Skip to main content
ClaudeWave
Skill235 estrellas del repoactualizado 3d ago

nudocs

I'll write a blog post about remote work and send it to Nudocs for you. [creates markdown content with clear structure and headings] Running: nudocs upload blog-post.md Result: https://nudocs.ai/docs/ulid-here/edit The blog post is ready for editing! You can access it here: https://nudocs.ai/docs/ulid-here/edit Share this link with anyone you'd like to collaborate with. User: What did I change? Assistant: Let me pull the updated document. Running: nudocs pull ulid-here --format docx [reads downloaded content] Here's what you changed: - Shortened the intro paragraph... - Added a new section on... - Reorganized the conclusion... ``` ## Troubleshooting | Error | Solution | |-------|----------| | API key not found | Verify key is set in environment or `~/.config/nudocs/api_key` | | "File not found" | Ensure file path is correct and file exists | | Rate limit exceeded | Wait 60s before retry |

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/jdrhyne/agent-skills /tmp/nudocs && cp -r /tmp/nudocs/skills/nudocs ~/.claude/skills/nudocs
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Nudocs

Upload documents to Nudocs.ai for rich editing, get shareable links, and pull back the results.

## Setup

1. Install the CLI using the repo's declared install metadata or your preferred package manager before first use.

2. Get your API key from https://nudocs.ai (click "Integration" after signing in)

3. Configure the key:
```bash
# Option 1: Environment variable
export NUDOCS_API_KEY="nudocs_your_key_here"

# Option 2: Config file
mkdir -p ~/.config/nudocs
echo "nudocs_your_key_here" > ~/.config/nudocs/api_key
```

## Commands

```bash
nudocs upload <file>              # Upload and get edit link
nudocs list                       # List all documents
nudocs link [ulid]                # Get edit link (last upload if no ULID)
nudocs pull [ulid] [--format fmt] # Download document (default: docx)
nudocs delete <ulid>              # Delete a document
nudocs config                     # Show configuration
```

## Workflow

### Upload Flow
1. Create/write document content
2. Save as markdown (or other supported format)
3. Run: `nudocs upload <file>`
4. Share the returned edit link with user

### Pull Flow
1. User requests document back
2. Run: `nudocs pull [ulid] --format <fmt>`
3. Read and present the downloaded file

### Format Selection

| Scenario | Recommended Format |
|----------|-------------------|
| User edited with rich formatting | `docx` (default) |
| Simple text/code content | `md` |
| Final delivery/sharing | `pdf` |

See `formats.md` in this skill's `references` folder for full format support.

## Natural Language Triggers

Recognize these user intents:

**Upload/Send:**
- "send to nudocs"
- "upload to nudocs"  
- "open in nudocs"
- "edit this in nudocs"
- "let me edit this in nudocs"
- "put this in nudocs"

**Pull/Fetch:**
- "pull it back"
- "pull from nudocs"
- "get that doc"
- "fetch from nudocs"
- "download from nudocs"
- "grab the updated version"
- "what did I change"
- "get my edits"

**Link:**
- "get the nudocs link"
- "share link"
- "where's that doc"
- "nudocs url"

**List:**
- "show my nudocs"
- "list my documents"
- "what docs do I have"
- "my nudocs documents"

## Document Best Practices

Before uploading, ensure good structure:
- Clear heading hierarchy (H1 → H2 → H3)
- Consistent spacing
- Appropriate list formatting
- Concise paragraphs (3-5 sentences)

See `document-design.md` in this skill's `references` folder for templates and guidelines.

## Example Session

```
User: Write me a blog post about remote work and send it to Nudocs

Agent:
1. Writes blog-remote-work.md with proper structure
2. Runs: nudocs upload blog-remote-work.md
3. Returns: "Here's your Nudocs link: https://nudocs.ai/file/01ABC..."

User: *edits in Nudocs, adds formatting, images*
User: Pull that back

Agent:
1. Runs: nudocs pull --format docx
2. Reads the downloaded file
3. Returns: "Got your updated document! Here's what changed..."
```

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| "No API key found" | Missing credentials | Set NUDOCS_API_KEY or create config file |
| "DOCUMENT_LIMIT_REACHED" | Free tier limit (10 docs) | Delete old docs or upgrade to Pro |
| "Unauthorized" | Invalid API key | Regenerate key in Nudocs settings |
| "No ULID provided" | Missing document ID | Specify ULID or upload a doc first |

## Links

- CLI: https://github.com/PSPDFKit/nudocs-cli (`@nutrient-sdk/nudocs-cli` on npm)
- MCP integration repo: https://github.com/PSPDFKit/nudocs-mcp-server
- Nudocs: https://nudocs.ai

## Safety Boundaries

- Do not upload sensitive documents unless the user confirmed that third-party processing is acceptable.
- Do not print API keys, edit links meant to stay private, or document contents the user did not ask to expose.
- Do not delete documents from Nudocs without explicit confirmation.
- Do not assume the default download format is correct; confirm the output format when it matters.
auto-updaterSkill

Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.

clawdbot-release-checkSkill

Check for new OpenClaw releases and notify once per new version.

clawddocsSkill

OpenClaw documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all OpenClaw features

gallery-scraperSkill

Bulk download images from login-protected gallery websites using an attached browser session. Use when asked to scrape, download, or save images from authenticated gallery pages, extract full-size images from thumbnails, or batch download from multi-page galleries.

knowledge-graphSkill

Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.

self-improving-agentSkill

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

skill-syncSkill

Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.

todo-trackerSkill

Persistent TODO scratch pad for tracking tasks across sessions. Use when user says "add to TODO", "what's on the TODO", "mark X done", "show TODO list", "remove from TODO", or asks about pending tasks. Also triggers on heartbeat to remind about stale items.