template-library – Documents & Office skill for AI agents
Template register: name, type, owning module and department, owner, last updated and content link. Use for document template governance.
Install the template-library skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/template-library-ddd0e.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /template-library – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/template-library-ddd0e.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $template-library – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/template-library-ddd0e.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /template-library – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/template-library-ddd0e.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /template-library – then describe the task you want done.
SKILL.md content
Template Library
What it is: Central templates.
Overview
Works out the smallest useful Template Library 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 7: Protect. Fits: Growth stage. Table code: n/a.
When to Use This Skill
- document template library
- template repository
- policy template store
Also use it when the user says "central templates", 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: Which documents do you write repeatedly?
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.
- Templates - Which documents? / How many? / Used by one person or many?
- Structure - Fields fixed or variable? / Any required sections? / Standard naming?
- Ownership - Who approves changes? / Version kept? / Where published?
- Current process - Where do templates live now? / Email attachments or a drive? / Which version is current?
- Outcome - What do you need? / A library, a naming rule or a review cycle?
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: template-library
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Templates": null
"Structure": 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 askingStep 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: Keep one current version per template with a named owner, and start the library with the documents people actually reuse.
Why this one: Template libraries sprawl when every variant is kept. Keep one current version and an explicit owner, and archive the rest.
Workflow: Template catalogued → Fields defined → Approved version → Published → Usage or update
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.
Template Name,Template Type,Module,Department,Owner,Last Updated,Content Link,Status,Template ID
Invoice Template,Checklist,Invoices & Billing,Delivery,Sneha Iyer,2026-01-15,https://example.com/template,Published,CREATE TABLE template_library (
template_name VARCHAR(255),
template_type VARCHAR(100) NOT NULL,
module VARCHAR(255),
department VARCHAR(255),
owner VARCHAR(255),
last_updated DATE NOT NULL,
content_link TEXT,
status VARCHAR(100) NOT NULL,
template_id SERIAL PRIMARY KEY,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_template_library_status ON template_library (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Template Library",
"type": "object",
"additionalProperties": false,
"properties": {
"Template Name": { "type": "string" },
"Template Type": { "type": "string" },
"Module": { "type": "string" },
"Department": { "type": "string" },
"Owner": { "type": "string" },
"Last Updated": { "type": "string", "format": "date" },
"Content Link": { "type": "string", "format": "uri" },
"Status": { "type": "string" },
"Template ID": { "type": "integer" }
},
"required": [
"Template Type",
"Last Updated",
"Status"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Template Name | Title | Use as the database title |
| Template Type | Select (add options after import) | Convert to Select, add options: "Policy", "Process", "Checklist", "Contract", "Report", "Invoice" |
| Module | Text | Leave as Text |
| Department | Text | Leave as Text |
| Owner | Text | Leave as Text |
| Last Updated | Date | Convert to Date |
| Content Link | URL | Convert to URL |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "In Review", "Published", "Retired" |
| Template 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 | Template Name | text | VARCHAR(255) | string | Text | Invoice Template |
| 2 | Template Type | select | VARCHAR(100) | string | Select (add options after import) | Checklist |
| 3 | Module | text | VARCHAR(255) | string | Text | Invoices & Billing |
| 4 | Department | text | VARCHAR(255) | string | Text | Delivery |
| 5 | Owner | text | VARCHAR(255) | string | Text | Sneha Iyer |
| 6 | Last Updated | date | DATE | string, format: date | Date | 2026-01-15 |
| 7 | Content Link | url | TEXT | string, format: uri | URL | https://example.com/template |
| 8 | Status | select | VARCHAR(100) | string | Select (add options after import) | Published |
| 9 | Template ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |
Select Options
Template Type
Policy | Process | Checklist | Contract | Report | InvoiceStatus
Draft | In Review | Published | RetiredRelations
Link fields: none
Examples
Prompt
Half the team uses an old version of the proposal template.Context first - one question per message, nothing already answered:
> Q: Which documents?
> A: Proposals, invoices and handover notes.
>
> Q: How many?
> A: Maybe fifteen.
>
> Q: Where do they live?
> A: Email attachments and a drive.
Recommended next step - offered, not built:
> Keep one current version per template with a named owner, and start the library with the documents people actually reuse.
>
> Workflow: Template catalogued → Fields defined → Approved version → Published
… (full content is in the download package)
Related skills
- unpaid-intern – A free second brain for work in plain markdown files the user owns. Turns transcripts…
- url-to-markdown – Fetch a public webpage as clean Markdown for an agent: read, summarize, quote, or cite…
- verify-document – Check whether a document (PDF or image) shows signs of tampering or forgery before you…
- weaviate-cookbooks – Build Weaviate AI apps from official cookbook blueprints for RAG, agentic RAG, data…
- wiki-builder – Create and maintain reusable research wikis with source provenance, configurable…
- wiki-vitepress – Transform generated wiki Markdown files into a polished VitePress static site with dark…
- wiki-yylo – Use YYLO Ledger wiki Records as durable project knowledge. Search before creating…
- word-count-structure-checker – Word Count & Structure Checker. Use when working with text or structured article.