Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Documents

ASecurity

Create and convert DOCX documents — contracts, policies, memoranda, letters, term sheets, opinions, press releases, and more. Also converts markdown ↔ DOCX. Use this skill for any Word-document task. For presentations (PPTX) use the presentations skill; for spreadsheets (XLSX) use the spreadsheets skill.

16 stars
0 votes
0 copies
0 views
Added 6/8/2026
ai-agentsgobashgitapi

Works with

api

Security Analysis

A100/100

Scanned 6/8/2026

$npx -y skills add ThomasMoreAI/legal-skills-open --skill documents --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Documents?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Documents
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thomasmoreai-documents/badge)](https://www.skillsdirectory.com/skills/thomasmoreai-documents)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: documents
title: Documents Skill
description: Create and convert DOCX documents — contracts, policies, memoranda, letters, term sheets, opinions, press releases, and more. Also converts markdown ↔ DOCX. Use this skill for any Word-document task. For presentations (PPTX) use the presentations skill; for spreadsheets (XLSX) use the spreadsheets skill.
author: firelex
author_url: https://github.com/firelex/open_teamsuzie/tree/main/packages/skills/templates/documents
license: MIT
version: 0.1.0
execution_mode: open
jurisdiction: general
practice: general
language: en
---

# Documents Skill

Everything Word-document-related lives behind one base URL. Three operations: **Draft**, **Markdown → DOCX**, **DOCX → Markdown**.

## Which operation should I use?

You have two ways to produce a new Word document:

1. **Draft it yourself in markdown, then use §2 Markdown → DOCX to convert.** Good for short or simple documents where you're confident in the structure yourself — quick notes, a letter, a one-page summary, an internal update.

2. **Use §1 Draft.** This runs the request through a structured drafting pipeline that's particularly well-suited for **legal and regulatory documents and other complex documents spanning many pages** — contracts, policies, memoranda, engagement letters, term sheets, opinions, press releases, and similar. It produces a properly-templated DOCX in one call.

   **When you use §1 Draft, include an appropriately detailed description in the `instructions` field** — the drafting pipeline works best with rich context (parties, dates, key terms, tone, length, etc.) rather than a one-line prompt.

Use §3 DOCX → Markdown to read or summarize an existing DOCX the user hands you.

## Operation types

- **Async** (Draft) — you get a `job_id` immediately; a webhook fires on completion (30–120s).
- **Sync** (Markdown → DOCX, DOCX → Markdown) — server returns the final response within a single request/response.

Both kinds share the **same download flow**: server returns `{ job_id, download_url, filename }`, you fetch the URL, save to workspace, attach the file. Never paste document contents directly into chat — always download to the workspace and attach as a file.

## Base URL

```
{{DOCX_AGENT_URL}}
```

## Authentication

All requests require this header:
```
X-API-Key: {{AGENT_API_KEY}}
```

---

## 1. Draft a Document (async)

Draft a new DOCX from natural-language instructions. Produces contracts, policies, memoranda, engagement letters, term sheets, opinions, press releases, and similar.

**Include a detailed `instructions` field for optimal results.** A rich prompt (parties, dates, key terms, tone, length, intended audience) produces a much better document than a one-line ask. If you only have a short prompt from the user, either ask a follow-up question to enrich it, or use §2 Markdown → DOCX for a simpler path.

**Method:** POST
**Endpoint:** `/api/documents/draft`
**Content-Type:** `application/json`

```json
{
  "instructions": "Draft a mutual non-disclosure agreement between Company A (disclosing party) and Company B (receiving party). Two-year term, standard carve-outs.",
  "document_type": "agreement"
}
```

| Field           | Required | Description                                                                                 |
| --------------- | -------- | ------------------------------------------------------------------------------------------- |
| `instructions`  | Yes      | Detailed natural-language description. Richer context produces better output.               |
| `document_type` | No       | Optional hint: `agreement`, `engagement_letter`, `memorandum`, `opinion`, `policy`, `press_release`, `term_sheet`, `other`. |

**Response (202 Accepted):**
```json
{
  "job_id": "a1b2c3d4-...",
  "status": "processing"
}
```

**IMPORTANT:** Do NOT wait for the response before replying to the user. Tell them you've submitted the request (quote the job id) and that you'll notify them when it's ready. A webhook system event arrives when the document is done.

Write JSON payloads to a file and pass them to curl with `--data-binary @file` to avoid escaping issues.

---

## 2. Convert Markdown → DOCX (sync)

Convert markdown text to a DOCX file. Useful when you have generated content as markdown and want to deliver it as a Word document.

**Method:** POST
**Endpoint:** `/api/documents/markdown-to-docx`
**Content-Type:** `application/json`

```json
{
  "markdown": "# Heading\n\nSome body text...",
  "filename": "notes"
}
```

Response returns `{ job_id, status: "completed", filename, download_url }`. Proceed directly to the download flow (§4).

---

## 3. Convert DOCX → Markdown (sync)

Convert a DOCX file to markdown text. Useful when the user wants to read or edit a Word document's contents as plain text.

**Method:** POST
**Endpoint:** `/api/documents/docx-to-markdown`
**Content-Type:** `multipart/form-data`

```bash
curl -X POST "{{DOCX_AGENT_URL}}/api/documents/docx-to-markdown" \
  -H "X-API-Key: {{AGENT_API_KEY}}" \
  -F "file=@/path/to/contract.docx"
```

Response returns `{ job_id, status: "completed", filename, download_url }`. Proceed to §4.

---

## 4. Download and deliver

Same flow for every operation above.

**Method:** GET
**Endpoint:** `/api/documents/:id/download`

### Agent procedure

1. **Parse** the `download_url` from the response (sync) or the webhook text (async).
2. **Save** the file into your workspace:
   ```bash
   mkdir -p /tmp/workspace/{{AGENT_SLUG}}
   curl -o /tmp/workspace/{{AGENT_SLUG}}/document.docx <download_url>
   ```
3. **Send** the file to the user via the message tool using `filePath` — never paste contents into chat, never send the download URL as text.

## Context variables

- `{{DOCX_AGENT_URL}}` — base URL of the DOCX service
- `{{AGENT_API_KEY}}` — API key this agent uses to authenticate
- `{{AGENT_SLUG}}` — this agent's slug, for workspace path segmentation

Attribution

ThomasMoreAIThomasMoreAI
View sourceSee grades on GitHubMore from ThomasMoreAI →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →