Skip to content
Agentmart
Submit a tool

doc-specialist

Generate specialized Claude agents from scraped documentation libraries.

Skill by webcomunicasolutions

IndexedMIT
Write a review

Chalk Labs

Need help deploying doc-specialist?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/webcomunicasolutions-doc-specialist

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate specialized Claude agents from scraped documentation libraries. Automates the flow from docs → agent template with full library references.

Use cases: documents, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/doc-specialist

What's inside

Skill name
doc-specialist
Description
Generate specialized Claude agents from scraped documentation libraries. Automates the flow from docs → agent template with full library references.
License
MIT
Instructions
68 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • generate_specialist.py · scripts/
  • specialist_base.md · templates/

SKILL.md (first lines)

# Doc Specialist - Agent Generator from Documentation Libraries

Generate specialized Claude agent templates from any scraped documentation library in `biblioteca/`.

## Decision Tree

1. **User wants to generate an agent from docs** → Run `generate_specialist.py`
2. **User wants to consult library docs directly** → Read files from `biblioteca/` folder
3. **User just finished scraping** → Suggest generating an agent

## Usage

### Generate a specialist agent from a library folder

```bash
python3 ~/.claude/skills/doc-specialist/scripts/generate_specialist.py \
  "~/docs/biblioteca/elevenlabs-agents-platform" \
  --name "ElevenLabs Specialist" \
  --lang es
```

### Options

| Flag | Description | Default |
|------|-------------|---------|
| `PATH` (positional) | Library folder path (required) | - |
| `-o, --output` | Output JSON path | `~/.claude/agent-templates/{name}.json` |
| `--name` | Agent name | Auto-detected from folder name |
| `--lang` | Language (es/en) | es |
| `--tools` | Comma-separated tools | Read,Grep,Glob,WebSearch,WebFetch,Bash |

### Output

A JSON file compatible with Claude Code agent format:
```json
{
  "name": "Agent Name",
  "description": "Auto-generated description",
  "instructions": "Full system prompt with library references",
  "tools": ["Read", "Grep", "Glob", "WebSearch", "WebFetch", "Bash"]
}
```

## Integration with web-scraper skill

1. Scrape docs: `python3 ~/.claude/skills/web-scraper/scripts/scrape_docs.py URL -o biblioteca/nombre/`
2. Generate agent: `python3 ~/.claude/skills/doc-specialist/scripts/generate_specialist.py biblioteca/nombre/`
3. Use agent in any project by copying the JSON to `.claude/agents/`

## Library Format Expected

The script expects the output format from `web-scraper` skill:
- `INDEX.md` - Categorized index of pages
- `index.json` - Metadata (URLs, titles, filenames)
- `FULL_DOCS.md` - All pages consolidated
- `*.md` - Individual page files


## Auto-mejora

Al cerrar cada aplicacion practica de esta skill:
1. Registrar aprendizajes en `aprendizajes/<caso>.md` (o en esta seccion si es breve)
2. Si el patron es generalizable, actualizar el cuerpo de este SKILL.md
3. Si se descubre un error recurrente, anadirlo a una seccion de "Errores conocidos"

Sin esta fase, la skill se fosiliza y pierde valor con el tiempo.

From webcomunicasolutions/claude-code-toolkit, MIT.

More from webcomunicasolutions/claude-code-toolkit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from webcomunicasolutions

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get doc-specialist running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying doc-specialist?

CallGet help
Cite this page

doc-specialist skill. Agent Mart. https://agentmart.dev/skills/webcomunicasolutions-doc-specialist (last updated 2026-10-24)