{"url":"https://github.com/techwolf-ai/ai-first-toolkit","stars":129,"forks":5,"license":"MIT","updatedAt":"2026-09-29T14:43:16Z"},"bodyHtml":"
\n

name: setup-knowledge-base\ndescription: |\nInteractive onboarding to create a structured knowledge base. Defines categories,\nscaffolds the directory structure, creates the index, and optionally imports initial content.\nRun this first before using /kb-answer or /kb-import.

\n

Knowledge Base Setup

\n

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

\n

When to Use

\n\n

Step 1: Discover Purpose

\n

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

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

Example category suggestions by domain:

\n\n

Step 2: Confirm Plan

\n

Before creating anything, present the plan to the user:

\n
I'll create this structure in your project:\n\nkb/\n  .kb-config.yaml\n  index.md\n  scopes/\n    _default.yaml\n    README.md\n  {category1}/\n  {category2}/\n  {category3}/\nscripts/\n  kb-index.py\n  kb-verify.py\n  kb-validate.py\n  kb-search.py\nCLAUDE.md (or append to existing)\n\nReady to proceed?\n
\n

Wait for user confirmation.

\n

Step 3: Scaffold the KB

\n

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

\n
    \n

  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.

    \n
    2. \n

  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:

    \n
    | encryption, certificates, access | security/ |\n| API, architecture, deployment | technical/ |\n
    \n
    3. \n

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

    \n
    4. \n

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

    \n
    5. \n

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

    \n
    6. \n

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

    \n
    7. \n

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

    \n
    8. \n

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

    \n
    9. \n

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

    \n
    10. \n
\n

Step 4: Create Project CLAUDE.md

\n

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.

\n

Step 5: Populate from Sources

\n

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

\n

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

\n\n

Step 6: Verify

\n

Run the index script to confirm everything is wired up:

\n
python3 scripts/kb-index.py\n
\n

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

\n
python3 scripts/kb-index.py --write\n
\n

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

\n
python3 scripts/kb-validate.py\n
\n

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

\n

Step 7: Summary

\n

Tell the user:

\n\n","files":[{"path":"SKILL.md","sizeBytes":4860,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-30T16:43:28.594835Z","sha256":"77BEBDDC6951BC82BC7F7D0935CE9598465619EA7D3C192965D5A4BD3E5B4A39","sizeBytes":2018},"review":null,"source":{"repositoryUrl":"https://github.com/techwolf-ai/ai-first-toolkit","path":"plugins/knowledge-base/skills/setup-knowledge-base","license":"MIT","commit":"2ee78415674eaaead2082a55691b68ffb1003e87","subtreeSha":"0B3A38BCC577F1D05ACD991941DDAA79F978FE3EC76FEE582F44E2332231263C","lastSyncedAt":"2026-09-30T16:42:38.836652Z"},"reviewedAt":"2026-09-30T16:44:57.816412Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/knowledge-base/skills/setup-knowledge-base"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install techwolf-ai-ai-first-toolkit@llmmart"},{"target":"git","command":"git clone https://github.com/techwolf-ai/ai-first-toolkit.git"}]}