knowledge-base – skill Viết lách & Nội dung cho agent AI

Knowledge Base

What it is: Searchable repository.

Overview

Works out the smallest useful Knowledge Base setup for the business in front of it, then

builds it only when asked. The default output is a short recommendation, not a

spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on

request, from one field list so they cannot drift apart.

Layer: Layer 5: Develop. Fits: Scale stage. Table code: n/a.

When to Use This Skill

• knowledge base
• company wiki articles
• help center database
• internal documentation index

Also use it when the user says "searchable repository", or describes the same process happening in a

spreadsheet, a document or someone inboxes.

Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces

empty templates only - it never holds or processes real employee or customer data.

How It Works

Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.

Step 1 - Identify intent

Read the request and pick the intent before asking anything.

• "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
• "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
• "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
• "how do I ..." -> advice question; answer directly and offer the build only if it helps.

Ask only if this is the highest-value missing fact; otherwise proceed without an opener:

> Q: What is hardest to find today?

Step 2 - Ask only what is missing

Skip anything the user already answered, in any earlier message. Ask the rest one at a

time, and stop as soon as the remaining answers would not change the output.

• Content - What documents? / How many? / Who writes them?
• Findability - How do people search now? / Tags or folders? / Internal only?
• Ownership - Who reviews? / Review cycle? / Outdated content removed?
• Current process - Where does content live now? / Drive, Notion or wiki? / What is missing?
• Outcome - What do you need? / An index, a structure or authoring rules?

Never invent an answer. If the user does not know, record it as unknown and carry on.

Step 3 - Hold the internal context

Hold the answers in this shape. It stays internal - it is not shown to the user unless

they ask, and it never carries a value the user did not give.

module: knowledge-base
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Content": null
  "Findability": null
  "Ownership": null
  "Current process": null
  "Outcome": null
requested_outputs: []   # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: []     # only what the user actually said
open_questions: []      # the unanswered ones, in the order worth asking

Step 4 - Recommend the smallest workflow

If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.

Recommended approach: Start with an index of what exists and who owns it, then fix findability. Writing missing content comes after.

Why this one: Knowledge bases die from unclear ownership, not from missing articles. A named owner and a review date per page is the minimum.

Workflow: Content capture → Owner → Tag and structure → Search → Review cycle

Step 5 - Build only on request

Once the user asks for it, derive the fields from the confirmed context and emit the

requested artifacts. For machine-readable text, keep prose outside the data; for files,

provide a usable link. Report material validation failures or limitations separately.

**A selected Notion output is rendered by notion-manual-import, so route the

Notion step there.** When the user selects Notion, hand that step to

@notion-manual-import: it holds the CSV, the property

mapping, the import steps and the verification checklist, and it renders the Field

Reference below instead of defining a table of its own. Do not restate the mapping

here and do not improvise the import steps. Manual CSV and mapping outputs need no

connection. For requested workspace changes, follow the shared contract: verify actual

tool access and the target before writing. A user saying "connected" is not tool evidence.

Never ask for a Notion password or token.

For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the

text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user

requests a workbook.

A CSV carries no types, so after it, name the columns

that need a number, date or currency format applied.

Article Title,Category,Department,Owner,Tags,Summary,Linked SOP,Audience,Last Reviewed,Next Review,Status,Article ID
How we raise an invoice,Process,Delivery,Sneha Iyer,"process, finance","How we raise an invoice, reviewed in January.",SOP-ONB-001,All employees,2026-01-15,2026-01-15,Published,

CREATE TABLE knowledge_base (
  article_title VARCHAR(255),
  category VARCHAR(100) NOT NULL,
  department VARCHAR(255),
  owner VARCHAR(255),
  tags VARCHAR(255),
  summary TEXT,
  linked_sop VARCHAR(255),  -- relation -> target record
  audience VARCHAR(255),
  last_reviewed DATE,
  next_review DATE NOT NULL,
  status VARCHAR(100) NOT NULL,
  article_id SERIAL PRIMARY KEY,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

CREATE INDEX idx_knowledge_base_status ON knowledge_base (status);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Knowledge Base",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Article Title": { "type": "string" },
      "Category": { "type": "string" },
      "Department": { "type": "string" },
      "Owner": { "type": "string" },
      "Tags": { "type": "string" },
      "Summary": { "type": "string" },
      "Linked SOP": { "type": "string" },
      "Audience": { "type": "string" },
      "Last Reviewed": { "type": ["string", "null"], "format": "date" },
      "Next Review": { "type": "string", "format": "date" },
      "Status": { "type": "string" },
      "Article ID": { "type": "integer" }
  },
  "required": [
      "Category",
      "Next Review",
      "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Article Title | Title | Use as the database title |
| Category | Select (add options after import) | Convert to Select, add options: "Process", "How To", "Policy", "Template", "Reference", "FAQ" |
| Department | Text | Leave as Text |
| Owner | Text | Leave as Text |
| Tags | Text | Leave as Text |
| Summary | Text | Leave as Text |
| Linked SOP | Relation (link to the target database) | Convert to Relation, link to the target database |
| Audience | Text | Leave as Text |
| Last Reviewed | Date | Convert to Date |
| Next Review | Date | Convert to Date |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "In Review", "Published", "Archived" |
| Article ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |

The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays currency, dates stay date,

and anything pointing at another table stays relation.

Field Reference

| # | Field | Type | SQL | JSON Schema | Notion | CSV example |

|---:|---|---|---|---|---|---|

| 1 | Article Title | text | VARCHAR(255) | string | Text | How we raise an invoice |

| 2 | Category | select | VARCHAR(100) | string | Select (add options after import) | Process |

| 3 | Department | text | VARCHAR(255) | string | Text | Delivery |

| 4 | Owner | text | VARCHAR(255) | string | Text | Sneha Iyer |

| 5 | Tags | text | VARCHAR(255) | string | Text | process, finance |

| 6 | Summary | long_text | TEXT | string | Text | How we raise an invoice, reviewed in January. |

| 7 | Linked SOP | relation | VARCHAR(255) | string | Relation (link to the target database) | SOP-ONB-001 |

| 8 | Audience | text | VARCHAR(255) | string | Text | All employees |

| 9 | Last Reviewed | date | DATE | string, format: date | Date | 2026-01-15 |

| 10 | Next Review | date | DATE | string, format: date | Date | 2026-01-15 |

| 11 | Status | select | VARCHAR(100) | string | Select (add options after import) | Published |

| 12 | Article ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |

Select Options

Category

Process | How To | Policy | Template | Reference | FAQ

Status

Draft | In Revie

… (nội dung đầy đủ có trong gói tải về)